Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Shi, Dingfeng"'
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
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
Designing an incentive-compatible auction mechanism that maximizes the auctioneer's revenue while minimizes the bidders' ex-post regret is an important yet intricate problem in economics. Remarkable progress has been achieved through learning the opt
Externí odkaz:
http://arxiv.org/abs/2210.05579
This work aims at advancing temporal action detection (TAD) using an encoder-decoder framework with action queries, similar to DETR, which has shown great success in object detection. However, the framework suffers from several problems if directly a
Externí odkaz:
http://arxiv.org/abs/2207.07097
Autor:
Shi, Dingfeng, Cheong, Kin-Pang, Jiao, Tengfei, Wu, Junjun, Song, Yong, Liu, Yushuai, Ren, Wei
Publikováno v:
In International Journal of Hydrogen Energy 2 January 2024 52 Part A:133-146
Autor:
Cheong, Kin-Pang1 (AUTHOR) kpcheong@scu.edu.cn, Shi, Dingfeng1 (AUTHOR), Liu, Shaotong1 (AUTHOR), Wu, Junjun2 (AUTHOR) kpcheong@scu.edu.cn, Duan, Kun3 (AUTHOR), Song, Yong4 (AUTHOR), Ren, Wei3 (AUTHOR)
Publikováno v:
Sensors (14248220). Aug2022, Vol. 22 Issue 16, p5939-5939. 11p.
Publikováno v:
ICME
Understanding an image with 3D representations has been an increasingly attractive topic in computer vision. The state-of the-art 3D reconstruction methods usually focus on the reconstruction of the holistic object, while missing important part infor