Year: 2017
Type: preprint
Abstract: Detecting activities in untrimmed videos is an important but challenging task. The performance of existing methods remains unsatisfactory, e.g., they often meet difficulties in locating the beginning and end of a long complex action. In this paper, we propose a generic framework that can accurately detect a wide variety of activities from untrimmed videos. Our first contribution is a novel proposal scheme that can efficiently generate candidates with accurate temporal boundaries. The other contribution is a cascaded classification pipeline that explicitly distinguishes between relevance and completeness of a candidate instance. On two challenging temporal activity detection datasets, THUMOS14 and ActivityNet, the proposed framework significantly outperforms the existing state-of-the-art methods, demonstrating superior accuracy and strong adaptivity in handling activities with various temporal structures.
Source: arXiv (Cornell University)
Authors: Xiong, Yuanjun, Zhao, Yue, Wang, Limin, Lin, Dahua, Tang, Xiaoou
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2604114396
