{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:08:57Z","timestamp":1777651737137,"version":"3.51.4"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"07","license":[{"start":{"date-parts":[[2020,4,3]],"date-time":"2020-04-03T00:00:00Z","timestamp":1585872000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.aaai.org"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Weakly-supervised temporal action localization is a very challenging problem because frame-wise labels are not given in the training stage while the only hint is video-level labels: whether each video contains action frames of interest. Previous methods aggregate frame-level class scores to produce video-level prediction and learn from video-level action labels. This formulation does not fully model the problem in that background frames are forced to be misclassified as action classes to predict video-level labels accurately. In this paper, we design Background Suppression Network (BaS-Net) which introduces an auxiliary class for background and has a two-branch weight-sharing architecture with an asymmetrical training strategy. This enables BaS-Net to suppress activations from background frames to improve localization performance. Extensive experiments demonstrate the effectiveness of BaS-Net and its superiority over the state-of-the-art methods on the most popular benchmarks \u2013 THUMOS'14 and ActivityNet. Our code and the trained model are available at https:\/\/github.com\/Pilhyeon\/BaSNet-pytorch.<\/jats:p>","DOI":"10.1609\/aaai.v34i07.6793","type":"journal-article","created":{"date-parts":[[2020,6,29]],"date-time":"2020-06-29T18:38:16Z","timestamp":1593455896000},"page":"11320-11327","source":"Crossref","is-referenced-by-count":205,"title":["Background Suppression Network for Weakly-Supervised Temporal Action Localization"],"prefix":"10.1609","volume":"34","author":[{"given":"Pilhyeon","family":"Lee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youngjung","family":"Uh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyeran","family":"Byun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2020,4,3]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/6793\/6647","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/6793\/6647","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T00:42:21Z","timestamp":1667522541000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/6793"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,3]]},"references-count":0,"journal-issue":{"issue":"07","published-online":{"date-parts":[[2020,6,18]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v34i07.6793","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2020,4,3]]}}}