Publications
OUR RESEARCH
Scientific Publications
Here you can find the comprehensive list of publications from the members of the Research Center on Computer Vision and eXtended Reality (xRAI).
Use the tag cloud to filter papers based on specific research topics, or use the menus to filter by year, type of publication, or authors.
For each paper, you have the option to view additional details such as the Abstract, Links, and BibTex record.
Research is formalized curiosity. It is poking and prying with a purpose
Zora Neale Hurston
2019
Becattini, Federico; Seidenari, Lorenzo; Berlincioni, Lorenzo; Galteri, Leonardo; Bimbo, Alberto Del
Vehicle trajectories from unlabeled data through iterative plane registration Proceedings Article
In: Image Analysis and Processing–ICIAP 2019: 20th International Conference, Trento, Italy, September 9–13, 2019, Proceedings, Part I 20, pp. 60–70, Springer International Publishing, 2019, ISBN: 3-030-30641-0, (tex.copyright: All rights reserved).
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Autonomous Driving, Computer Vision and Pattern Recognition, Plane Registration, Semantic Segmentation, Trajectory Prediction, Urban Planning
@inproceedings{becattiniVehicleTrajectoriesUnlabeled2019,
title = {Vehicle trajectories from unlabeled data through iterative plane registration},
author = {Federico Becattini and Lorenzo Seidenari and Lorenzo Berlincioni and Leonardo Galteri and Alberto Del Bimbo},
url = {https://link.springer.com/chapter/10.1007/978-3-030-30642-7_6},
doi = {10.1007/978-3-030-30642-7_6},
isbn = {3-030-30641-0},
year = {2019},
date = {2019-01-01},
booktitle = {Image Analysis and Processing–ICIAP 2019: 20th International Conference, Trento, Italy, September 9–13, 2019, Proceedings, Part I 20},
pages = {60–70},
publisher = {Springer International Publishing},
abstract = {One of the most complex aspects of autonomous driving concerns understanding the surrounding environment. In particular, the interest falls on detecting which agents are populating it and how they are moving. The capacity to predict how these may act in the near future would allow an autonomous vehicle to safely plan its trajectory, minimizing the risks for itself and others. In this work we propose an automatic trajectory annotation method exploiting an Iterative Plane Registration algorithm based on homographies and semantic segmentations. The output of our technique is a set of holistic trajectories (past-present-future) paired with a single image context, useful to train a predictive model.},
note = {tex.copyright: All rights reserved},
keywords = {Artificial Intelligence, Autonomous Driving, Computer Vision and Pattern Recognition, Plane Registration, Semantic Segmentation, Trajectory Prediction, Urban Planning},
pubstate = {published},
tppubtype = {inproceedings}
}
One of the most complex aspects of autonomous driving concerns understanding the surrounding environment. In particular, the interest falls on detecting which agents are populating it and how they are moving. The capacity to predict how these may act in the near future would allow an autonomous vehicle to safely plan its trajectory, minimizing the risks for itself and others. In this work we propose an automatic trajectory annotation method exploiting an Iterative Plane Registration algorithm based on homographies and semantic segmentations. The output of our technique is a set of holistic trajectories (past-present-future) paired with a single image context, useful to train a predictive model.
Galteri, Leonardo; Seidenari, Lorenzo; Bertini, Marco; Bimbo, Alberto Del
Towards real-time image enhancement GANs Proceedings Article
In: Computer Analysis of Images and Patterns: 18th International Conference, CAIP 2019, Salerno, Italy, September 3–5, 2019, Proceedings, Part I 18, pp. 183–195, Springer International Publishing, 2019, ISBN: 3-030-29887-6, (tex.copyright: All rights reserved).
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Compression Artifact Removal, Computer Vision and Pattern Recognition, Generative Adversarial Networks, Image Synthesis and Enhancement, Real-time Video Processing, Video Summarization
@inproceedings{galteriRealtimeImageEnhancement2019,
title = {Towards real-time image enhancement GANs},
author = {Leonardo Galteri and Lorenzo Seidenari and Marco Bertini and Alberto Del Bimbo},
url = {https://link.springer.com/chapter/10.1007/978-3-030-29888-3_15},
doi = {10.1007/978-3-030-29888-3_15},
isbn = {3-030-29887-6},
year = {2019},
date = {2019-01-01},
booktitle = {Computer Analysis of Images and Patterns: 18th International Conference, CAIP 2019, Salerno, Italy, September 3–5, 2019, Proceedings, Part I 18},
pages = {183–195},
publisher = {Springer International Publishing},
abstract = {Video stream compression, using lossy algorithms, is performed to reduce the bandwidth required for transmission. To improve the video quality, either for human view or for automatic video analysis, videos are post-processed to eliminate the introduced compression artifacts. Generative Adversarial Network have been shown to obtain extremely high quality results in image enhancement tasks; however, to obtain top quality results high capacity large generators are usually employed, resulting in high computational costs and processing time. In this paper we present an architecture that can be used to reduce the cost of generators, paving a way towards real-time frame enhancement with GANs. With the proposed approach, enhanced images appear natural and pleasant to the eye. Locally high frequency patterns often differ from the raw uncompressed images. A possible application is to improve video conferencing, or live streaming. In these cases there is no original uncompressed video stream available. Therefore, we report results using popular no-reference metrics showing high naturalness and quality even for efficient networks.},
note = {tex.copyright: All rights reserved},
keywords = {Artificial Intelligence, Compression Artifact Removal, Computer Vision and Pattern Recognition, Generative Adversarial Networks, Image Synthesis and Enhancement, Real-time Video Processing, Video Summarization},
pubstate = {published},
tppubtype = {inproceedings}
}
Video stream compression, using lossy algorithms, is performed to reduce the bandwidth required for transmission. To improve the video quality, either for human view or for automatic video analysis, videos are post-processed to eliminate the introduced compression artifacts. Generative Adversarial Network have been shown to obtain extremely high quality results in image enhancement tasks; however, to obtain top quality results high capacity large generators are usually employed, resulting in high computational costs and processing time. In this paper we present an architecture that can be used to reduce the cost of generators, paving a way towards real-time frame enhancement with GANs. With the proposed approach, enhanced images appear natural and pleasant to the eye. Locally high frequency patterns often differ from the raw uncompressed images. A possible application is to improve video conferencing, or live streaming. In these cases there is no original uncompressed video stream available. Therefore, we report results using popular no-reference metrics showing high naturalness and quality even for efficient networks.
Galteri, Leonardo; Seidenari, Lorenzo; Bertini, Marco; Uricchio, Tiberio; Bimbo, Alberto Del
Fast video quality enhancement using gans Proceedings Article
In: Proceedings of the 27th ACM international conference on multimedia, pp. 1065–1067, 2019, (tex.copyright: All rights reserved).
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Compression Artifact Removal, Computer Vision and Pattern Recognition, Generative Adversarial Networks, Image Synthesis and Enhancement, Real-time Video Processing, Video Streaming
@inproceedings{galteriFastVideoQuality2019,
title = {Fast video quality enhancement using gans},
author = {Leonardo Galteri and Lorenzo Seidenari and Marco Bertini and Tiberio Uricchio and Alberto Del Bimbo},
url = {https://dl.acm.org/doi/abs/10.1145/3343031.3350592},
doi = {10.1145/3343031.3350592},
year = {2019},
date = {2019-01-01},
booktitle = {Proceedings of the 27th ACM international conference on multimedia},
pages = {1065–1067},
abstract = {Video compression algorithms result in a reduction of image quality, because of their lossy approach to reduce the required bandwidth. This affects commercial streaming services such as Netflix, or Amazon Prime Video, but affects also video conferencing and video surveillance systems. In all these cases it is possible to improve the video quality, both for human view and for automatic video analysis, without changing the compression pipeline, through a post-processing that eliminates the visual artifacts created by the compression algorithms. Generative Adversarial Networks have obtained extremely high quality results in image enhancement tasks; however, to obtain such results large generators are usually employed, resulting in high computational costs and processing time. In this work we present an architecture that can be used to reduce the computational cost and that has been implemented on mobile devices. A possible application is to improve video conferencing, or live streaming. In these cases there is no original uncompressed video stream available. Therefore, we report results using no-reference video quality metric showing high naturalness and quality even for efficient networks.},
note = {tex.copyright: All rights reserved},
keywords = {Artificial Intelligence, Compression Artifact Removal, Computer Vision and Pattern Recognition, Generative Adversarial Networks, Image Synthesis and Enhancement, Real-time Video Processing, Video Streaming},
pubstate = {published},
tppubtype = {inproceedings}
}
Video compression algorithms result in a reduction of image quality, because of their lossy approach to reduce the required bandwidth. This affects commercial streaming services such as Netflix, or Amazon Prime Video, but affects also video conferencing and video surveillance systems. In all these cases it is possible to improve the video quality, both for human view and for automatic video analysis, without changing the compression pipeline, through a post-processing that eliminates the visual artifacts created by the compression algorithms. Generative Adversarial Networks have obtained extremely high quality results in image enhancement tasks; however, to obtain such results large generators are usually employed, resulting in high computational costs and processing time. In this work we present an architecture that can be used to reduce the computational cost and that has been implemented on mobile devices. A possible application is to improve video conferencing, or live streaming. In these cases there is no original uncompressed video stream available. Therefore, we report results using no-reference video quality metric showing high naturalness and quality even for efficient networks.
