Zobrazeno 1 - 10
of 131
pro vyhledávání: '"Rogerio Feris"'
Publikováno v:
EURASIP Journal on Image and Video Processing, Vol 2010 (2010)
We address the problem of unsupervised discovery of action classes in video data. Different from all existing methods thus far proposed for this task, we present a space-time link analysis approach which consistently matches or exceeds the performanc
Externí odkaz:
https://doaj.org/article/fab6c2ec0cb84403bad7a7bf0a6c4304
Autor:
Raja Giryes, Rogerio Feris, Chao Xue, Alexander M. Bronstein, Eli Schwartz, Leonid Karlinsky, Sivan Doveh
Publikováno v:
Pattern Recognition Letters. 149:130-136
Recently, great progress has been made in the field of Few-Shot Learning (FSL). While many different methods have been proposed, one of the key factors leading to higher FSL performance is surprisingly simple. It is the backbone network architecture
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6bee0a7db4e8952e3f9701e7518950fa
https://doi.org/10.1016/j.patrec.2021.05.010
https://doi.org/10.1016/j.patrec.2021.05.010
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::33d981ce291000b4fd57d62b8c55ea71
https://doi.org/10.1109/cvpr52688.2022.00500
https://doi.org/10.1109/cvpr52688.2022.00500
Autor:
Andrew Rouditchenko, Yung-Sung Chuang, Nina Shvetsova, Samuel Thomas, Rogerio Feris, Brian Kingsbury, Leonid Karlinsky, David Harwath, Hilde Kuehne, James Glass
Multilingual text-video retrieval methods have improved significantly in recent years, but the performance for other languages lags behind English. We propose a Cross-Lingual Cross-Modal Knowledge Distillation method to improve multilingual text-vide
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::14e9221132f9b7c09a4f9a64bf4baa19
Autor:
SouYoung Jin, James Glass, Alexander H. Liu, Mathew Monfort, Aude Oliva, David Harwath, Rogerio Feris
Publikováno v:
CVPR
When people observe events, they are able to abstract key information and build concise summaries of what is happening. These summaries include contextual and semantic information describing the important high-level details (what, where, who and how)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5b2a854ae31c856c91683142ef07b4da
https://doi.org/10.1109/cvpr46437.2021.01463
https://doi.org/10.1109/cvpr46437.2021.01463
Publikováno v:
CVPR
Generalization to out-of-distribution data has been a problem for Visual Question Answering (VQA) models. To measure generalization to novel questions, we propose to separate them into "skills" and "concepts". "Skills" are visual tasks, such as count
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::29053de58321a34006bcb24d814d8ad8
https://doi.org/10.1109/cvpr46437.2021.00558
https://doi.org/10.1109/cvpr46437.2021.00558
Autor:
Quoc-Bao Nguyen, Rogerio Feris, Minh N. Do, Hammer Stephen C, Michele Merler, John R. Smith, Jinjun Xiong, John Kent, Dhiraj Joshi, Khoi-Nguyen C. Mac
Publikováno v:
IEEE Transactions on Multimedia. 21:1147-1160
The production of sports highlight packages summarizing a game's most exciting moments is an essential task for broadcast media. Yet, it requires labor-intensive video editing. We propose a novel approach for auto-curating sports highlights, and demo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a0c21f2c8a9ba3ecdd89497f6a856305
https://doi.org/10.1109/tmm.2018.2876046
https://doi.org/10.1109/tmm.2018.2876046
Tremendous progress has been made in visual representation learning, notably with the recent success of self-supervised contrastive learning methods. Supervised contrastive learning has also been shown to outperform its cross-entropy counterparts by
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::08ff43386c4bdf5ecf1b5e0dca0c4cff
http://arxiv.org/abs/2103.13517
http://arxiv.org/abs/2103.13517
Autor:
Jinjun Xiong, Wen-mei W. Hwu, Rogerio Feris, Jiachen Li, Bowen Cheng, Humphrey Shi, Thomas S. Huang
Publikováno v:
CVPR Workshops
Current anchor-free object detectors are quite simple and effective yet lack accurate label assignment methods, which limits their potential in competing with classic anchor-based models that are supported by well-designed assignment methods based on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7f2f1d18b173f2d8183e6584b0a840ea
Autor:
Rameswar Panda, Andrew Rouditchenko, Hilde Kuehne, Angie Boggust, James Glass, Rogerio Feris, David Harwath, Brian Chen, Brian Kingsbury, Samuel Thomas, Michael Picheny
In this paper, we explore self-supervised audio-visual models that learn from instructional videos. Prior work has shown that these models can relate spoken words and sounds to visual content after training on a large-scale dataset of videos, but the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4e8574a412328c0178369baec3688670