Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Gianpiero Francesca"'
Autor:
Mauro Birattari, Antoine Ligot, Darko Bozhinoski, Manuele Brambilla, Gianpiero Francesca, Lorenzo Garattoni, David Garzón Ramos, Ken Hasselmann, Miquel Kegeleirs, Jonas Kuckling, Federico Pagnozzi, Andrea Roli, Muhammad Salman, Thomas Stützle
Publikováno v:
Frontiers in Robotics and AI, Vol 6 (2019)
Designing collective behaviors for robot swarms is a difficult endeavor due to their fully distributed, highly redundant, and ever-changing nature. To overcome the challenge, a few approaches have been proposed, which can be classified as manual, sem
Externí odkaz:
https://doaj.org/article/25062b53f32b461abea37a38502c2fad
Autor:
Rui Dai, Srijan Das, Saurav Sharma, Luca Minciullo, Lorenzo Garattoni, Francois Bremond, Gianpiero Francesca
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence, inPress, ⟨10.1109/tpami.2022.3169976⟩
IEEE Transactions on Pattern Analysis and Machine Intelligence, inPress, ⟨10.1109/tpami.2022.3169976⟩
Designing activity detection systems that can be successfully deployed in daily-living environments requires datasets that pose the challenges typical of real-world scenarios. In this paper, we introduce a new untrimmed daily-living dataset that feat
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Action segmentation is the task of predicting the actions for each frame of a video. As obtaining the full annotation of videos for action segmentation is expensive, weakly supervised approaches that can learn only from transcripts are appealing. In
Autor:
Di Yang, Yaohui Wang, Antitza Dantcheva, Lorenzo Garattoni, Gianpiero Francesca, Francois Bremond
Publikováno v:
FG 2021-IEEE International Conference on Automatic Face and Gesture Recognition
FG 2021-IEEE International Conference on Automatic Face and Gesture Recognition, Dec 2021, Jodhpur (Virtual), India. ⟨10.1109/FG52635.2021.9667032⟩
IEEE International Conference on Automatic Face and Gesture Recognition (FG)
IEEE International Conference on Automatic Face and Gesture Recognition (FG), Dec 2021, Jodhpur (Virtual), India
FG 2021-IEEE International Conference on Automatic Face and Gesture Recognition, Dec 2021, Jodhpur (Virtual), India. ⟨10.1109/FG52635.2021.9667032⟩
IEEE International Conference on Automatic Face and Gesture Recognition (FG)
IEEE International Conference on Automatic Face and Gesture Recognition (FG), Dec 2021, Jodhpur (Virtual), India
International audience; Action recognition based on human pose has witnessed increasing attention due to its robustness to changes in appearances, environments, and viewpoints. Despite associated progress, one remaining challenge has to do with occlu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d53a1c0e2cafbb51f66a667a01e49274
https://hal.science/hal-03476564
https://hal.science/hal-03476564
Autor:
Gianpiero Francesca, Yaohui Wang, Di Yang, Rupayan Mallick, Rui Dai, Francois Bremond, Luca Minciullo
Publikováno v:
WACV 2021 – IEEE Winter Conference on Applications of Computer Vision
WACV 2021 – IEEE Winter Conference on Applications of Computer Vision, Jan 2021, Virtual, United States
HAL
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan 2021, Virtual, United States
WACV
WACV 2021 – IEEE Winter Conference on Applications of Computer Vision, Jan 2021, Virtual, United States
HAL
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan 2021, Virtual, United States
WACV
Taking advantage of human pose data for understanding human activities has attracted much attention these days. However, state-of-the-art pose estimators struggle in obtaining high-quality 2D or 3D pose data due to occlusion, truncation and low-resol
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ef053b713605c7fa5c924b71882ead07
https://hal.science/hal-03121883/document
https://hal.science/hal-03121883/document
Autor:
Lorenzo Garattoni, Luca Minciullo, Srijan Das, Gianpiero Francesca, Rui Dai, Francois Bremond
Publikováno v:
WACV
HAL
WACV 2021-Winter Conference on Applications of Computer Vision 2021
WACV 2021-Winter Conference on Applications of Computer Vision 2021, Jan 2021, Waikoloa / Virtual, United States
HAL
WACV 2021-Winter Conference on Applications of Computer Vision 2021
WACV 2021-Winter Conference on Applications of Computer Vision 2021, Jan 2021, Waikoloa / Virtual, United States
Handling long and complex temporal information is an important challenge for action detection tasks. This challenge is further aggravated by densely distributed actions in untrimmed videos. Previous action detection methods fail in selecting the key
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030926588
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::77b1e98af9ae1fdbfc5dde0c39998456
https://doi.org/10.1007/978-3-030-92659-5_18
https://doi.org/10.1007/978-3-030-92659-5_18
Autor:
Gianpiero Francesca, Catherine Lai, Beatrice Alex, Leimin Tian, Johanna D. Moore, Hori Tatsuro
Publikováno v:
Lai, C, Alex, B, Moore, J D, Tian, L, Hori, T & Francesca, G 2019, Detecting Topic-Oriented Speaker Stance in Conversational Speech . in Proceedings of Interspeech 2019 . Interspeech, pp. 46-50, Interspeech 2019, Graz, Austria, 15/09/19 . https://doi.org/10.21437/Interspeech.2019-2632
INTERSPEECH
INTERSPEECH
Being able to detect topics and speaker stances in conversations is a key requirement for developing spoken language understanding systems that are personalized and adaptive. In this work, we explore how topic-oriented speaker stance is expressed in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::882ce4f748e8c1e484ef97863e3a6848
https://hdl.handle.net/20.500.11820/b56fe7f4-1ed4-4a39-80ac-bbd004312346
https://hdl.handle.net/20.500.11820/b56fe7f4-1ed4-4a39-80ac-bbd004312346
Publikováno v:
AVSS 2019-16th IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS)
AVSS 2019-16th IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS), Sep 2019, Taipei, Taiwan
AVSS
HAL
AVSS 2019-16th IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS), Sep 2019, Taipei, Taiwan
AVSS
HAL
International audience; In this paper, we address the detection of daily living activities in long-term untrimmed videos. The detection of daily living activities is challenging due to their long temporal components, low inter-class variation and hig
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bef57e7f10a50e33c84fc60bdbe6d841
https://hal.science/hal-02357161
https://hal.science/hal-02357161
Autor:
Michal Koperski, Abhishek Goel, Francois Bremond, Abdelrahman G. Abubakr, Gianpiero Francesca
Publikováno v:
IEEE IPAS 2018
IEEE IPAS 2018, Dec 2018, Nice, France
IPAS
IEEE IPAS 2018, Dec 2018, Nice, France
IPAS
International audience; Many approaches were proposed to solve the problem of activity recognition in short clipped videos, which achieved impressive results with hand-crafted and deep features. However, it is not practical to have clipped videos in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f12029f47d362aef337790c21e3caf15
https://inria.hal.science/hal-01948387
https://inria.hal.science/hal-01948387