Zobrazeno 1 - 10
of 544
pro vyhledávání: '"Cao, Qiong"'
Tracking by detection has been the prevailing paradigm in the field of Multi-object Tracking (MOT). These methods typically rely on the Kalman Filter to estimate the future locations of objects, assuming linear object motion. However, they fall short
Externí odkaz:
http://arxiv.org/abs/2408.09178
Generating 3D scenes from human motion sequences supports numerous applications, including virtual reality and architectural design. However, previous auto-regression-based human-aware 3D scene generation methods have struggled to accurately capture
Externí odkaz:
http://arxiv.org/abs/2406.18159
Pose estimation aims to accurately identify anatomical keypoints in humans and animals using monocular images, which is crucial for various applications such as human-machine interaction, embodied AI, and autonomous driving. While current models show
Externí odkaz:
http://arxiv.org/abs/2406.14367
This paper addresses the problem of generating lifelike holistic co-speech motions for 3D avatars, focusing on two key aspects: variability and coordination. Variability allows the avatar to exhibit a wide range of motions even with similar speech co
Externí odkaz:
http://arxiv.org/abs/2404.00368
This paper addresses the problem of generating 3D interactive human motion from text. Given a textual description depicting the actions of different body parts in contact with static objects, we synthesize sequences of 3D body poses that are visually
Externí odkaz:
http://arxiv.org/abs/2403.15709
Temporal action detection (TAD) aims to detect all action boundaries and their corresponding categories in an untrimmed video. The unclear boundaries of actions in videos often result in imprecise predictions of action boundaries by existing methods.
Externí odkaz:
http://arxiv.org/abs/2309.05590
Demystifying complex human-ground interactions is essential for accurate and realistic 3D human motion reconstruction from RGB videos, as it ensures consistency between the humans and the ground plane. Prior methods have modeled human-ground interact
Externí odkaz:
http://arxiv.org/abs/2306.16736
Autor:
Xiao, Changcheng, Cao, Qiong, Zhong, Yujie, Lan, Long, Zhang, Xiang, Luo, Zhigang, Tao, Dacheng
Significant progress has been achieved in multi-object tracking (MOT) through the evolution of detection and re-identification (ReID) techniques. Despite these advancements, accurately tracking objects in scenarios with homogeneous appearance and het
Externí odkaz:
http://arxiv.org/abs/2306.02585
In this paper, we present a one-stage framework TriDet for temporal action detection. Existing methods often suffer from imprecise boundary predictions due to the ambiguous action boundaries in videos. To alleviate this problem, we propose a novel Tr
Externí odkaz:
http://arxiv.org/abs/2303.07347
Autor:
Xue, Chao, Liu, Wei, Xie, Shuai, Wang, Zhenfang, Li, Jiaxing, Peng, Xuyang, Ding, Liang, Zhao, Shanshan, Cao, Qiong, Yang, Yibo, He, Fengxiang, Cai, Bohua, Bian, Rongcheng, Zhao, Yiyan, Zheng, Heliang, Liu, Xiangyang, Liu, Dongkai, Liu, Daqing, Shen, Li, Li, Chang, Zhang, Shijin, Zhang, Yukang, Chen, Guanpu, Chen, Shixiang, Zhan, Yibing, Zhang, Jing, Wang, Chaoyue, Tao, Dacheng
Automated machine learning (AutoML) seeks to build ML models with minimal human effort. While considerable research has been conducted in the area of AutoML in general, aiming to take humans out of the loop when building artificial intelligence (AI)
Externí odkaz:
http://arxiv.org/abs/2303.00501