{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:15:44Z","timestamp":1765340144077,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754583","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:47:18Z","timestamp":1761374838000},"page":"9177-9185","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Dialogue-Driven Interactive Dynamic Learning for Text-to-Image Person Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4244-6696","authenticated-orcid":false,"given":"Hongyu","family":"Liu","sequence":"first","affiliation":[{"name":"Dalian University of Technology, Dalian, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8937-1515","authenticated-orcid":false,"given":"Hongwei","family":"Ge","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1168-6645","authenticated-orcid":false,"given":"Yuxuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9929-2650","authenticated-orcid":false,"given":"Yaqing","family":"Hou","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023a. Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)."},{"key":"e_1_3_2_1_3_1","volume-title":"Rasa: Relation and sensitivity aware representation learning for text-based person search. arXiv preprint arXiv:2305.13653","author":"Bai Yang","year":"2023","unstructured":"Yang Bai, Min Cao, Daming Gao, Ziqiang Cao, Chen Chen, Zhenfeng Fan, Liqiang Nie, and Min Zhang. 2023b. Rasa: Relation and sensitivity aware representation learning for text-based person search. arXiv preprint arXiv:2305.13653 (2023)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_4_1","DOI":"10.1609\/aaai.v38i1.27801"},{"key":"e_1_3_2_1_5_1","volume-title":"Semantically self-aligned network for text-to-image part-aware person re-identification. arXiv preprint arXiv:2107.12666","author":"Ding Zefeng","year":"2021","unstructured":"Zefeng Ding, Changxing Ding, Zhiyin Shao, and Dacheng Tao. 2021. Semantically self-aligned network for text-to-image part-aware person re-identification. arXiv preprint arXiv:2107.12666 (2021)."},{"unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024).","key":"e_1_3_2_1_6_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_7_1","DOI":"10.1609\/aaai.v36i4.20370"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_8_1","DOI":"10.1109\/ICCVW60793.2023.00295"},{"key":"e_1_3_2_1_9_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840-6851."},{"key":"e_1_3_2_1_10_1","volume-title":"Adriane Boyd, et al.","author":"Honnibal Matthew","year":"2020","unstructured":"Matthew Honnibal, Ines Montani, Sofie Van Landeghem, Adriane Boyd, et al., 2020. spaCy: Industrial-strength natural language processing in python. (2020)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_11_1","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of naacL-HLT, Vol. 1. Minneapolis, Minnesota."},{"key":"e_1_3_2_1_13_1","volume-title":"Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach. arXiv preprint arXiv:2406.03411","author":"Lee Saehyung","year":"2024","unstructured":"Saehyung Lee, Sangwon Yu, Junsung Park, Jihun Yi, and Sungroh Yoon. 2024. Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach. arXiv preprint arXiv:2406.03411 (2024)."},{"key":"e_1_3_2_1_14_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Levy Matan","year":"2024","unstructured":"Matan Levy, Rami Ben-Ari, Nir Darshan, and Dani Lischinski. 2024. Chatting makes perfect: Chat-based image retrieval. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_15_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_16_1","volume-title":"International conference on machine learning. PMLR, 12888-12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888-12900."},{"key":"e_1_3_2_1_17_1","volume-title":"Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Shafiq Joty, Caiming Xiong, and Steven Chu Hong Hoi. 2021. Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems, Vol. 34 (2021), 9694-9705."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_18_1","DOI":"10.1609\/aaai.v38i4.28101"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_19_1","DOI":"10.1109\/CVPR.2017.551"},{"key":"e_1_3_2_1_20_1","volume-title":"Citation-Enhanced Generation for LLM-based Chatbots. arXiv preprint arXiv:2402.16063","author":"Li Weitao","year":"2024","unstructured":"Weitao Li, Junkai Li, Weizhi Ma, and Yang Liu. 2024b. Citation-Enhanced Generation for LLM-based Chatbots. arXiv preprint arXiv:2402.16063 (2024)."},{"key":"e_1_3_2_1_21_1","first-page":"740","volume-title":"Switzerland","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer vision-ECCV 2014: 13th European conference, zurich, Switzerland, September 6-12, 2014, proceedings, part v 13. Springer, 740-755."},{"unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et al. 2024a. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437 (2024).","key":"e_1_3_2_1_22_1"},{"key":"e_1_3_2_1_23_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2023), 34892-34916."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_24_1","DOI":"10.1609\/aaai.v38i12.29314"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_25_1","DOI":"10.1145\/3503161.3547753"},{"key":"e_1_3_2_1_26_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_27_1","volume-title":"PLOT: Text-Based Person Search with Part Slot Attention for Corresponding Part Discovery. In European Conference on Computer Vision. Springer, 474-490","author":"Park Jicheol","year":"2024","unstructured":"Jicheol Park, Dongwon Kim, Boseung Jeong, and Suha Kwak. 2024. PLOT: Text-Based Person Search with Part Slot Attention for Corresponding Part Discovery. In European Conference on Computer Vision. Springer, 474-490."},{"key":"e_1_3_2_1_28_1","volume-title":"Yarn: Efficient context window extension of large language models. arXiv preprint arXiv:2309.00071","author":"Peng Bowen","year":"2023","unstructured":"Bowen Peng, Jeffrey Quesnelle, Honglu Fan, and Enrico Shippole. 2023. Yarn: Efficient context window extension of large language models. arXiv preprint arXiv:2309.00071 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9.","key":"e_1_3_2_1_30_1"},{"key":"e_1_3_2_1_31_1","volume-title":"Fuzzy-trace theory: An interim synthesis. Learning and individual Differences","author":"Reyna Valerie F","year":"1995","unstructured":"Valerie F Reyna and Charles J Brainerd. 1995. Fuzzy-trace theory: An interim synthesis. Learning and individual Differences, Vol. 7, 1 (1995), 1-75."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_32_1","DOI":"10.1109\/CVPR52688.2022.01042"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_33_1","DOI":"10.1145\/3503161.3548028"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_34_1","DOI":"10.1609\/aaai.v38i5.28298"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_35_1","DOI":"10.1609\/aaai.v38i5.28298"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_36_1","DOI":"10.1109\/CVPR52733.2024.01621"},{"key":"e_1_3_2_1_37_1","volume-title":"Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al.","author":"Team Gemini","year":"2024","unstructured":"Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al., 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_38_1","DOI":"10.1109\/CVPR52688.2022.00715"},{"unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024a. Qwen2-vl: Enhancing vision-language model's perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024).","key":"e_1_3_2_1_39_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_40_1","DOI":"10.1145\/3664647.3681553"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_41_1","DOI":"10.1145\/3503161.3548057"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_42_1","DOI":"10.1109\/CVPR52688.2022.00471"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_43_1","DOI":"10.1109\/TIP.2023.3327924"},{"unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei et al. 2024. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115 (2024).","key":"e_1_3_2_1_44_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_45_1","DOI":"10.1145\/3581783.3611709"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_46_1","DOI":"10.1145\/3474085.3475369"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_47_1","DOI":"10.1145\/3474085.3475369"}],"event":{"sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"acronym":"MM '25","name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754583","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:13:07Z","timestamp":1765339987000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754583"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":47,"alternative-id":["10.1145\/3746027.3754583","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754583","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}