Zobrazeno 1 - 10
of 34
pro vyhledávání: '"Keze Wang"'
Autor:
Arjun R. Akula, Keze Wang, Changsong Liu, Sari Saba-Sadiya, Hongjing Lu, Sinisa Todorovic, Joyce Chai, Song-Chun Zhu
Publikováno v:
iScience, Vol 25, Iss 1, Pp 103581- (2022)
Summary: We propose CX-ToM, short for counterfactual explanations with theory-of-mind, a new explainable AI (XAI) framework for explaining decisions made by a deep convolutional neural network (CNN). In contrast to the current methods in XAI that gen
Externí odkaz:
https://doaj.org/article/6b5ea88555234442861e8e1dd3d7a90a
Publikováno v:
IEEE Transactions on Multimedia. :1-13
Video self-supervised learning is a challenging task, which requires significant expressive power from the model to leverage rich spatial-temporal knowledge and generate effective supervisory signals from large amounts of unlabeled videos. However, e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a4c0e9621d46ba16c18ea195dfd3b8ac
http://arxiv.org/abs/2112.03587
http://arxiv.org/abs/2112.03587
Aiming at recognizing the samples from novel categories with few reference samples, few-shot learning (FSL) is a challenging problem. We found that the existing works often build their few-shot model based on the image-level feature by mixing all loc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::411e12495a292a93be3e433835f5d3b4
http://arxiv.org/abs/2111.04331
http://arxiv.org/abs/2111.04331
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Publikováno v:
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 30
Existing vision-based action recognition is susceptible to occlusion and appearance variations, while wearable sensors can alleviate these challenges by capturing human motion with one-dimensional time-series signal. For the same action, the knowledg
Publikováno v:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.
Publikováno v:
ICRA
Although deep reinforcement learning (RL) has been successfully applied to a variety of robotic control tasks, it’s still challenging to apply it to real-world tasks, due to the poor sample efficiency. Attempting to overcome this shortcoming, sever
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4bf66c0b504f2fa7421fad108472fc67
http://arxiv.org/abs/2011.14487
http://arxiv.org/abs/2011.14487
Though beneficial for encouraging the Visual Question Answering (VQA) models to discover the underlying knowledge by exploiting the input-output correlation beyond image and text contexts, the existing knowledge VQA datasets are mostly annotated in a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::51145d54c8cf83a60e17ab6130561351
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 28:2667-2678
Aiming at improving performance of visual classification in a cost-effective manner, this paper proposes an incremental semi-supervised learning paradigm called Deep Co-Space (DCS). Unlike many conventional semi-supervised learning methods usually pe