Zobrazeno 1 - 10
of 187
pro vyhledávání: '"Wu, Wenhan"'
Complex behavioral contagion in collective evasion of mobile animal groups can be predicted by reconstructing quantitative interaction networks. Based on the assumption of time-scale separation between a fast contagion process and a slower movement r
Externí odkaz:
http://arxiv.org/abs/2408.05096
Recently, transformers have demonstrated great potential for modeling long-term dependencies from skeleton sequences and thereby gained ever-increasing attention in skeleton action recognition. However, the existing transformer-based approaches heavi
Externí odkaz:
http://arxiv.org/abs/2407.12322
Autor:
Li, Bowen, Wu, Wenhan, Tang, Ziwei, Shi, Lin, Yang, John, Li, Jinyang, Yao, Shunyu, Qian, Chen, Hui, Binyuan, Zhang, Qicheng, Yu, Zhiyin, Du, He, Yang, Ping, Lin, Dahua, Peng, Chao, Chen, Kai
Recent advancements in large language models (LLMs) have significantly enhanced their coding capabilities. However, existing benchmarks predominantly focused on simplified or isolated aspects of programming, such as single-file code generation or rep
Externí odkaz:
http://arxiv.org/abs/2403.08604
Autor:
Ma, Zheng, Pan, Mianzhi, Wu, Wenhan, Cheng, Kanzhi, Zhang, Jianbing, Huang, Shujian, Chen, Jiajun
Vision-language models (VLMs) have shown impressive performance in substantial downstream multi-modal tasks. However, only comparing the fine-tuned performance on downstream tasks leads to the poor interpretability of VLMs, which is adverse to their
Externí odkaz:
http://arxiv.org/abs/2308.03151
In recent years, remarkable results have been achieved in self-supervised action recognition using skeleton sequences with contrastive learning. It has been observed that the semantic distinction of human action features is often represented by local
Externí odkaz:
http://arxiv.org/abs/2305.00666
Fully supervised skeleton-based action recognition has achieved great progress with the blooming of deep learning techniques. However, these methods require sufficient labeled data which is not easy to obtain. In contrast, self-supervised skeleton-ba
Externí odkaz:
http://arxiv.org/abs/2209.02399
Publikováno v:
In Transportation Research Part C June 2024 163
Publikováno v:
In Expert Systems With Applications 15 May 2024 242
Autor:
Yang, Hanyu, You, Linjun, Wang, Zhongyan, Yang, Lu, Wang, Xun, Wu, Wenhan, Zhi, Hao, Rong, Guangmei, Sheng, Yun, Liu, Xiaodong, Liu, Li
Publikováno v:
In Redox Biology February 2024 69
Autor:
Zheng, Ce, Wu, Wenhan, Chen, Chen, Yang, Taojiannan, Zhu, Sijie, Shen, Ju, Kehtarnavaz, Nasser, Shah, Mubarak
Human pose estimation aims to locate the human body parts and build human body representation (e.g., body skeleton) from input data such as images and videos. It has drawn increasing attention during the past decade and has been utilized in a wide ra
Externí odkaz:
http://arxiv.org/abs/2012.13392