{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T10:48:33Z","timestamp":1782038913560,"version":"3.54.5"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687550","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":6,"title":["ProTA: Probabilistic Token Aggregation for Text-Video Retrieval"],"prefix":"10.1109","author":[{"given":"Han","family":"Fang","sequence":"first","affiliation":[{"name":"China Telecom Corporation Ltd. Data&AI Technology Company"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianghao","family":"Zang","sequence":"additional","affiliation":[{"name":"China Telecom Corporation Ltd. Data&AI Technology Company"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Ban","sequence":"additional","affiliation":[{"name":"China Telecom Corporation Ltd. Data&AI Technology Company"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zerun","family":"Feng","sequence":"additional","affiliation":[{"name":"China Telecom Corporation Ltd. Data&AI Technology Company"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lanxiang","family":"Zhou","sequence":"additional","affiliation":[{"name":"China Telecom Corporation Ltd. Data&AI Technology Company"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongjiang","family":"He","sequence":"additional","affiliation":[{"name":"China Telecom Corporation Ltd. Data&AI Technology Company"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongxiang","family":"Li","sequence":"additional","affiliation":[{"name":"China Telecom Corporation Ltd. Data&AI Technology Company"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Sun","sequence":"additional","affiliation":[{"name":"China Telecom Corporation Ltd. Data&AI Technology Company"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss","author":"Cheng","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref4","article-title":"Use what you have: Video retrieval using representations from collaborative experts","author":"Liu","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3227416"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00374"},{"key":"ref9","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref10","article-title":"Modeling uncertainty with hedged instance embedding","author":"Oh","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01430"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0987-1"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"ref16","article-title":"Learning a text-video embedding from incomplete and heterogeneous data","author":"Miech","year":"2018"},{"key":"ref17","article-title":"Disentangled representation learning for text-video retrieval","author":"Wang","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_19"},{"key":"ref21","article-title":"Center-clip: Token clustering for efficient text-video retrieval","author":"Zhao","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01138"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01031"},{"key":"ref24","article-title":"Decaf: A deep convolutional activation feature for generic visual recognition","volume-title":"ICML","author":"Donahue"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687550.pdf?arnumber=10687550","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T19:23:46Z","timestamp":1736969026000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687550\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687550","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}