{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:23:30Z","timestamp":1740169410859,"version":"3.37.3"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100015282","name":"Foundation of China Academy of Railway Sciences","doi-asserted-by":"publisher","award":["2023YJ138"],"award-info":[{"award-number":["2023YJ138"]}],"id":[{"id":"10.13039\/501100015282","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3447872","type":"journal-article","created":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T18:47:25Z","timestamp":1724352445000},"page":"119563-119576","source":"Crossref","is-referenced-by-count":0,"title":["MVItem: A Benchmark for Multi-View Cross-Modal Item Retrieval"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2892-8911","authenticated-orcid":false,"given":"Bo","family":"Li","sequence":"first","affiliation":[{"name":"Postgraduate Department, China Academy of Railway Sciences, Beijing, China"}]},{"given":"Jiansheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Science, Technology and Information, China Railway, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0776-3719","authenticated-orcid":false,"given":"Linlin","family":"Dai","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, China Academy of Railway Sciences Corporation Ltd., Beijing, China"}]},{"given":"Hui","family":"Jing","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, China Academy of Railway Sciences Corporation Ltd., Beijing, China"}]},{"given":"Zhizheng","family":"Huang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, China Academy of Railway Sciences Corporation Ltd., Beijing, China"}]},{"given":"Yuteng","family":"Sui","sequence":"additional","affiliation":[{"name":"Postgraduate Department, China Academy of Railway Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3291237"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01157"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3029387.3029420"},{"key":"ref4","article-title":"RPC: A large-scale retail product checkout dataset","author":"Wei","year":"2019","journal-title":"arXiv:1901.07249"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3453892.3453894"},{"key":"ref6","article-title":"Products-10K: A large-scale product recognition dataset","author":"Bai","year":"2020","journal-title":"arXiv:2008.10545"},{"key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref9","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv:2205.01917"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02169"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref13","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv:1504.00325"},{"key":"ref14","article-title":"LAION-400M: Open dataset of CLIP-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv:2111.02114"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00883"},{"key":"ref16","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_29"},{"key":"ref18","article-title":"RP2K: A large-scale retail product dataset for fine-grained image classification","author":"Peng","year":"2020","journal-title":"arXiv:2006.12634"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2009.09.002"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3218591"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_41"},{"key":"ref22","article-title":"Deep region hashing for efficient large-scale instance search from images","author":"Song","year":"2017","journal-title":"arXiv:1701.07901"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.442"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref28","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref29","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43895-0_10"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01752"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACII59096.2023.10388075"},{"key":"ref33","first-page":"1","article-title":"Cola: A benchmark for compositional text-to-image retrieval","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Ray"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3348599"},{"key":"ref35","article-title":"UFineBench: Towards text-based person retrieval with ultra-fine granularity","author":"Zuo","year":"2023","journal-title":"arXiv:2312.03441"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01834"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00583"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00466"},{"volume-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90%* chatgpt quality","year":"2023","author":"Chiang","key":"ref39"},{"key":"ref40","article-title":"Long-CLIP: Unlocking the long-text capability of CLIP","author":"Zhang","year":"2024","journal-title":"arXiv:2403.15378"},{"key":"ref41","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10643520.pdf?arnumber=10643520","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,14]],"date-time":"2024-09-14T05:17:30Z","timestamp":1726291050000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10643520\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3447872","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}