Zobrazeno 1 - 10
of 61
pro vyhledávání: '"Su, Haisheng"'
Current end-to-end autonomous driving methods resort to unifying modular designs for various tasks (e.g. perception, prediction and planning). Although optimized in a planning-oriented spirit with a fully differentiable framework, existing end-to-end
Externí odkaz:
http://arxiv.org/abs/2409.09777
Robust object detection and tracking under arbitrary sight of view is challenging yet essential for the development of Autonomous Vehicle technology. With the growing demand of unmanned function vehicles, near-field scene understanding becomes an imp
Externí odkaz:
http://arxiv.org/abs/2408.15503
Autor:
Li, Yong-Lu, Fan, Hongwei, Qiu, Zuoyu, Dou, Yiming, Xu, Liang, Fang, Hao-Shu, Guo, Peiyang, Su, Haisheng, Wang, Dongliang, Wu, Wei, Lu, Cewu
Spatio-temporal Human-Object Interaction (ST-HOI) detection aims at detecting HOIs from videos, which is crucial for activity understanding. In daily HOIs, humans often interact with a variety of objects, e.g., holding and touching dozens of househol
Externí odkaz:
http://arxiv.org/abs/2211.07501
Distracted driving causes thousands of deaths per year, and how to apply deep-learning methods to prevent these tragedies has become a crucial problem. In Track3 of the 6th AI City Challenge, researchers provide a high-quality video dataset with dens
Externí odkaz:
http://arxiv.org/abs/2207.02042
Autor:
Yu, Shoubin, Zhao, Zhongyin, Fang, Haoshu, Deng, Andong, Su, Haisheng, Wang, Dongliang, Gan, Weihao, Lu, Cewu, Wu, Wei
Anomaly detection in surveillance videos is challenging and important for ensuring public security. Different from pixel-based anomaly detection methods, pose-based methods utilize highly-structured skeleton data, which decreases the computational bu
Externí odkaz:
http://arxiv.org/abs/2112.03649
This technical report presents an overview of our solution used in the submission to 2021 HACS Temporal Action Localization Challenge on both Supervised Learning Track and Weakly-Supervised Learning Track. Temporal Action Localization (TAL) requires
Externí odkaz:
http://arxiv.org/abs/2107.12618
Efficient spatiotemporal modeling is an important yet challenging problem for video action recognition. Existing state-of-the-art methods exploit neighboring feature differences to obtain motion clues for short-term temporal modeling with a simple co
Externí odkaz:
http://arxiv.org/abs/2106.01088
Autor:
Qing, Zhiwu, Su, Haisheng, Gan, Weihao, Wang, Dongliang, Wu, Wei, Wang, Xiang, Qiao, Yu, Yan, Junjie, Gao, Changxin, Sang, Nong
Temporal action proposal generation aims to estimate temporal intervals of actions in untrimmed videos, which is a challenging yet important task in the video understanding field. The proposals generated by current methods still suffer from inaccurat
Externí odkaz:
http://arxiv.org/abs/2103.13141
Autor:
Su, Haisheng, Su, Jing, Wang, Dongliang, Gan, Weihao, Wu, Wei, Wang, Mengmeng, Yan, Junjie, Qiao, Yu
Recent years have witnessed the significant progress of action recognition task with deep networks. However, most of current video networks require large memory and computational resources, which hinders their applications in practice. Existing knowl
Externí odkaz:
http://arxiv.org/abs/2009.06902
Generating human action proposals in untrimmed videos is an important yet challenging task with wide applications. Current methods often suffer from the noisy boundary locations and the inferior quality of confidence scores used for proposal retrievi
Externí odkaz:
http://arxiv.org/abs/2009.07641