{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:35:15Z","timestamp":1773801315178,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Multi-person eyeblink detection in untrimmed in-the-wild videos is a recently emerged and challenging task. Due to its significant spatio-temporal fine-grained characteristics compared to general actions, we empirically find that general action detectors, though effective in general domains, struggle with this task (i.e., Blink-AP &lt; 2%). Specialized eyeblink detection methods alleviate it through fine-grained spatio-temporal operations. SOTA method proposes a unified model combining instance-aware face localization and eyeblink detection through joint multi-task learning and feature sharing. While effective, it exhibits two critical limitations that may contribute to its unsatisfactory performance (i.e., Blink-AP=10.11%): (1) Face localization and eyeblink detection require distinct spatio-temporal feature granularities, making joint modeling in a unified feature space suboptimal. (2) Eyeblink task training could be largely affected by unstable face-eye feature learning under the joint training paradigm. To address this, we propose DeFB, a decomposed feature learning paradigm with favorable effectiveness and efficiency: (1) We model faces and eyes in granularity-specific feature spaces, which enhances fine-grained perception while reducing computational costs compared to a unified feature space. (2) To mitigate face-eye feature learning instability, we adopt an asynchronous learning mechanism where eye feature learning refines well-trained coarse face features, with shared queries acting as a bridge between stages to retain the efficient feature sharing of existing unified models. Compared with SOTA method, DeFB doubles the performance (Blink-AP: 24.65% v.s. 10.11%) while boosting efficiency by nearly 35%. DeFB can also be integrated as a plug-in to substantially augment the eyeblink detection capabilities of general action detectors.<\/jats:p>","DOI":"10.1609\/aaai.v40i5.37411","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:07:40Z","timestamp":1773788860000},"page":"4076-4084","source":"Crossref","is-referenced-by-count":0,"title":["DeFB: Decomposed Feature Learning for Real-Time Multi-Person Eyeblink Detection in Untrimmed In-the-Wild Videos"],"prefix":"10.1609","volume":"40","author":[{"given":"Jinfang","family":"Gan","sequence":"first","affiliation":[]},{"given":"Wenzheng","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Xintao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Chaoyang","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Ran","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Ran","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Min","family":"Du","sequence":"additional","affiliation":[]},{"given":"Zhiguo","family":"Cao","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37411\/41373","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37411\/41373","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:07:41Z","timestamp":1773788861000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/37411"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i5.37411","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}