We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1703.02716")
get_code_for_paper("1703.02716")
have("1703.02716")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1703.02716.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1703.02716)
Connect an agent — have() is free.