Galteri, Leonardo; Ferrari, Claudio; Lisanti, Giuseppe; Berretti, Stefano; Bimbo, Alberto Del
Deep 3d morphable model refinement via progressive growing of conditional generative adversarial networks Journal Article
In: Computer Vision and Image Understanding, vol. 185, pp. 31–42, 2019, (ISBN: 1077-3142 tex.copyright: All rights reserved).
Abstract | Links | BibTeX | Tags: 3D Face Reconstruction, 3D Morphable Models, Artificial Intelligence, Computer Vision and Pattern Recognition, Digital Reconstruction, Generative Adversarial Networks, Image Synthesis and Enhancement
@article{galteriDeep3dMorphable2019,
title = {Deep 3d morphable model refinement via progressive growing of conditional generative adversarial networks},
author = {Leonardo Galteri and Claudio Ferrari and Giuseppe Lisanti and Stefano Berretti and Alberto Del Bimbo},
url = {https://www.sciencedirect.com/science/article/abs/pii/S1077314219300773},
doi = {10.1016/j.cviu.2019.05.002},
year = {2019},
date = {2019-01-01},
journal = {Computer Vision and Image Understanding},
volume = {185},
pages = {31–42},
publisher = {Academic Press},
abstract = {3D face reconstruction from a single 2D image is a fundamental Computer Vision problem of extraordinary difficulty. Statistical modeling techniques, such as the 3D Morphable Model (3DMM), have been widely exploited because of their capability of reconstructing a plausible model grounding on the prior knowledge of the facial shape. However, most of these techniques derive an approximated and smooth reconstruction of the face, without accounting for fine-grained details. In this work, we propose an approach based on a Conditional Generative Adversarial Network (CGAN) for refining the coarse reconstruction provided by a 3DMM. The latter is represented as a three channels image, where the pixel intensities represent the depth, curvature and elevation values of the 3D vertices. The architecture is an encoder–decoder, which is trained progressively, starting from the lower-resolution layers; this technique allows a more stable training, which leads to the generation of high quality outputs even when high-resolution images are fed during the training. Experimental results show that our method is able to produce reconstructions with fine-grained realistic details and lower reconstruction errors with respect to the 3DMM. A cross-dataset evaluation also shows that the network retains good generalization capabilities. Finally, comparison with state-of-the-art solutions evidence competitive performance, with comparable or lower error in most of the cases, and a clear improvement in the quality of the generated models.},
note = {ISBN: 1077-3142
tex.copyright: All rights reserved},
keywords = {3D Face Reconstruction, 3D Morphable Models, Artificial Intelligence, Computer Vision and Pattern Recognition, Digital Reconstruction, Generative Adversarial Networks, Image Synthesis and Enhancement},
pubstate = {published},
tppubtype = {article}
}
3D face reconstruction from a single 2D image is a fundamental Computer Vision problem of extraordinary difficulty. Statistical modeling techniques, such as the 3D Morphable Model (3DMM), have been widely exploited because of their capability of reconstructing a plausible model grounding on the prior knowledge of the facial shape. However, most of these techniques derive an approximated and smooth reconstruction of the face, without accounting for fine-grained details. In this work, we propose an approach based on a Conditional Generative Adversarial Network (CGAN) for refining the coarse reconstruction provided by a 3DMM. The latter is represented as a three channels image, where the pixel intensities represent the depth, curvature and elevation values of the 3D vertices. The architecture is an encoder–decoder, which is trained progressively, starting from the lower-resolution layers; this technique allows a more stable training, which leads to the generation of high quality outputs even when high-resolution images are fed during the training. Experimental results show that our method is able to produce reconstructions with fine-grained realistic details and lower reconstruction errors with respect to the 3DMM. A cross-dataset evaluation also shows that the network retains good generalization capabilities. Finally, comparison with state-of-the-art solutions evidence competitive performance, with comparable or lower error in most of the cases, and a clear improvement in the quality of the generated models.
Galteri, Leonardo; Ferrari, Claudio; Lisanti, Giuseppe; Berretti, Stefano; Bimbo, Alberto Del
Coarse-to-fine 3D face reconstruction Proceedings Article
In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 25–31, 2019, (tex.copyright: All rights reserved).
Abstract | Links | BibTeX | Tags: 3D Face Reconstruction, 3D Morphable Models, Artificial Intelligence, Computer Vision and Pattern Recognition, Digital Reconstruction, Generative Adversarial Networks, Image Synthesis and Enhancement
@inproceedings{galteriCoarsetofine3DFace2019,
title = {Coarse-to-fine 3D face reconstruction},
author = {Leonardo Galteri and Claudio Ferrari and Giuseppe Lisanti and Stefano Berretti and Alberto Del Bimbo},
url = {http://openaccess.thecvf.com/content_CVPRW_2019/papers/3D-WidDGET/Leonardo_Galteri_Coarse-to-Fine_3D_Face_Reconstruction_CVPRW_2019_paper.pdf},
doi = {Unavailable},
year = {2019},
date = {2019-01-01},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
pages = {25–31},
abstract = {Reconstructing accurate 3D shapes of human faces from a single 2D image is a highly challenging Computer Vision problem that is studied since decades. Statistical modeling techniques, such as the 3D Morphable Model (3DMM), have been widely employed because of their capability of reconstructing a plausible model grounding on the prior knowledge of the facial shape. However, most of them derive a and smooth approximation of the real shape, without accounting for the surface details. In this work, we propose an approach based on a Conditional Generative Adversarial Network (CGAN) for refining the reconstruction provided by a 3DMM. The latter is represented as a three-channel image, where the pixel intensities represent, respectively, the depth and the azimuth and elevation angles of the surface normals. The network architecture is an encoder-decoder, which is trained progressively, starting from the lower-resolution layers; this technique allows a more stable training, which led to the generation of high-quality outputs even when high-resolution images are fed during the training. Experimental results show that our method is able to produce detailed realistic reconstructions and obtain lower errors with respect to the 3DMM. Finally, a comparison with a state-of-the-art solution evidences competitive performance and a clear improvement in the quality of the generated models.},
note = {tex.copyright: All rights reserved},
keywords = {3D Face Reconstruction, 3D Morphable Models, Artificial Intelligence, Computer Vision and Pattern Recognition, Digital Reconstruction, Generative Adversarial Networks, Image Synthesis and Enhancement},
pubstate = {published},
tppubtype = {inproceedings}
}
Reconstructing accurate 3D shapes of human faces from a single 2D image is a highly challenging Computer Vision problem that is studied since decades. Statistical modeling techniques, such as the 3D Morphable Model (3DMM), have been widely employed because of their capability of reconstructing a plausible model grounding on the prior knowledge of the facial shape. However, most of them derive a and smooth approximation of the real shape, without accounting for the surface details. In this work, we propose an approach based on a Conditional Generative Adversarial Network (CGAN) for refining the reconstruction provided by a 3DMM. The latter is represented as a three-channel image, where the pixel intensities represent, respectively, the depth and the azimuth and elevation angles of the surface normals. The network architecture is an encoder-decoder, which is trained progressively, starting from the lower-resolution layers; this technique allows a more stable training, which led to the generation of high-quality outputs even when high-resolution images are fed during the training. Experimental results show that our method is able to produce detailed realistic reconstructions and obtain lower errors with respect to the 3DMM. Finally, a comparison with a state-of-the-art solution evidences competitive performance and a clear improvement in the quality of the generated models.
