{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T20:05:27Z","timestamp":1778789127889,"version":"3.51.4"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272494"],"award-info":[{"award-number":["62272494"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876045"],"award-info":[{"award-number":["61876045"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206060"],"award-info":[{"award-number":["62206060"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836012"],"award-info":[{"award-number":["61836012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515012845"],"award-info":[{"award-number":["2023A1515012845"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515011374"],"award-info":[{"award-number":["2023A1515011374"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental Research Funds for the Central Universities, Sun Yat-sen University","award":["23ptpy111"],"award-info":[{"award-number":["23ptpy111"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tcsvt.2023.3329220","type":"journal-article","created":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T18:31:46Z","timestamp":1698863506000},"page":"7005-7016","source":"Crossref","is-referenced-by-count":25,"title":["Contrastive Transformer Learning With Proximity Data Generation for Text-Based Person Search"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2132-6515","authenticated-orcid":false,"given":"Hefeng","family":"Wu","sequence":"first","affiliation":[{"name":"Guangdong Province Key Laboratory of Information Security Technology, School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5040-4618","authenticated-orcid":false,"given":"Weifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Guangdong Province Key Laboratory of Information Security Technology, School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhibin","family":"Liu","sequence":"additional","affiliation":[{"name":"Guangdong Province Key Laboratory of Information Security Technology, School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5848-5624","authenticated-orcid":false,"given":"Tianshui","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Guangdong University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiguang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2248-3755","authenticated-orcid":false,"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"Guangdong Province Key Laboratory of Information Security Technology, School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00190"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938523"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20370"},{"key":"ref5","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093640"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3025814"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref12","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref13","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.081"},{"key":"ref15","article-title":"Contextual non-local alignment over full-scale representation for text-based person search","author":"Gao","year":"2021","journal-title":"arXiv:2101.03036"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6777"},{"key":"ref18","first-page":"1","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Saharia"},{"key":"ref19","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref20","article-title":"Control-a-video: Controllable text-to-video generation with diffusion models","author":"Chen","year":"2023","journal-title":"arXiv:2305.13840"},{"key":"ref21","article-title":"Semantically self-aligned network for text-to-image part-aware person re-identification","author":"Ding","year":"2021","journal-title":"arXiv:2107.12666"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3073718"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548028"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_42"},{"key":"ref27","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Touvron"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref29","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref30","first-page":"1","article-title":"FILIP: Fine-grained interactive language-image pre-training","volume-title":"Proc. 10th Int. Conf. Learn. Represent. (ICLR)","author":"Yao"},{"key":"ref31","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. (ICML)","volume":"162","author":"Li"},{"key":"ref32","first-page":"1","article-title":"Large scale GAN training for high fidelity natural image synthesis","volume-title":"Proc. 7th Int. Conf. Learn. Represent. (ICLR)","author":"Brock"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2970919"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2106.12423"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3157444"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref38","first-page":"1","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"Proc. 11th Int. Conf. Learn. Represent. (ICLR)","author":"Hertz"},{"key":"ref39","article-title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","author":"Couairon","year":"2022","journal-title":"arXiv:2210.11427"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref43","first-page":"1","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Ho"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref45","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Song"},{"key":"ref46","volume-title":"SpaCy: Industrial-strength natural language processing in Python","author":"Honnibal","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref48","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00252"},{"key":"ref50","first-page":"1","article-title":"Text-based person search with limited data","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Han"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25072-9_42"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10634006\/10303286.pdf?arnumber=10303286","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T17:43:31Z","timestamp":1723571011000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10303286\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":51,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3329220","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}