Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Zhu, Fangrui"'
Autor:
Cai, Mu, Tan, Reuben, Zhang, Jianrui, Zou, Bocheng, Zhang, Kai, Yao, Feng, Zhu, Fangrui, Gu, Jing, Zhong, Yiwu, Shang, Yuzhang, Dou, Yao, Park, Jaden, Gao, Jianfeng, Lee, Yong Jae, Yang, Jianwei
Understanding fine-grained temporal dynamics is crucial for multimodal video comprehension and generation. Due to the lack of fine-grained temporal annotations, existing video benchmarks mostly resemble static image benchmarks and are incompetent at
Externí odkaz:
http://arxiv.org/abs/2410.10818
Visual relationship understanding has been studied separately in human-object interaction(HOI) detection, scene graph generation(SGG), and referring relationships(RR) tasks. Given the complexity and interconnectedness of these tasks, it is crucial to
Externí odkaz:
http://arxiv.org/abs/2408.08305
Zero-shot referring expression comprehension aims at localizing bounding boxes in an image corresponding to provided textual prompts, which requires: (i) a fine-grained disentanglement of complex visual scene and textual context, and (ii) a capacity
Externí odkaz:
http://arxiv.org/abs/2311.17048
Publikováno v:
应用气象学报, Vol 35, Iss 6, Pp 725-736 (2024)
The Tibetan Plateau, located in the mid-latitude region of the Asian continent, is commonly referred to as the third pole and the water tower of Asia. The high-altitude terrain and distinct circulation systems contribute to the formation of an ozone
Externí odkaz:
https://doaj.org/article/98be30035b7042078d7931cdc973f2e4
We have witnessed significant progress in human-object interaction (HOI) detection. The reliance on mAP (mean Average Precision) scores as a summary metric, however, does not provide sufficient insight into the nuances of model performance (e.g., why
Externí odkaz:
http://arxiv.org/abs/2308.08529
Semantic segmentation is a challenging problem due to difficulties in modeling context in complex scenes and class confusions along boundaries. Most literature either focuses on context modeling or boundary refinement, which is less generalizable in
Externí odkaz:
http://arxiv.org/abs/2107.14209
Autor:
Liang, Tian, Luo, Jiali, Zhang, Chongyang, Tian, Hongying, Bai, Zhixuan, Bian, Jianchun, Wang, Zhiting, Luo, Fuhai, Zhu, Fangrui, Mao, Lixin, He, Xin, Wang, Shuyu, Zhang, Kequan, Zhang, Jiankai
Publikováno v:
In Atmospheric Research March 2024 298
Autor:
Hu, Shengnan, Tang, Xueying, Zhu, Fangrui, Liang, Chen, Wang, Sa, Wang, Hongjie, Li, Peifeng, Li, Yuzhen
Publikováno v:
In Genes & Diseases February 2024
The objective of this paper is self-supervised representation learning, with the goal of solving semi-supervised video object segmentation (a.k.a. dense tracking). We make the following contributions: (i) we propose to improve the existing self-super
Externí odkaz:
http://arxiv.org/abs/2006.12480
Autor:
Qian, Xuelin, Wang, Wenxuan, Zhang, Li, Zhu, Fangrui, Fu, Yanwei, Xiang, Tao, Jiang, Yu-Gang, Xue, Xiangyang
Person re-identification (Re-ID) aims to match a target person across camera views at different locations and times. Existing Re-ID studies focus on the short-term cloth-consistent setting, under which a person re-appears in different camera views wi
Externí odkaz:
http://arxiv.org/abs/2005.12633