Galteri, Leonardo; Ferrari, Claudio; Lisanti, Giuseppe; Berretti, Stefano; Bimbo, Alberto Del
Coarse to Fine 3D Face Reconstruction from Single Image Proceedings Article
In: 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019), pp. 1–1, IEEE, 2019, ISBN: 1-7281-0089-5, (tex.copyright: All rights reserved).
Abstract | Links | BibTeX | Tags: 3D Face Reconstruction, 3D Morphable Models, Artificial Intelligence, Computer Vision and Pattern Recognition, Digital Reconstruction, Generative Adversarial Networks, Image Synthesis and Enhancement
@inproceedings{galteriCoarseFine3D2019,
title = {Coarse to Fine 3D Face Reconstruction from Single Image},
author = {Leonardo Galteri and Claudio Ferrari and Giuseppe Lisanti and Stefano Berretti and Alberto Del Bimbo},
url = {https://ieeexplore.ieee.org/abstract/document/8756603},
doi = {10.1109/FG.2019.8756603},
isbn = {1-7281-0089-5},
year = {2019},
date = {2019-01-01},
booktitle = {2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019)},
pages = {1–1},
publisher = {IEEE},
abstract = {In this demo we propose a coarse to fine reconstruction pipeline, which takes a single RGB image as input and outputs a detailed 3D model of the face. The pipeline is composed by two main blocks, the coarse reconstruction block, which is based on a 3D Morphable Model, and the refinement block, which instead grounds on a Generative Adversarial Network (GAN).},
note = {tex.copyright: All rights reserved},
keywords = {3D Face Reconstruction, 3D Morphable Models, Artificial Intelligence, Computer Vision and Pattern Recognition, Digital Reconstruction, Generative Adversarial Networks, Image Synthesis and Enhancement},
pubstate = {published},
tppubtype = {inproceedings}
}
In this demo we propose a coarse to fine reconstruction pipeline, which takes a single RGB image as input and outputs a detailed 3D model of the face. The pipeline is composed by two main blocks, the coarse reconstruction block, which is based on a 3D Morphable Model, and the refinement block, which instead grounds on a Generative Adversarial Network (GAN).
Amerini, Irene; Galteri, Leonardo; Caldelli, Roberto; Bimbo, Alberto Del
Deepfake video detection through optical flow based cnn Proceedings Article
In: Proceedings of the IEEE/CVF international conference on computer vision workshops, pp. 0–0, 2019, (tex.copyright: All rights reserved).
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Civil Security for Society, Computer Vision and Pattern Recognition, Cybersecurity, Deepfake Detection, Digital Media Integrity, Information Systems, Optical Flow, Video Forensics
@inproceedings{ameriniDeepfakeVideoDetection2019,
title = {Deepfake video detection through optical flow based cnn},
author = {Irene Amerini and Leonardo Galteri and Roberto Caldelli and Alberto Del Bimbo},
url = {http://openaccess.thecvf.com/content_ICCVW_2019/papers/HBU/Amerini_Deepfake_Video_Detection_through_Optical_Flow_Based_CNN_ICCVW_2019_paper.pdf},
doi = {10.1109/ICCVW.2019.00152},
year = {2019},
date = {2019-01-01},
booktitle = {Proceedings of the IEEE/CVF international conference on computer vision workshops},
pages = {0–0},
abstract = {Recent advances in visual media technology have led to new tools for processing and, above all, generating multimedia contents. In particular, modern AI-based technologies have provided easy-to-use tools to create extremely realistic manipulated videos. Such synthetic videos, named Deep Fakes, may constitute a serious threat to attack the reputation of public subjects or to address the general opinion on a certain event. According to this, being able to individuate this kind of fake information becomes fundamental. In this work, a new forensic technique able to discern between fake and original video sequences is given; unlike other state-of-the-art methods which resorts at single video frames, we propose the adoption of optical flow fields to exploit possible inter-frame dissimilarities. Such a clue is then used as feature to be learned by CNN classifiers. Preliminary results obtained on FaceForensics++ dataset highlight very promising performances.},
note = {tex.copyright: All rights reserved},
keywords = {Artificial Intelligence, Civil Security for Society, Computer Vision and Pattern Recognition, Cybersecurity, Deepfake Detection, Digital Media Integrity, Information Systems, Optical Flow, Video Forensics},
pubstate = {published},
tppubtype = {inproceedings}
}
Recent advances in visual media technology have led to new tools for processing and, above all, generating multimedia contents. In particular, modern AI-based technologies have provided easy-to-use tools to create extremely realistic manipulated videos. Such synthetic videos, named Deep Fakes, may constitute a serious threat to attack the reputation of public subjects or to address the general opinion on a certain event. According to this, being able to individuate this kind of fake information becomes fundamental. In this work, a new forensic technique able to discern between fake and original video sequences is given; unlike other state-of-the-art methods which resorts at single video frames, we propose the adoption of optical flow fields to exploit possible inter-frame dissimilarities. Such a clue is then used as feature to be learned by CNN classifiers. Preliminary results obtained on FaceForensics++ dataset highlight very promising performances.
Caggianese, Giuseppe; Cuomo, Salvatore; Esposito, Massimo; Franceschini, Marco; Gallo, Luigi; Infarinato, Francesco; Minutolo, Aniello; Piccialli, Francesco; Romano, Paola
Serious Games and In-Cloud Data Analytics for the Virtualization and Personalization of Rehabilitation Treatments Journal Article
In: IEEE Transactions on Industrial Informatics, vol. 15, no. 1, pp. 517–526, 2019, ISSN: 1941-0050.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Healthcare, Human Computer Interaction, Natural User Interfaces, Rehabilitation, Serious game, Stroke
@article{caggianeseSeriousGamesInCloud2019,
title = {Serious Games and In-Cloud Data Analytics for the Virtualization and Personalization of Rehabilitation Treatments},
author = {Giuseppe Caggianese and Salvatore Cuomo and Massimo Esposito and Marco Franceschini and Luigi Gallo and Francesco Infarinato and Aniello Minutolo and Francesco Piccialli and Paola Romano},
doi = {10.1109/TII.2018.2856097},
issn = {1941-0050},
year = {2019},
date = {2019-01-01},
journal = {IEEE Transactions on Industrial Informatics},
volume = {15},
number = {1},
pages = {517–526},
abstract = {During the last years, the significant increase in the number of patients in need of rehabilitation has generated an unsustainable economic impact on healthcare systems, implying a reduction in therapeutic supervision and support for each patient. To address this problem, this paper proposes a telerehabilitation system based on serious games and in-cloud data analytics services, in accordance with Industry 4.0 design principles regarding modularity, service orientation, decentralization, virtualization, and real-time capability. The system, specialized for poststroke patients, comprises components for real-time acquisition of patient's motor data and a decision support service for their analysis. Raw data, reports, and recommendations are made available on the cloud to clinical operators to remotely assess rehabilitation outcomes and dynamically improve therapies. Furthermore, the results of a pilot study on the clinical impact deriving from the adoption of the proposed solution, and of a qualitative analysis about its acceptance, are presented and discussed.},
keywords = {Artificial Intelligence, Healthcare, Human Computer Interaction, Natural User Interfaces, Rehabilitation, Serious game, Stroke},
pubstate = {published},
tppubtype = {article}
}
During the last years, the significant increase in the number of patients in need of rehabilitation has generated an unsustainable economic impact on healthcare systems, implying a reduction in therapeutic supervision and support for each patient. To address this problem, this paper proposes a telerehabilitation system based on serious games and in-cloud data analytics services, in accordance with Industry 4.0 design principles regarding modularity, service orientation, decentralization, virtualization, and real-time capability. The system, specialized for poststroke patients, comprises components for real-time acquisition of patient's motor data and a decision support service for their analysis. Raw data, reports, and recommendations are made available on the cloud to clinical operators to remotely assess rehabilitation outcomes and dynamically improve therapies. Furthermore, the results of a pilot study on the clinical impact deriving from the adoption of the proposed solution, and of a qualitative analysis about its acceptance, are presented and discussed.
Altieri, A.; Ceccacci, S.; Ciabattoni, L.; Generosi, Andrea; Talipu, A.; Turri, G.; Mengoni, M.
