Zobrazeno 1 - 10
of 2 477
pro vyhledávání: '"Zhang,Jinghui"'
Autor:
Huang, Wenbo, Zhang, Jinghui, Li, Guang, Zhang, Lei, Wang, Shuoyuan, Dong, Fang, Jin, Jiahui, Ogawa, Takahiro, Haseyama, Miki
In few-shot action recognition~(FSAR), long sub-sequences of video naturally express entire actions more effectively. However, the computational complexity of mainstream Transformer-based methods limits their application. Recent Mamba demonstrates ef
Externí odkaz:
http://arxiv.org/abs/2412.07481
Sentiment analysis and emotion recognition are crucial for applications such as human-computer interaction and depression detection. Traditional unimodal methods often fail to capture the complexity of emotional expressions due to conflicting signals
Externí odkaz:
http://arxiv.org/abs/2412.08049
Predicting crime hotspots in a city is a complex and critical task with significant societal implications. Numerous spatiotemporal correlations and irregularities pose substantial challenges to this endeavor. Existing methods commonly employ fixed-ti
Externí odkaz:
http://arxiv.org/abs/2411.01134
As graphs grow larger, full-batch GNN training becomes hard for single GPU memory. Therefore, to enhance the scalability of GNN training, some studies have proposed sampling-based mini-batch training and distributed graph learning. However, these met
Externí odkaz:
http://arxiv.org/abs/2408.11500
Autor:
Jin, Jiahui, Song, Yifan, Kan, Dong, Zhu, Haojia, Sun, Xiangguo, Li, Zhicheng, Sun, Xigang, Zhang, Jinghui
Urban region representation is crucial for various urban downstream tasks. However, despite the proliferation of methods and their success, acquiring general urban region knowledge and adapting to different tasks remains challenging. Previous work of
Externí odkaz:
http://arxiv.org/abs/2408.05920
High frame-rate (HFR) videos of action recognition improve fine-grained expression while reducing the spatio-temporal relation and motion information density. Thus, large amounts of video samples are continuously required for traditional data-driven
Externí odkaz:
http://arxiv.org/abs/2407.16344
What happens if we train a new Large Language Model (LLM) using data that are at least partially generated by other LLMs? The explosive success of LLMs means that a substantial amount of content online will be generated by LLMs rather than humans, wh
Externí odkaz:
http://arxiv.org/abs/2407.12835
Autor:
WANG Linna, ZHANG Jinghui
Publikováno v:
Zhongguo quanke yixue, Vol 28, Iss 03, Pp 293-298 (2025)
Background Acute kidney injury (AKI) is a common complication of sepsis. Immune-inflammatory markers are commonly used to assess the prognosis of these patients. However, studies evaluating microRNAs (miR) in this context are scarce, indicating a nee
Externí odkaz:
https://doaj.org/article/3d925c77017e4137a0bb8fb1ad5efec9
Autor:
Wang, Yuchen, Zhang, Jinghui, Huang, Zhengjie, Li, Weibin, Feng, Shikun, Ma, Ziheng, Sun, Yu, Yu, Dianhai, Dong, Fang, Jin, Jiahui, Wang, Beilun, Luo, Junzhou
Node classification is a substantial problem in graph-based fraud detection. Many existing works adopt Graph Neural Networks (GNNs) to enhance fraud detectors. While promising, currently most GNN-based fraud detectors fail to generalize to the low ho
Externí odkaz:
http://arxiv.org/abs/2302.10407
Autor:
Zhang, Jinghui1 (AUTHOR) 542651213@qq.com, Liu, Guangtao1 (AUTHOR), Han, Wenji1 (AUTHOR), Liu, Ling1 (AUTHOR), Wang, Ziming1 (AUTHOR)
Publikováno v:
Scientific Reports. 11/27/2024, Vol. 14 Issue 1, p1-19. 19p.