{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T11:24:19Z","timestamp":1757589859147,"version":"3.43.0"},"reference-count":18,"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"}],"funder":[{"DOI":"10.13039\/501100003696","name":"Electronics and Telecommunications Research Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003696","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,15]]},"DOI":"10.1109\/avss61716.2024.10672583","type":"proceedings-article","created":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T13:51:42Z","timestamp":1726667502000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["MOVES: Motion-Oriented VidEo Sampling for Natural Language-Based Vehicle Retrieval"],"prefix":"10.1109","author":[{"given":"Dongyoung","family":"Kim","sequence":"first","affiliation":[{"name":"Ulsan National Institute of Science Technology (UNIST),South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyoungoh","family":"Lee","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute (ETRI),South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"In-Su","family":"Jang","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute (ETRI),South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kwang-Ju","family":"Kim","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute (ETRI),South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pyong-Kun","family":"Kim","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute (ETRI),South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaejun","family":"Yoo","sequence":"additional","affiliation":[{"name":"Ulsan National Institute of Science Technology (UNIST),South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Cityflow-nl: Tracking and retrieval of vehicles at city scale by natural language descriptions","author":"Feng","year":"2021","journal-title":"arXiv preprint arXiv:2101.04741"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00364"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00455"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00470"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00458"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref8","article-title":"Internvideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022","journal-title":"arXiv preprint arXiv:2212.03191"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref10","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint arXiv:1409.1556"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00900"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00363"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00572"},{"key":"ref14","article-title":"Video-mae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","author":"Tong","year":"2022","journal-title":"arXiv preprint arXiv:2203.12602"},{"key":"ref15","article-title":"Uniformerv2: Spatiotemporal learning by arming image vits with video uniformer","author":"Li","year":"2022","journal-title":"arXiv preprint arXiv:2211.09552"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00583"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00571"}],"event":{"name":"2024 IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)","start":{"date-parts":[[2024,7,15]]},"location":"Niagara Falls, ON, Canada","end":{"date-parts":[[2024,7,16]]}},"container-title":["2024 IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10672516\/10672563\/10672583.pdf?arnumber=10672583","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T17:40:39Z","timestamp":1754588439000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10672583\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/avss61716.2024.10672583","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}