An Adaptive System to Manage Playlists and Lighting Scenarios Based on the User’s Emotions Proceedings Article
In: 2019 IEEE International Conference on Consumer Electronics (ICCE), pp. 1–2, IEEE, Las Vegas, NV, USA, 2019, ISBN: 978-1-5386-7910-4.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Emotion Recognition, Machine Learning, User experience
@inproceedings{altieri_adaptive_2019,
title = {An Adaptive System to Manage Playlists and Lighting Scenarios Based on the User’s Emotions},
author = {A. Altieri and S. Ceccacci and L. Ciabattoni and Andrea Generosi and A. Talipu and G. Turri and M. Mengoni},
url = {https://ieeexplore.ieee.org/document/8662061/},
doi = {10.1109/ICCE.2019.8662061},
isbn = {978-1-5386-7910-4},
year = {2019},
date = {2019-01-01},
urldate = {2024-12-28},
booktitle = {2019 IEEE International Conference on Consumer Electronics (ICCE)},
pages = {1–2},
publisher = {IEEE},
address = {Las Vegas, NV, USA},
abstract = {This paper introduces a new system capable of adaptively managing multimedia contents (e.g. music, video clips, etc.) and lighting scenarios based on the detected user's emotional state. The system captures the emotion from the user's face expression mapping it into a 2D valence-arousal space where the multimedia content is mapped and matches them with lighting color. Results of preliminary tests suggest that the proposed system is able to detect the user's emotional state and manage proper music and light colors in a symbiotic way.},
keywords = {Artificial Intelligence, Emotion Recognition, Machine Learning, User experience},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper introduces a new system capable of adaptively managing multimedia contents (e.g. music, video clips, etc.) and lighting scenarios based on the detected user's emotional state. The system captures the emotion from the user's face expression mapping it into a 2D valence-arousal space where the multimedia content is mapped and matches them with lighting color. Results of preliminary tests suggest that the proposed system is able to detect the user's emotional state and manage proper music and light colors in a symbiotic way.
Talipu, A.; Generosi, Andrea; Mengoni, M.; Giraldi, L.
Evaluation of Deep Convolutional Neural Network architectures for Emotion Recognition in the Wild Proceedings Article
In: 2019 IEEE 23rd International Symposium on Consumer Technologies (ISCT), pp. 25–27, IEEE, Ancona, Italy, 2019, ISBN: 978-1-7281-3570-0.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Computer Vision and Pattern Recognition, Deep Learning, Emotion Recognition
@inproceedings{talipu_evaluation_2019,
title = {Evaluation of Deep Convolutional Neural Network architectures for Emotion Recognition in the Wild},
author = {A. Talipu and Andrea Generosi and M. Mengoni and L. Giraldi},
url = {https://ieeexplore.ieee.org/document/8900994/},
doi = {10.1109/ISCE.2019.8900994},
isbn = {978-1-7281-3570-0},
year = {2019},
date = {2019-01-01},
urldate = {2024-12-28},
booktitle = {2019 IEEE 23rd International Symposium on Consumer Technologies (ISCT)},
pages = {25–27},
publisher = {IEEE},
address = {Ancona, Italy},
abstract = {This paper presents a software based on an innovative Convolutional Neural Network model to recognize the six Ekman's universal emotions from the photos of human faces captured in the wild. The CNN was trained using three different datasets already labeled and merged after making them homogeneous. A comparison among different types of CNN architectures using the Keras framework for Python language is proposed and the evaluation results are presented.},
keywords = {Artificial Intelligence, Computer Vision and Pattern Recognition, Deep Learning, Emotion Recognition},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper presents a software based on an innovative Convolutional Neural Network model to recognize the six Ekman's universal emotions from the photos of human faces captured in the wild. The CNN was trained using three different datasets already labeled and merged after making them homogeneous. A comparison among different types of CNN architectures using the Keras framework for Python language is proposed and the evaluation results are presented.
Generosi, Andrea; Altieri, A.; Ceccacci, S.; Foresi, G.; Talipu, A.; Turri, G.; Mengoni, M.; Giraldi, L.
MoBeTrack: A Toolkit to Analyze User Experience of Mobile Apps in the Wild Proceedings Article
In: 2019 IEEE International Conference on Consumer Electronics (ICCE), pp. 1–2, IEEE, Las Vegas, NV, USA, 2019, ISBN: 978-1-5386-7910-4.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Deep Learning, User experience
@inproceedings{generosi_mobetrack_2019,
title = {MoBeTrack: A Toolkit to Analyze User Experience of Mobile Apps in the Wild},
author = {Andrea Generosi and A. Altieri and S. Ceccacci and G. Foresi and A. Talipu and G. Turri and M. Mengoni and L. Giraldi},
url = {https://ieeexplore.ieee.org/document/8662020/},
doi = {10.1109/ICCE.2019.8662020},
isbn = {978-1-5386-7910-4},
year = {2019},
date = {2019-01-01},
urldate = {2024-12-28},
booktitle = {2019 IEEE International Conference on Consumer Electronics (ICCE)},
pages = {1–2},
publisher = {IEEE},
address = {Las Vegas, NV, USA},
abstract = {MoBeTrack (Mobile Behaviour Tracking) is a toolkit for automated collection of data necessary to support User Experience (UX) assessment of mobile applications. In contrast to existing frameworks, it is able to collect user demographic information (i.e., age and gender), trace any user interaction and recognize user's emotions during the use of an application. An SDK for iOS allows to easily embedding the toolkit in every mobile application in a flexible and scalable way.},
keywords = {Artificial Intelligence, Deep Learning, User experience},
pubstate = {published},
tppubtype = {inproceedings}
}
MoBeTrack (Mobile Behaviour Tracking) is a toolkit for automated collection of data necessary to support User Experience (UX) assessment of mobile applications. In contrast to existing frameworks, it is able to collect user demographic information (i.e., age and gender), trace any user interaction and recognize user's emotions during the use of an application. An SDK for iOS allows to easily embedding the toolkit in every mobile application in a flexible and scalable way.
Caggianese, Giuseppe; Cuomo, Salvatore; Esposito, Massimo; Franceschini, Marco; Gallo, Luigi; Infarinato, Francesco; Minutolo, Aniello; Piccialli, Francesco; Romano, Paola
Serious Games and In-Cloud Data Analytics for the Virtualization and Personalization of Rehabilitation Treatments Journal Article
In: IEEE Transactions on Industrial Informatics, vol. 15, no. 1, pp. 517–526, 2019, ISSN: 1941-0050.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Healthcare, Human Computer Interaction, Natural User Interfaces, Rehabilitation, Serious game, Stroke
@article{caggianese_serious_2019,
title = {Serious Games and In-Cloud Data Analytics for the Virtualization and Personalization of Rehabilitation Treatments},
author = {Giuseppe Caggianese and Salvatore Cuomo and Massimo Esposito and Marco Franceschini and Luigi Gallo and Francesco Infarinato and Aniello Minutolo and Francesco Piccialli and Paola Romano},
doi = {10.1109/TII.2018.2856097},
issn = {1941-0050},
year = {2019},
date = {2019-01-01},
journal = {IEEE Transactions on Industrial Informatics},
volume = {15},
number = {1},
pages = {517–526},
abstract = {During the last years, the significant increase in the number of patients in need of rehabilitation has generated an unsustainable economic impact on healthcare systems, implying a reduction in therapeutic supervision and support for each patient. To address this problem, this paper proposes a telerehabilitation system based on serious games and in-cloud data analytics services, in accordance with Industry 4.0 design principles regarding modularity, service orientation, decentralization, virtualization, and real-time capability. The system, specialized for poststroke patients, comprises components for real-time acquisition of patient's motor data and a decision support service for their analysis. Raw data, reports, and recommendations are made available on the cloud to clinical operators to remotely assess rehabilitation outcomes and dynamically improve therapies. Furthermore, the results of a pilot study on the clinical impact deriving from the adoption of the proposed solution, and of a qualitative analysis about its acceptance, are presented and discussed.},
keywords = {Artificial Intelligence, Healthcare, Human Computer Interaction, Natural User Interfaces, Rehabilitation, Serious game, Stroke},
pubstate = {published},
tppubtype = {article}
}
During the last years, the significant increase in the number of patients in need of rehabilitation has generated an unsustainable economic impact on healthcare systems, implying a reduction in therapeutic supervision and support for each patient. To address this problem, this paper proposes a telerehabilitation system based on serious games and in-cloud data analytics services, in accordance with Industry 4.0 design principles regarding modularity, service orientation, decentralization, virtualization, and real-time capability. The system, specialized for poststroke patients, comprises components for real-time acquisition of patient's motor data and a decision support service for their analysis. Raw data, reports, and recommendations are made available on the cloud to clinical operators to remotely assess rehabilitation outcomes and dynamically improve therapies. Furthermore, the results of a pilot study on the clinical impact deriving from the adoption of the proposed solution, and of a qualitative analysis about its acceptance, are presented and discussed.
