{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T15:49:33Z","timestamp":1776440973595,"version":"3.51.2"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210145","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["EAV-Mamba: Efficient Audio-Visual Representation Learning for Weakly-Supervised Temporal Action Localization"],"prefix":"10.1109","author":[{"given":"Quan","family":"Zhang","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinwei","family":"Fang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxin","family":"Qi","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyang","family":"Wan","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guojun","family":"Ma","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun","family":"Yuan","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Qu","year":"2021","journal-title":"Acm-net: Action context modeling network for weakly-supervised temporal action localization"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00877"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_10"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01339"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00560"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16280"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref12","author":"Simonyan","year":"2014","journal-title":"Very deep convolutional networks for large-scale image recognition"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461392"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01320"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01017"},{"key":"ref19","author":"Qu","year":"2021","journal-title":"Acm-net: Action context modeling network for weakly-supervised temporal action localization"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00877"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_10"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_25"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132058"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01320"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"ref28","author":"Gu","year":"2023","journal-title":"Mamba: Linear-time sequence modeling with selective state spaces"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28539"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_12"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02202"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28516"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00609"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02203"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref37","author":"Gu","year":"2023","journal-title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_43"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3089361"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3178957"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00237"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3287208"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00957"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02401"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32231"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33094"},{"key":"ref47","article-title":"IMDPrompter: Adapting SAM to Image Manipulation Detection by Cross-View Automated Prompt Learning","volume-title":"The Thirteenth International Conference On Learning Representations","author":"Zhang","year":"2025"},{"key":"ref48","author":"Zhang","year":"2024","journal-title":"Can MLLMs Guide Weakly-Supervised Temporal Action Localization Tasks?"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/76"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611976"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096598"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210145.pdf?arnumber=11210145","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T07:00:32Z","timestamp":1766559632000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210145\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210145","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}