{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:47:00Z","timestamp":1753602420002},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icasspw59220.2023.10192960","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:54Z","timestamp":1690997454000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Investigating Pooling Strategies and Loss Functions for Weakly-Supervised Text-to-Audio Grounding via Contrastive Learning"],"prefix":"10.1109","author":[{"given":"Xuenan","family":"Xu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence X-LANCE Lab,Department of Computer Science and Engineering AI Institute,Shanghai,China"}]},{"given":"Mengyue","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence X-LANCE Lab,Department of Computer Science and Engineering AI Institute,Shanghai,China"}]},{"given":"Kai","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence X-LANCE Lab,Department of Computer Science and Engineering AI Institute,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682847"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747336"},{"key":"ref15","article-title":"Vse++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2018","journal-title":"Proceedings of British Machine Vision Conference (BMVC)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11115"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053459"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6915"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747556"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/111"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052995"},{"key":"ref2","article-title":"Weakly-supervised video object grounding from text by loss weighting and object interaction","author":"zhou","year":"2018","journal-title":"Proceedings of British Machine Vision Conference (BMVC)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref17","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proceedings of International Conference on Machine Learning (ICML)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01302"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414579"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref8","article-title":"Query-graph with cross-gating attention model for text-to-audio grounding","author":"tang","year":"2021","journal-title":"arXiv preprint arXiv 2106 14881"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054478"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414834"},{"key":"ref3","article-title":"A survey on temporal sentence grounding in videos","author":"lan","year":"2021","journal-title":"ACM Transactions on Multimedia Computing Communications and Applications (TOMM)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2005.1540194"}],"event":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10192576\/10192577\/10192960.pdf?arnumber=10192960","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:42:52Z","timestamp":1692639772000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10192960\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icasspw59220.2023.10192960","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}