Altieri, A.; Ceccacci, S.; Ciabattoni, Lucio; Generosi, Andrea; Talipu, A.; Turri, G.; Mengoni, M.
An adaptive system to manage playlists and lighting scenarios based on the user's emotions Proceedings Article
In: Institute of Electrical and Electronics Engineers Inc., 2019, ISBN: 978-1-5386-7910-4, (Type: Conference paper tex.affiliations: Dipartimento di Ingegneria Industriale e Scienze Matematiche, Università Politecnica Delle Marche, Ancona, Italy; Dipartimento di Ingegneria dell'Informazione, Università Politecnica Delle Marche, Ancona, Italy tex.source: Scopus).
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Electronics engineering, Electronics industry, Emotion Recognition, Emotional state, Face expressions, Light color, Lighting, Machine Learning, Multimedia contents, User experience, Video clips
@inproceedings{Altieri2019,
title = {An adaptive system to manage playlists and lighting scenarios based on the user's emotions},
author = {A. Altieri and S. Ceccacci and Lucio Ciabattoni and Andrea Generosi and A. Talipu and G. Turri and M. Mengoni},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85063806248&doi=10.1109%2fICCE.2019.8662061&partnerID=40&md5=97e7957ed61b8628a4355743e790fd1f},
doi = {10.1109/ICCE.2019.8662061},
isbn = {978-1-5386-7910-4},
year = {2019},
date = {2019-01-01},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
series = {2019 IEEE International Conference on Consumer Electronics, ICCE 2019},
abstract = {This paper introduces a new system capable of adaptively managing multimedia contents (e.g. music, video clips, etc.) and lighting scenarios based on the detected user's emotional state. The system captures the emotion from the user's face expression mapping it into a 2D valence-arousal space where the multimedia content is mapped and matches them with lighting color. Results of preliminary tests suggest that the proposed system is able to detect the user's emotional state and manage proper music and light colors in a symbiotic way. © 2019 IEEE.},
note = {Type: Conference paper
tex.affiliations: Dipartimento di Ingegneria Industriale e Scienze Matematiche, Università Politecnica Delle Marche, Ancona, Italy; Dipartimento di Ingegneria dell'Informazione, Università Politecnica Delle Marche, Ancona, Italy
tex.source: Scopus},
keywords = {Artificial Intelligence, Electronics engineering, Electronics industry, Emotion Recognition, Emotional state, Face expressions, Light color, Lighting, Machine Learning, Multimedia contents, User experience, Video clips},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper introduces a new system capable of adaptively managing multimedia contents (e.g. music, video clips, etc.) and lighting scenarios based on the detected user's emotional state. The system captures the emotion from the user's face expression mapping it into a 2D valence-arousal space where the multimedia content is mapped and matches them with lighting color. Results of preliminary tests suggest that the proposed system is able to detect the user's emotional state and manage proper music and light colors in a symbiotic way. © 2019 IEEE.
Cristani, Matteo; Domenichini, Francesco; Tomazzoli, Claudio; Zorzi, Margherita
It Could Be Worse, It Could Be Raining: Reliable Automatic Meteorological Forecasting for Holiday Planning Proceedings Article
In: Proceedings of 32nd International Conference on Industrial, Engineering & Other Applications of Applied Intelligent Systems (IEA/AIE 2019), pp. 3–11, Springer, 2019, ISBN: 978-3-030-22998-6.
Abstract | Links | BibTeX | Tags: Automatic reasoning, Defeasible logic, Machine Learning, Non monotonic logic
@inproceedings{cristani_it_2019,
title = {It Could Be Worse, It Could Be Raining: Reliable Automatic Meteorological Forecasting for Holiday Planning},
author = {Matteo Cristani and Francesco Domenichini and Claudio Tomazzoli and Margherita Zorzi},
url = {https://link.springer.com/chapter/10.1007/978-3-030-22999-3_1},
doi = {10.1007/978-3-030-22999-3_1},
isbn = {978-3-030-22998-6},
year = {2019},
date = {2019-01-01},
booktitle = {Proceedings of 32nd International Conference on Industrial, Engineering & Other Applications of Applied Intelligent Systems (IEA/AIE 2019)},
volume = {11606},
pages = {3–11},
publisher = {Springer},
abstract = {Weather forecasting is a logical process that consists in evaluating the predictions provided by a set of stochastic models, compare these and take a conclusion about the weather in a given area and a given interval of time. Meteorological forecasting provides reliable predictions about the weather within a given interval of time. The automation of the forecasting process would be helpful in a number of contexts. For instance, when forecasting about underpopulated or small geographic areas is out of the human forecasters' tasks but is central, e.g., for tourism. In this paper, we start to deal with these challenging tasks by developing a defeasible reasoner for meteorological forecasting, which we evaluate against a real-world example with applications to tourism and holiday planning.},
keywords = {Automatic reasoning, Defeasible logic, Machine Learning, Non monotonic logic},
pubstate = {published},
tppubtype = {inproceedings}
}
Weather forecasting is a logical process that consists in evaluating the predictions provided by a set of stochastic models, compare these and take a conclusion about the weather in a given area and a given interval of time. Meteorological forecasting provides reliable predictions about the weather within a given interval of time. The automation of the forecasting process would be helpful in a number of contexts. For instance, when forecasting about underpopulated or small geographic areas is out of the human forecasters' tasks but is central, e.g., for tourism. In this paper, we start to deal with these challenging tasks by developing a defeasible reasoner for meteorological forecasting, which we evaluate against a real-world example with applications to tourism and holiday planning.
Cristani, Matteo; Olivieri, Francesco; Tomazzoli, Claudio; Zorzi, Margherita
Web Literature, Authorship Attribution and Editorial Workflow Ontologies Proceedings Article
In: Proceedings of 13th International Conference on Agents and Multi-Agent Systems: Technologies and Applications (KES-AMSTA-19), pp. 129–140, Springer, Berlin, 2019.
Abstract | Links | BibTeX | Tags: Machine Learning, Natural language analysis, Natural Language Processing, Semantic
@inproceedings{cristani_web_2019,
title = {Web Literature, Authorship Attribution and Editorial Workflow Ontologies},
author = {Matteo Cristani and Francesco Olivieri and Claudio Tomazzoli and Margherita Zorzi},
url = {https://link.springer.com/chapter/10.1007/978-981-13-8679-4_11},
doi = {10.1007/978-981-13-8679-4_11},
year = {2019},
date = {2019-01-01},
booktitle = {Proceedings of 13th International Conference on Agents and Multi-Agent Systems: Technologies and Applications (KES-AMSTA-19)},
volume = {148},
pages = {129–140},
publisher = {Springer},
address = {Berlin},
abstract = {In this paper, we illustrate a combinatorial approach to the problem of defining an ontology used for detecting multiple authorship and roles in weblogs and social network literature production. The investigation aims at providing a model of workflows and therefore traits to be recognised in these documents.},
keywords = {Machine Learning, Natural language analysis, Natural Language Processing, Semantic},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we illustrate a combinatorial approach to the problem of defining an ontology used for detecting multiple authorship and roles in weblogs and social network literature production. The investigation aims at providing a model of workflows and therefore traits to be recognised in these documents.
Cristani, Matteo; Tomazzoli, Claudio; Zorzi, Margherita
Automatic Generation of Dictionaries: The Journalistic Lexicon Case. Proceedings Article
In: Proceedings of 32nd International Conference on Industrial, Engineering & Other Applications of Applied Intelligent Systems (IEA/AIE 2019), pp. 744–752, Springer, 2019, ISBN: 978-3-030-22998-6.
