{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T12:43:08Z","timestamp":1768394588312,"version":"3.49.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,21]]},"DOI":"10.1109\/mmsp64401.2025.11324394","type":"proceedings-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T20:55:15Z","timestamp":1768337715000},"page":"84-89","source":"Crossref","is-referenced-by-count":0,"title":["CG-SMFNet: Consensus-Guided Selective Multimodal Fusion for Weakly Supervised Temporal Action Localization"],"prefix":"10.1109","author":[{"given":"Peng","family":"Liu","sequence":"first","affiliation":[{"name":"Beihang University,School of Instrumentation and Optoelectronic Engineering,Beijing,China"}]},{"given":"Zitai","family":"Jiang","sequence":"additional","affiliation":[{"name":"Beihang University,School of Instrumentation and Optoelectronic Engineering,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5862","article-title":"VNL-STES: A Benchmark Dataset and Model for Spatiotemporal Event Spotting in Volleyball Analytics[C]","volume-title":"CVPR","volume":"2025","author":"Nguyen"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S1473-3099(13)70108-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.02.006"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3330794"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02248"},{"key":"ref6","first-page":"7094","article-title":"Graph convolutional networks for temporal action localization[C]","volume-title":"ICCV","volume":"2019","author":"Zeng"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00327"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3195321"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2025.3528727"},{"key":"ref10","first-page":"19914","article-title":"Exploring denoised cross-video contrast for weakly-supervised temporal action localization[C]","volume-title":"CVPR","volume":"2022","author":"Li"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20216"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475261"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3193752"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/a13110301"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122000"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref19","first-page":"7479","article-title":"Basnet: Boundary-aware salient object detection[C]","volume-title":"CVPR","volume":"2019","author":"Qin"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_43"},{"key":"ref21","first-page":"9969","article-title":"Action unit memory network for weakly supervised temporal action localization[C]","volume-title":"CVPR","volume":"2021","author":"Luo"},{"key":"ref22","first-page":"8002","article-title":"Foreground-action consistency network for weakly supervised temporal action localization[C]","volume-title":"ICCV","volume":"2021","author":"Huang"},{"key":"ref23","first-page":"19999","article-title":"Fine-grained temporal contrastive learning for weakly-supervised temporal action localization[C]","volume-title":"CVPR","volume":"2022","author":"Gao"},{"key":"ref24","first-page":"13925","article-title":"Asm-loc: Action-aware segment modeling for weakly-supervised temporal action localization[C]","volume-title":"CVPR","volume":"2022","author":"He"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3244411"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3377468"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00237"}],"event":{"name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","location":"Beijing, China","start":{"date-parts":[[2025,9,21]]},"end":{"date-parts":[[2025,9,23]]}},"container-title":["2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11324077\/11324018\/11324394.pdf?arnumber=11324394","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T07:48:11Z","timestamp":1768376891000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11324394\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,21]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/mmsp64401.2025.11324394","relation":{},"subject":[],"published":{"date-parts":[[2025,9,21]]}}}