{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:42:59Z","timestamp":1773801779640,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"13","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Event cameras deliver visual information characterized by a high dynamic range and high temporal resolution, offering significant advantages in estimating optical flow for complex lighting conditions and fast-moving objects. Current advanced optical flow methods for event cameras largely adopt established image-based frameworks. However, the spatial sparsity of event data limits their performance. In this paper, we present BAT, an innovative framework that estimates event-based optical flow using bidirectional adaptive temporal correlation. BAT includes three novel designs: 1) a bidirectional temporal correlation that transforms bidirectional temporally dense motion cues into spatially dense ones, enabling accurate and spatially dense optical flow estimation; 2) an adaptive temporal sampling strategy for maintaining temporal consistency in correlation; 3) spatially adaptive temporal motion aggregation to efficiently and adaptively aggregate consistent target motion features into adjacent motion features while suppressing inconsistent ones. Our BAT achieves\nstate-of-the-art performance on the DSEC-Flow benchmark,\noutperforming existing methods by a large margin while also\nexhibiting sharp edges and high-quality details. Our BAT can\naccurately predict future optical flow using only past events,\nsignificantly outperforming E-RAFT\u2019s warm-start approach.<\/jats:p>","DOI":"10.1609\/aaai.v40i13.38100","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:59:27Z","timestamp":1773791967000},"page":"11205-11213","source":"Crossref","is-referenced-by-count":0,"title":["BAT: Learning Event-based Optical Flow with Bidirectional Adaptive Temporal Correlation"],"prefix":"10.1609","volume":"40","author":[{"given":"Gangwei","family":"Xu","sequence":"first","affiliation":[]},{"given":"Haotong","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Zhaoxing","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Hongcheng","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Haiyang","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Yang","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\/38100\/42062","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38100\/42062","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:59:28Z","timestamp":1773791968000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38100"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i13.38100","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]]}}}