Abstract | Links | BibTeX | Tags: Machine Learning, Natural Language Processing
@inproceedings{cristani_automatic_2019-1,
title = {Automatic Generation of Dictionaries: The Journalistic Lexicon Case.},
author = {Matteo Cristani and Claudio Tomazzoli and Margherita Zorzi},
url = {https://link.springer.com/chapter/10.1007/978-3-030-22999-3_63},
doi = {10.1007/978-3-030-22999-3_63},
isbn = {978-3-030-22998-6},
year = {2019},
date = {2019-01-01},
booktitle = {Proceedings of 32nd International Conference on Industrial, Engineering & Other Applications of Applied Intelligent Systems (IEA/AIE 2019)},
volume = {11606},
pages = {744–752},
publisher = {Springer},
abstract = {Text normalisation is an important task in the context of Natural Language Processing. By normalisation, free text is mapped into dictionaries, i.e. indexed collections of locutions recognised as typical of a particular jaergon. In general, technical dictionaries are difficult to build and validate. They are typically constructed by hand on the basis of everyday human work and they are agreement-based. This is indubitably time consuming and the approach requires a strong human supervision and does not provide a general methodology. In this paper, we perform the first steps towards the to automatic building of a dictionary for Italian journalistic lexicon, called NewsDict, based on sub dictionaries able to characterise main topics occurring in newspaper articles. We exploit a dataset of annotated documents from some Italian newspapers and a statistical techniques based on the Mutual Information Principle. Documents contains information such as the release date and the topic of the article and has been directly annotated by the author. To check the accuracy of the dictionary we built, we develop an initial test. We normalise a control set of journal article into NewsDict. Crossing results presented in this paper against the human annotation, we provide a fist measure of performances of the described methodology.},
keywords = {Machine Learning, Natural Language Processing},
pubstate = {published},
tppubtype = {inproceedings}
}
Text normalisation is an important task in the context of Natural Language Processing. By normalisation, free text is mapped into dictionaries, i.e. indexed collections of locutions recognised as typical of a particular jaergon. In general, technical dictionaries are difficult to build and validate. They are typically constructed by hand on the basis of everyday human work and they are agreement-based. This is indubitably time consuming and the approach requires a strong human supervision and does not provide a general methodology. In this paper, we perform the first steps towards the to automatic building of a dictionary for Italian journalistic lexicon, called NewsDict, based on sub dictionaries able to characterise main topics occurring in newspaper articles. We exploit a dataset of annotated documents from some Italian newspapers and a statistical techniques based on the Mutual Information Principle. Documents contains information such as the release date and the topic of the article and has been directly annotated by the author. To check the accuracy of the dictionary we built, we develop an initial test. We normalise a control set of journal article into NewsDict. Crossing results presented in this paper against the human annotation, we provide a fist measure of performances of the described methodology.
Cristani, Matteo; Manzato, Michele; Scannapieco, Simone; Tomazzoli, Claudio; Zuliani, Stefano Francesco
Automatic Clustering of User Communities: A System Architecture Proceedings Article
In: Proceedings of 32nd International Conference on Industrial, Engineering & Other Applications of Applied Intelligent Systems (IEA/AIE 2019), pp. 69–80, Springer, 2019.
Abstract | Links | BibTeX | Tags: Deep Learning, Machine Learning, Semantic
@inproceedings{cristani_automatic_2019,
title = {Automatic Clustering of User Communities: A System Architecture},
author = {Matteo Cristani and Michele Manzato and Simone Scannapieco and Claudio Tomazzoli and Stefano Francesco Zuliani},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85068331511&doi=10.1007%2f978-981-13-8679-4_6&partnerID=40&md5=c82c16aa107359bbf626a90c43fcc816},
doi = {10.1007/978-981-13-8679-4_6},
year = {2019},
date = {2019-01-01},
booktitle = {Proceedings of 32nd International Conference on Industrial, Engineering & Other Applications of Applied Intelligent Systems (IEA/AIE 2019)},
volume = {148},
pages = {69–80},
publisher = {Springer},
series = {Smart Innovation, Systems and Technologies},
abstract = {A semantic community is a set of individuals who are interested in the contents that refer to a specific domain, around which they aggregate to perform social activities such as sharing, commenting, possibly editing, those contents. Every producer of contents that is interested in interacting on social networks and in general on digital news platforms is interested in actively collaborating with the semantic communities that exist about the topics she produces. In general, moreover, a content producer is interested in fostering communities, mainly because this will generate a higher interest on her contents. In this paper, we illustrate an architecture of a system able to support and manage semantic communities in the framework of a project for digital news delivering. The architecture is illustrated and its basic concept is presented.},
keywords = {Deep Learning, Machine Learning, Semantic},
pubstate = {published},
tppubtype = {inproceedings}
}
A semantic community is a set of individuals who are interested in the contents that refer to a specific domain, around which they aggregate to perform social activities such as sharing, commenting, possibly editing, those contents. Every producer of contents that is interested in interacting on social networks and in general on digital news platforms is interested in actively collaborating with the semantic communities that exist about the topics she produces. In general, moreover, a content producer is interested in fostering communities, mainly because this will generate a higher interest on her contents. In this paper, we illustrate an architecture of a system able to support and manage semantic communities in the framework of a project for digital news delivering. The architecture is illustrated and its basic concept is presented.
2018
Bonci, Andrea; Pirani, Massimiliano; Cucchiarelli, Alessandro; Carbonari, Alessandro; Naticchia, Berardo; Longhi, Sauro
A Review of Recursive Holarchies for Viable Systems in CPSs Proceedings Article
In: 2018 IEEE 16th International Conference on Industrial Informatics (INDIN), pp. 37–42, 2018, ISSN: 2378-363X, (ISSN: 2378-363X).
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Automation, Cognition, Computer Architecture, Cyber-Physical Systems, Holonic Systems, Industry Automation, Knowledge and Reasoning, Resilience, Situated Agents
@inproceedings{bonciReviewRecursiveHolarchies2018,
title = {A Review of Recursive Holarchies for Viable Systems in CPSs},
author = {Andrea Bonci and Massimiliano Pirani and Alessandro Cucchiarelli and Alessandro Carbonari and Berardo Naticchia and Sauro Longhi},
url = {https://ieeexplore.ieee.org/abstract/document/8472055},
doi = {10.1109/INDIN.2018.8472055},
issn = {2378-363X},
year = {2018},
date = {2018-07-01},
urldate = {2024-10-09},
booktitle = {2018 IEEE 16th International Conference on Industrial Informatics (INDIN)},
pages = {37–42},
abstract = {This work reviews and recaps some lessons learnt in the industrial cyber-physical systems playground to indicate a viable path towards an effective use of artificial intelligence in distributed automation. The holon concept is used as a pivotal tool towards a simplification of the design and implementation of architectures that exploit recursive patterns and self-similarities to keep the industrial systems-of-systems problem under control, whilst addressing the consistent coupling between the physical environmental and the reasoning processes. The Beer's viable system model is used as an inspiration towards new viable holistic visions of the production system-of-systems.},
note = {ISSN: 2378-363X},
keywords = {Artificial Intelligence, Automation, Cognition, Computer Architecture, Cyber-Physical Systems, Holonic Systems, Industry Automation, Knowledge and Reasoning, Resilience, Situated Agents},
pubstate = {published},
tppubtype = {inproceedings}
}
This work reviews and recaps some lessons learnt in the industrial cyber-physical systems playground to indicate a viable path towards an effective use of artificial intelligence in distributed automation. The holon concept is used as a pivotal tool towards a simplification of the design and implementation of architectures that exploit recursive patterns and self-similarities to keep the industrial systems-of-systems problem under control, whilst addressing the consistent coupling between the physical environmental and the reasoning processes. The Beer's viable system model is used as an inspiration towards new viable holistic visions of the production system-of-systems.
Ceccacci, S.; Generosi, Andrea; Giraldi, L.; Mengoni, M.
An Emotion Recognition System for monitoring Shopping Experience Proceedings Article
In: Proceedings of the 11th PErvasive Technologies Related to Assistive Environments Conference, pp. 102–103, ACM, Corfu Greece, 2018, ISBN: 978-1-4503-6390-7.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Emotion Recognition, User experience
@inproceedings{ceccacci_emotion_2018,
title = {An Emotion Recognition System for monitoring Shopping Experience},
author = {S. Ceccacci and Andrea Generosi and L. Giraldi and M. Mengoni},
url = {https://dl.acm.org/doi/10.1145/3197768.3201518},
doi = {10.1145/3197768.3201518},
isbn = {978-1-4503-6390-7},
year = {2018},
date = {2018-06-01},
urldate = {2024-12-28},
booktitle = {Proceedings of the 11th PErvasive Technologies Related to Assistive Environments Conference},
pages = {102–103},
publisher = {ACM},
address = {Corfu Greece},
abstract = {The present work introduces an emotional tracking system to monitor Shopping Experience at different touchpoints in a store, based on the elaboration of the information extracted from biometric data and facial expressions. Preliminary tests suggest that the proposed system can be effectively used in a retail context.},
keywords = {Artificial Intelligence, Emotion Recognition, User experience},
pubstate = {published},
tppubtype = {inproceedings}
}
The present work introduces an emotional tracking system to monitor Shopping Experience at different touchpoints in a store, based on the elaboration of the information extracted from biometric data and facial expressions. Preliminary tests suggest that the proposed system can be effectively used in a retail context.
