A Pursuit of Temporal Accuracy in General Activity Detection

8 Mar 2017  ·  Yuanjun Xiong, Yue Zhao, Li-Min Wang, Dahua Lin, Xiaoou Tang ·

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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Temporal Action Localization ActivityNet-1.3 SSN mAP IOU@0.5 39.12 # 28
mAP 32.26 # 29


No methods listed for this paper. Add relevant methods here