{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:43:24Z","timestamp":1772934204665,"version":"3.50.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"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":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11400868","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["False Negative Aware Learning for Cross-Modal Video-Text Retrieval: When Intra-Modal Auxiliary Signals Meet Cross-Modal Objectives"],"prefix":"10.1109","author":[{"given":"Yichao","family":"Deng","sequence":"first","affiliation":[{"name":"School of Engineering and IT, The University of Melbourne,Melbourne,Australia"}]},{"given":"Birong","family":"Sima","sequence":"additional","affiliation":[{"name":"School of Media and Information Engineering, Yunnan Open University,Kunming,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"139","author":"Radford"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1016\/j.neucom.2022.07.028","article-title":"Clip4clip: An empirical study of clip for end to end video clip retrieval and captioning","volume":"508","author":"Luo","year":"2022","journal-title":"Neurocomputing"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02579"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00148"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02563"},{"key":"ref9","volume-title":"Nv-retriever: Improving text embedding models with effective hard-negative mining","author":"Moreira","year":"2025"},{"key":"ref10","volume-title":"Contrastive alignment with semantic gap-aware corrections in text-video retrieval","author":"Xiao","year":"2025"},{"key":"ref11","article-title":"Internvideo2: Scaling video foundation models for multimodal video understanding","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","volume-title":"Clip-vip: Adapting pre-trained image-text model to video-language representation alignment","author":"Xue","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref14","volume-title":"Learning language-visual embedding for movie understanding with natural-language","author":"Torabi","year":"2016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.20"},{"key":"ref17","article-title":"Support-set bottlenecks for video-text representation learning","author":"Patrick","year":"2021","journal-title":"ICLR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00234"},{"key":"ref19","volume-title":"Teachclip: Multi-grained teaching for efficient text-to-video retrieval","author":"Tian","year":"2023"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1007\/s11263-025-02535-y","volume-title":"Positive-augmented contrastive learning for vision-and-language evaluation and training","author":"Sarto","year":"2025"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11400868.pdf?arnumber=11400868","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T07:02:20Z","timestamp":1772866940000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11400868\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11400868","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}