Ceccacci, Silvia; Generosi, Andrea; Giraldi, Luca; Mengoni, Maura; Engineering, Department Industrial; delle Marche 12 Via Brecce Bianche Mathematical Sciences, Ancona 60133 Università Politecnica
Tool to Make Shopping Experience Responsive to Customer Emotions Journal Article
In: International Journal of Automation Technology, vol. 12, no. 3, pp. 319–326, 2018, ISSN: 1883-8022, 1881-7629.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Emotion Recognition, User experience
@article{ceccacci_tool_2018,
title = {Tool to Make Shopping Experience Responsive to Customer Emotions},
author = {Silvia Ceccacci and Andrea Generosi and Luca Giraldi and Maura Mengoni and Department Industrial Engineering and Ancona 60133 Università Politecnica delle Marche 12 Via Brecce Bianche Mathematical Sciences},
url = {https://www.fujipress.jp/ijat/au/ijate001200030319},
doi = {10.20965/ijat.2018.p0319},
issn = {1883-8022, 1881-7629},
year = {2018},
date = {2018-05-01},
urldate = {2024-12-28},
journal = {International Journal of Automation Technology},
volume = {12},
number = {3},
pages = {319–326},
abstract = {This research aims to develop a system that examines and reacts to the changing behaviors and emotions of individuals in order to improve their shopping experience. The system is able to track emotions in real time at different touchpoints in a store and control a set of networked devices to configure the sensing space and all provided services responsive to the customers’ needs. This paper describes the general approach adopted to design the overall system and illustrates in detail the module prototyped to understand the users’ emotions through the analysis of facial expressions.},
keywords = {Artificial Intelligence, Emotion Recognition, User experience},
pubstate = {published},
tppubtype = {article}
}
This research aims to develop a system that examines and reacts to the changing behaviors and emotions of individuals in order to improve their shopping experience. The system is able to track emotions in real time at different touchpoints in a store and control a set of networked devices to configure the sensing space and all provided services responsive to the customers’ needs. This paper describes the general approach adopted to design the overall system and illustrates in detail the module prototyped to understand the users’ emotions through the analysis of facial expressions.
Gargiulo, Francesco; Silvestri, Stefano; Fontanella, Mariarosaria; Ciampi, Mario; Pietro, Giuseppe De
A Deep Learning Approach for Scientific Paper Semantic Ranking Proceedings Article
In: Pietro, Giuseppe De; Gallo, Luigi; Howlett, Robert J.; Jain, Lakhmi C. (Ed.): Intelligent Interactive Multimedia Systems and Services 2017, pp. 471–481, Springer International Publishing, Cham, 2018, ISBN: 978-3-319-59480-4.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Deep Learning, Word Embeddings
@inproceedings{gargiulo_deep_2018,
title = {A Deep Learning Approach for Scientific Paper Semantic Ranking},
author = {Francesco Gargiulo and Stefano Silvestri and Mariarosaria Fontanella and Mario Ciampi and Giuseppe De Pietro},
editor = {Giuseppe De Pietro and Luigi Gallo and Robert J. Howlett and Lakhmi C. Jain},
doi = {10.1007/978-3-319-59480-4_47},
isbn = {978-3-319-59480-4},
year = {2018},
date = {2018-01-01},
booktitle = {Intelligent Interactive Multimedia Systems and Services 2017},
pages = {471–481},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {In this paper we proposed a novel Deep Learning approach to realize a Word Embeddings (WEs) similarity based search tool, considering the medical literature as case study. Using the compositional properties of the WEs we defined a methodology to aggregate the information coming from each word to obtain a vector corresponding to the abstracts of each PubMed article. Through this paradigm it is possible to capture the semantic content of the papers and, consequently, to evaluate and rank the similarity among them. The preliminary results with the proposed approach are obtained analysing a subset of the whole the PubMed collection. The results correctness has been verified by human domain experts, showing that the methodology is promising.},
keywords = {Artificial Intelligence, Deep Learning, Word Embeddings},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper we proposed a novel Deep Learning approach to realize a Word Embeddings (WEs) similarity based search tool, considering the medical literature as case study. Using the compositional properties of the WEs we defined a methodology to aggregate the information coming from each word to obtain a vector corresponding to the abstracts of each PubMed article. Through this paradigm it is possible to capture the semantic content of the papers and, consequently, to evaluate and rank the similarity among them. The preliminary results with the proposed approach are obtained analysing a subset of the whole the PubMed collection. The results correctness has been verified by human domain experts, showing that the methodology is promising.
Bonci, Andrea; Clini, Paolo; Martin, Rafael; Pirani, Massimiliano; Quattrini, Ramona; Raikov, Alexander
Collaborative intelligence cyber-physical system for the valorization and re-use of cultural heritage Journal Article
In: JOURNAL OF INFORMATION TECHNOLOGY IN CONSTRUCTION, vol. 23, no. 1, pp. 305–323, 2018.
Abstract | Links | BibTeX | Tags: Adaptive Re-use, Artificial Intelligence, Assistant system, Cultural Heritage, Decision Making, Networked Model
@article{20.500.12607_24606,
title = {Collaborative intelligence cyber-physical system for the valorization and re-use of cultural heritage},
author = {Andrea Bonci and Paolo Clini and Rafael Martin and Massimiliano Pirani and Ramona Quattrini and Alexander Raikov},
url = {https://www.itcon.org/papers/2018_15-ITcon-Bonci.pdf},
year = {2018},
date = {2018-01-01},
journal = {JOURNAL OF INFORMATION TECHNOLOGY IN CONSTRUCTION},
volume = {23},
number = {1},
pages = {305–323},
abstract = {This paper is a proposition of methodological and technological approaches that try to constitute a framework that introduces modern artificial intelligence (AI) technologies for decision-making in the adaptive re- use of cultural heritage (CH) processes. The research aims to accelerate and improve the quality of adaptive CH re-use. The complexity of the problem derives from some causes of different nature: lack of attention to this problem from the public administration and private investors; decision-making processes complicated by the need to connect with experts, located in different countries. Most professionals, related to the CH management, cannot access detailed data about already existing successful initiatives. The specific objective and goal of the research is the creation of an AI framework and eco-system for supporting the development and implementation of innovative business and governance models to fill up the investment gap in the adaptive re-use practices. The paper shortly describes the first steps for creating a platform designed and developed to assist and advice public entities, networked experts, private entrepreneurs and citizens in actions aiming at the valorisation of the historic and CH asset and its integration in different groups of countries to boost growth, job opportunities and social benefits, under overall sustainability constraints. The technical solutions here adopted are based on convergent methodology and networked expertise (e-expertise) technology, open data models and active knowledge extraction and processing, machine learning, collective intelligence, recommendation systems and predictive analytics, CH adaptive re-use, innovation business, and models and case-based reasoning methods. Examples of case studies giving the inception for the project components are given.},
keywords = {Adaptive Re-use, Artificial Intelligence, Assistant system, Cultural Heritage, Decision Making, Networked Model},
pubstate = {published},
tppubtype = {article}
}
This paper is a proposition of methodological and technological approaches that try to constitute a framework that introduces modern artificial intelligence (AI) technologies for decision-making in the adaptive re- use of cultural heritage (CH) processes. The research aims to accelerate and improve the quality of adaptive CH re-use. The complexity of the problem derives from some causes of different nature: lack of attention to this problem from the public administration and private investors; decision-making processes complicated by the need to connect with experts, located in different countries. Most professionals, related to the CH management, cannot access detailed data about already existing successful initiatives. The specific objective and goal of the research is the creation of an AI framework and eco-system for supporting the development and implementation of innovative business and governance models to fill up the investment gap in the adaptive re-use practices. The paper shortly describes the first steps for creating a platform designed and developed to assist and advice public entities, networked experts, private entrepreneurs and citizens in actions aiming at the valorisation of the historic and CH asset and its integration in different groups of countries to boost growth, job opportunities and social benefits, under overall sustainability constraints. The technical solutions here adopted are based on convergent methodology and networked expertise (e-expertise) technology, open data models and active knowledge extraction and processing, machine learning, collective intelligence, recommendation systems and predictive analytics, CH adaptive re-use, innovation business, and models and case-based reasoning methods. Examples of case studies giving the inception for the project components are given.
