{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T13:16:53Z","timestamp":1769087813415,"version":"3.49.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/cbmi66578.2025.11339243","type":"proceedings-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:38:56Z","timestamp":1768941536000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Mitigating Shortcut Learning in Online Action Detection and Anticipation via Cross-Modal Semantic Alignment"],"prefix":"10.1109","author":[{"given":"Sensen","family":"Wang","sequence":"first","affiliation":[{"name":"Xi'an Jiaotong University,College of Artificial Intelligence,Xi’ an,China"}]},{"given":"Yuehu","family":"Liu","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University,College of Artificial Intelligence,Xi’ an,China"}]},{"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University,College of Artificial Intelligence,Xi’ an,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_17"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.39"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681456"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967279"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240548"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3313258"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00316"},{"key":"ref9","first-page":"1086","article-title":"Long short-term transformer for online action detection","volume":"34","author":"Xu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01930"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01271"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_28"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"ref14","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning. PMLR","author":"Radford","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.03.022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref18","volume-title":"THUMOS challenge: Action recognition with a large number of classes","author":"Jiang","year":"2014"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_17"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.92"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00563"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref23","author":"Chung","year":"2014","journal-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5555\/3042817.3043083"},{"key":"ref26","author":"Lipton","year":"2015","journal-title":"A critical review of recurrent neural networks for sequence learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00949"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00089"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1518"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650511"},{"issue":"11","key":"ref34","article-title":"Visualizing data using t -sne","volume":"9","author":"der Maaten Laurens","year":"2008","journal-title":"Journal of machine learning research"}],"event":{"name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","location":"Dublin, Ireland","start":{"date-parts":[[2025,10,22]]},"end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 International Conference on Content-Based Multimedia Indexing (CBMI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11339229\/11339242\/11339243.pdf?arnumber=11339243","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T21:07:04Z","timestamp":1769029624000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11339243\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/cbmi66578.2025.11339243","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}