{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:51:49Z","timestamp":1753602709190,"version":"3.37.3"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4202049"],"award-info":[{"award-number":["4202049"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/icme52920.2022.9859629","type":"proceedings-article","created":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T19:45:18Z","timestamp":1661543118000},"page":"01-06","source":"Crossref","is-referenced-by-count":2,"title":["Spatial-Temporal Alignment via Optimal Transport for Video-Text Retrieval"],"prefix":"10.1109","author":[{"given":"Zerun","family":"Feng","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications,Beijing Key Laboratory of Network System Architecture and Convergence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhimin","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications,Beijing Key Laboratory of Network System Architecture and Convergence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Caili","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications,Beijing Key Laboratory of Network System Architecture and Convergence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications,Beijing Key Laboratory of Network System Architecture and Convergence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"China Telecom Dict Application Capability Center,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2408346"},{"key":"ref11","article-title":"Vse++: Improving visual-semantic em-beddings with hard negatives","author":"faghri","year":"2018","journal-title":"BMVC"},{"key":"ref12","first-page":"3377","article-title":"Pre-dicting visual features from text for image and video caption retrieval","volume":"20","author":"dong","year":"2018","journal-title":"TMM"},{"key":"ref13","article-title":"Simple bert models for relation extraction and semantic role labeling","author":"shi","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1113"},{"key":"ref15","article-title":"Sinkhorn distances: lightspeed compu-tation of optimal transport","author":"cuturi","year":"2013","journal-title":"NIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.502"},{"key":"ref4","article-title":"Fine-grained video-text retrieval with hierarchical graph rea-soning","author":"chen","year":"2020","journal-title":"CVPR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref6","volume":"338","author":"villani","year":"2008","journal-title":"Optimal Transport Old and New"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1561\/2200000073"},{"key":"ref8","article-title":"Semantic correspondence as an optimal trans-port problem","author":"liu","year":"2020","journal-title":"CVPR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-011-9093-5"},{"key":"ref2","article-title":"Exploiting visual semantic reasoning for video-text re-trieval","author":"feng","year":"2020","journal-title":"IJCAI"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00957"},{"key":"ref9","article-title":"Graph optimal transport for cross-domain alignment","author":"chen","year":"2020","journal-title":"ICML"}],"event":{"name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2022,7,18]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2022,7,22]]}},"container-title":["2022 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9859562\/9858923\/09859629.pdf?arnumber=9859629","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T20:25:15Z","timestamp":1663619115000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9859629\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icme52920.2022.9859629","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}