Galteri, Leonardo; Bertini, Marco; Seidenari, Lorenzo; Bimbo, Alberto Del
Video compression for object detection algorithms Proceedings Article
In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 3007–3012, IEEE, 2018, ISBN: 1-5386-3788-X, (tex.copyright: All rights reserved).
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Autonomous Driving, Computer Vision and Pattern Recognition, Object Detection, Real-time Video Processing, Saliency Mapping, Video Compression, Video Streaming, Video Surveillance
@inproceedings{galteriVideoCompressionObject2018,
title = {Video compression for object detection algorithms},
author = {Leonardo Galteri and Marco Bertini and Lorenzo Seidenari and Alberto Del Bimbo},
url = {https://ieeexplore.ieee.org/abstract/document/8546064},
doi = {10.1109/ICPR.2018.8546064},
isbn = {1-5386-3788-X},
year = {2018},
date = {2018-01-01},
booktitle = {2018 24th International Conference on Pattern Recognition (ICPR)},
pages = {3007–3012},
publisher = {IEEE},
abstract = {Video compression algorithms have been designed aiming at pleasing human viewers, and are driven by video quality metrics that are designed to account for the capabilities of the human visual system. However, thanks to the advances in computer vision systems more and more videos are going to be watched by algorithms, e.g. implementing video surveillance systems or performing automatic video tagging. This paper describes an adaptive video coding approach for computer vision-based systems. We show how to control the quality of video compression so that automatic object detectors can still process the resulting video, improving their detection performance, by preserving the elements of the scene that are more likely to contain meaningful content. Our approach is based on computation of saliency maps exploiting a fast objectness measure. The computational efficiency of this approach makes it usable in a real-time video coding pipeline. Experiments show that our technique outperforms standard H.265 in speed and coding efficiency, and can be applied to different types of video domains, from surveillance to web videos.},
note = {tex.copyright: All rights reserved},
keywords = {Artificial Intelligence, Autonomous Driving, Computer Vision and Pattern Recognition, Object Detection, Real-time Video Processing, Saliency Mapping, Video Compression, Video Streaming, Video Surveillance},
pubstate = {published},
tppubtype = {inproceedings}
}
Video compression algorithms have been designed aiming at pleasing human viewers, and are driven by video quality metrics that are designed to account for the capabilities of the human visual system. However, thanks to the advances in computer vision systems more and more videos are going to be watched by algorithms, e.g. implementing video surveillance systems or performing automatic video tagging. This paper describes an adaptive video coding approach for computer vision-based systems. We show how to control the quality of video compression so that automatic object detectors can still process the resulting video, improving their detection performance, by preserving the elements of the scene that are more likely to contain meaningful content. Our approach is based on computation of saliency maps exploiting a fast objectness measure. The computational efficiency of this approach makes it usable in a real-time video coding pipeline. Experiments show that our technique outperforms standard H.265 in speed and coding efficiency, and can be applied to different types of video domains, from surveillance to web videos.
Becattini, Federico; Berlincioni, Lorenzo; Galteri, Leonardo; Seidenari, Lorenzo; Bimbo, Alberto Del
Semantic road layout understanding by generative adversarial inpainting Journal Article
In: CoRR, 2018, (tex.copyright: All rights reserved).
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Autonomous Driving, Computer Vision and Pattern Recognition, Generative Adversarial Networks, Image Inpainting, Image Processing, Semantic Segmentation, Urban Planning
@article{becattiniSemanticRoadLayout2018,
title = {Semantic road layout understanding by generative adversarial inpainting},
author = {Federico Becattini and Lorenzo Berlincioni and Leonardo Galteri and Lorenzo Seidenari and Alberto Del Bimbo},
url = {https://www.researchgate.net/profile/Federico-Becattini-2/publication/325464130_Semantic_Road_Layout_Understanding_by_Generative_Adversarial_Inpainting/links/5b1e7c2245851587f2a01eeb/Semantic-Road-Layout-Understanding-by-Generative-Adversarial-Inpainting.pdf},
doi = {Unavailable},
year = {2018},
date = {2018-01-01},
journal = {CoRR},
abstract = {Autonomous driving is becoming a reality, yet vehicles still need to rely on complex sensor fusion techniques to fully understand the scene they act in. Being able to discern the static environment from the dynamic entities that populate it, will improve scene comprehension algorithms and will pose constraints to the reasoning process about moving objects. With this in mind, we propose a scene comprehension task aimed at providing a complete understanding of the static surroundings, with a particular attention to road layout. In order to cut to the bare minimum the sensor requirements to be deployed on-board, we solely rely on semantic segmentation masks, which can be reliably obtained with computer vision algorithms from any RGB source. We cast this problem as an inpainting task based on a Generative Adversarial Network model to remove all dynamic objects from the scene and focus on understanding its static components such as streets, sidewalks and buildings. We evaluate this task on a synthetically generated dataset obtained with the CARLA simulator, demonstrating the effectiveness of our method.},
note = {tex.copyright: All rights reserved},
keywords = {Artificial Intelligence, Autonomous Driving, Computer Vision and Pattern Recognition, Generative Adversarial Networks, Image Inpainting, Image Processing, Semantic Segmentation, Urban Planning},
pubstate = {published},
tppubtype = {article}
}
Autonomous driving is becoming a reality, yet vehicles still need to rely on complex sensor fusion techniques to fully understand the scene they act in. Being able to discern the static environment from the dynamic entities that populate it, will improve scene comprehension algorithms and will pose constraints to the reasoning process about moving objects. With this in mind, we propose a scene comprehension task aimed at providing a complete understanding of the static surroundings, with a particular attention to road layout. In order to cut to the bare minimum the sensor requirements to be deployed on-board, we solely rely on semantic segmentation masks, which can be reliably obtained with computer vision algorithms from any RGB source. We cast this problem as an inpainting task based on a Generative Adversarial Network model to remove all dynamic objects from the scene and focus on understanding its static components such as streets, sidewalks and buildings. We evaluate this task on a synthetically generated dataset obtained with the CARLA simulator, demonstrating the effectiveness of our method.
Gargiulo, Francesco; Silvestri, Stefano; Fontanella, Mariarosaria; Ciampi, Mario; Pietro, Giuseppe De
A Deep Learning Approach for Scientific Paper Semantic Ranking Proceedings Article
In: Pietro, Giuseppe De; Gallo, Luigi; Howlett, Robert J.; Jain, Lakhmi C. (Ed.): Intelligent Interactive Multimedia Systems and Services 2017, pp. 471–481, Springer International Publishing, Cham, 2018, ISBN: 978-3-319-59480-4.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Deep Learning, Word Embeddings
@inproceedings{gargiuloDeepLearningApproach2018,
title = {A Deep Learning Approach for Scientific Paper Semantic Ranking},
author = {Francesco Gargiulo and Stefano Silvestri and Mariarosaria Fontanella and Mario Ciampi and Giuseppe De Pietro},
editor = {Giuseppe De Pietro and Luigi Gallo and Robert J. Howlett and Lakhmi C. Jain},
doi = {10.1007/978-3-319-59480-4_47},
isbn = {978-3-319-59480-4},
year = {2018},
date = {2018-01-01},
booktitle = {Intelligent Interactive Multimedia Systems and Services 2017},
pages = {471–481},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {In this paper we proposed a novel Deep Learning approach to realize a Word Embeddings (WEs) similarity based search tool, considering the medical literature as case study. Using the compositional properties of the WEs we defined a methodology to aggregate the information coming from each word to obtain a vector corresponding to the abstracts of each PubMed article. Through this paradigm it is possible to capture the semantic content of the papers and, consequently, to evaluate and rank the similarity among them. The preliminary results with the proposed approach are obtained analysing a subset of the whole the PubMed collection. The results correctness has been verified by human domain experts, showing that the methodology is promising.},
keywords = {Artificial Intelligence, Deep Learning, Word Embeddings},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper we proposed a novel Deep Learning approach to realize a Word Embeddings (WEs) similarity based search tool, considering the medical literature as case study. Using the compositional properties of the WEs we defined a methodology to aggregate the information coming from each word to obtain a vector corresponding to the abstracts of each PubMed article. Through this paradigm it is possible to capture the semantic content of the papers and, consequently, to evaluate and rank the similarity among them. The preliminary results with the proposed approach are obtained analysing a subset of the whole the PubMed collection. The results correctness has been verified by human domain experts, showing that the methodology is promising.