{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:27:52Z","timestamp":1774420072873,"version":"3.50.1"},"reference-count":53,"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\/icassp49660.2025.10888493","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Video-Text Matching via Sparse Stratified Sampling"],"prefix":"10.1109","author":[{"given":"Chenyang","family":"Lyu","sequence":"first","affiliation":[{"name":"Alibaba International Digital Commerce,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxi","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianbo","family":"Ji","sequence":"additional","affiliation":[{"name":"Nantong University,Nantong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liting","family":"Zhou","sequence":"additional","affiliation":[{"name":"Dublin City University,Dublin,Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pintu","family":"Lohar","sequence":"additional","affiliation":[{"name":"Sitare University,Indore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yu","sequence":"additional","affiliation":[{"name":"Hiroshima University,Hiroshima,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longyue","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba International Digital Commerce,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5121\/iju.2012.3202"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref3","article-title":"Hierarchical question-image co-attention for visual question answering","author":"Lu","year":"2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350971"},{"key":"ref6","article-title":"Use what you have: Video retrieval using representations from collaborative experts","author":"Liu","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3010650"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2020.3048440"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00204"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3538533"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2024.3402613"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859629"},{"key":"ref18","article-title":"mplug-2: A modularized multi-modal foundation model across text, image and video","author":"Xu","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687688"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.432"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.29"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612132"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475621"},{"key":"ref25","first-page":"2320","article-title":"Stratified sampling meets machine learning","volume-title":"ICML","volume":"48","author":"Liberty"},{"key":"ref26","article-title":"Attention is all you need","volume-title":"CoRR","volume":"abs\/1706.03762","author":"Vaswani","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2832602"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00233"},{"key":"ref31","article-title":"Vse++: Improving visual-semantic embeddings with hard negatives","author":"Faghri","year":"2017"},{"key":"ref32","article-title":"W2vv++ fully deep learning for ad-hoc video search","volume-title":"ACMMM","author":"Li"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401151"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3088863"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_29"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref40","article-title":"Learning a text-video embedding from incomplete and heterogeneous data","author":"Miech","year":"2018"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00774"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00484"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548291"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01852"},{"key":"ref45","article-title":"Decoupled weight decay regularization","volume-title":"ICLR","author":"Loshchilov"},{"key":"ref46","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.5040\/9798881817916.ch-004"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548361"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28238-6_40"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"}],"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\/10888493.pdf?arnumber=10888493","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:15Z","timestamp":1774416375000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888493\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888493","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}