A Pursuit of Temporal Accuracy in General Activity Detection
It addresses the challenge of temporal accuracy in activity detection for video analysis applications, representing a strong specific gain rather than a foundational advancement.
The paper tackles the problem of accurately detecting activities in untrimmed videos, particularly in locating temporal boundaries, and achieves significant performance improvements over state-of-the-art methods on THUMOS14 and ActivityNet datasets.
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.