{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:21:47Z","timestamp":1774419707786,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890183","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Text-Infused Audio-Visual Video Parsing with Semantic-Aware Multimodal Contrastive Learning"],"prefix":"10.1109","author":[{"given":"Pengcheng","family":"Zhao","sequence":"first","affiliation":[{"name":"Hefei University of Technology,Hefei,China"}]},{"given":"Yanxiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Hefei University of Technology,Hefei,China"}]},{"given":"Dan","family":"Guo","sequence":"additional","affiliation":[{"name":"Hefei University of Technology,Hefei,China"}]},{"given":"Yuanzhi","family":"Yao","sequence":"additional","affiliation":[{"name":"Hefei University of Technology,Hefei,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_26"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00833"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223688"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_3"},{"key":"ref5","article-title":"Towards open-vocabulary audio-visual event localization","author":"Zhou","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_22"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02261-x"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680612"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28116"},{"key":"ref11","article-title":"Audio-visual instance segmentation","author":"Guo","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33134"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32538"},{"key":"ref14","first-page":"34 722","article-title":"Multi-modal grouping network for weakly-supervised audio-visual video parsing","volume":"35","author":"Mo","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097072"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3337134"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547869"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548309"},{"key":"ref19","first-page":"11 449","article-title":"Exploring cross-video and cross-modality signals for weakly-supervised audiovisual video parsing","volume":"34","author":"Lin","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00138"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_25"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref23","first-page":"1","article-title":"Improving audio-visual video parsing with pseudo visual labels","author":"Zhou","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02142-3"},{"key":"ref25","first-page":"73 633","article-title":"Modality-independent teachers meet weakly-supervised audio-visual event parser","volume":"36","author":"Lai","year":"2023","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref29","first-page":"18 661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref30","first-page":"1","article-title":"Contrastive learning for multi-label classification","author":"Zaigrajew","year":"2022","journal-title":"NeurIPS workshops"},{"key":"ref31","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref32","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding","author":"Yang","year":"2019"},{"key":"ref33","first-page":"1","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref34","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890183.pdf?arnumber=10890183","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:13Z","timestamp":1774416253000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890183\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890183","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}