Zobrazeno 1 - 10
of 265
pro vyhledávání: '"Li, Fuxin"'
Autor:
Liu, Yu-Ying, Moreno, Alexander, Xu, Maxwell A., Li, Shuang, McDaniel, Jena C., Brady, Nancy C., Rozga, Agata, Li, Fuxin, Song, Le, Rehg, James M.
The Continuous-Time Hidden Markov Model (CT-HMM) is an attractive approach to modeling disease progression due to its ability to describe noisy observations arriving irregularly in time. However, the lack of an efficient parameter learning algorithm
Externí odkaz:
http://arxiv.org/abs/2110.13998
Autor:
Chen, Lin1 (AUTHOR) venguamecl@163.com, Li, Fuxin1 (AUTHOR) lifuxin202310@163.com, Li, Lanxin1 (AUTHOR) lilanxin0530@163.com, Ma, Shengnan2 (AUTHOR) mashengnan34@163.com, Yu, Lin2 (AUTHOR) nkyulin@sina.com, Tang, Chunshuang2 (AUTHOR) 13644546046@163.com, Zhao, Kuangyu3 (AUTHOR) 18686860676@163.com, Song, Zhen1 (AUTHOR) cyliucn@neau.edu.cn, Liu, Chunyan1 (AUTHOR), Chen, Qingshan1 (AUTHOR) qshchen@126.com, Wang, Jinhui1 (AUTHOR) qshchen@126.com
Publikováno v:
Agronomy. May2024, Vol. 14 Issue 5, p1019. 16p.
Autor:
Chai, Ran, Li, Fuxin, Gao, Yuqian, Liu, Dehai, Shang, Di, Yang, Yanqing, Yu, Jiayang, Zhou, Chenxiao, Li, Yanan, Song, Andong, Qiu, Liyou
Publikováno v:
In Computers and Electronics in Agriculture October 2024 225
We present MetaUVFS as the first Unsupervised Meta-learning algorithm for Video Few-Shot action recognition. MetaUVFS leverages over 550K unlabeled videos to train a two-stream 2D and 3D CNN architecture via contrastive learning to capture the appear
Externí odkaz:
http://arxiv.org/abs/2109.15317
Transformers have recently been popular for learning and inference in the spatial-temporal domain. However, their performance relies on storing and applying attention to the feature tensor of each frame in video. Hence, their space and time complexit
Externí odkaz:
http://arxiv.org/abs/2109.06474
Publikováno v:
In Computer Vision and Image Understanding April 2024 241
Publikováno v:
Artificial Intelligence, 2021, 103455, ISSN 0004-3702
Counterfactual explanations, which deal with "why not?" scenarios, can provide insightful explanations to an AI agent's behavior. In this work, we focus on generating counterfactual explanations for deep reinforcement learning (RL) agents which opera
Externí odkaz:
http://arxiv.org/abs/2101.12446
The black-box nature of the deep networks makes the explanation for "why" they make certain predictions extremely challenging. Saliency maps are one of the most widely-used local explanation tools to alleviate this problem. One of the primary approac
Externí odkaz:
http://arxiv.org/abs/2012.15783
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
In Construction and Building Materials 15 August 2023 392