{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:00:49Z","timestamp":1775815249039,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China under Grants, China","award":["No. 62222203 and No. 62476201"],"award-info":[{"award-number":["No. 62222203 and No. 62476201"]}]},{"name":"New Cornerstone Science Foundation through the XPLORER PRIZE"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754835","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"5951-5960","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["SaP-Bot: A Multimodal Large-Language Model for End-to-End Same-Product Identification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1397-9396","authenticated-orcid":false,"given":"Yixuan","family":"Zhou","sequence":"first","affiliation":[{"name":"Alipay, Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9104-5027","authenticated-orcid":false,"given":"Yulu","family":"Tian","sequence":"additional","affiliation":[{"name":"Alipay, Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8861-9503","authenticated-orcid":false,"given":"Wenliang","family":"Zhong","sequence":"additional","affiliation":[{"name":"Alipay, Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7522-5900","authenticated-orcid":false,"given":"Xingbin","family":"Yu","sequence":"additional","affiliation":[{"name":"Alipay, Ant Group, Hangzhou, Alipay, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-2088","authenticated-orcid":false,"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5685-3123","authenticated-orcid":false,"given":"Xing","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Scicence and Technology, Tongji University, Shanghai, 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":"Cvpr 2020 aliproducts challenge: Large-scale product recognition","author":"Alibaba T","year":"2020","unstructured":"T Alibaba. [n.d.]. Cvpr 2020 aliproducts challenge: Large-scale product recognition (2020)."},{"key":"e_1_3_2_1_3_1","volume-title":"The claude 3 model family: Opus, sonnet, haiku. Claude-3 Model Card","author":"Anthropic AI","year":"2024","unstructured":"AI Anthropic. 2024. The claude 3 model family: Opus, sonnet, haiku. Claude-3 Model Card, Vol. 1 (2024), 1."},{"key":"e_1_3_2_1_4_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023a. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_5_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et al. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00524"},{"key":"e_1_3_2_1_7_1","volume-title":"Products-10k: A large-scale product recognition dataset. arXiv preprint arXiv:2008.10545","author":"Bai Yalong","year":"2020","unstructured":"Yalong Bai, Yuxiang Chen, Wei Yu, Linfang Wang, and Wei Zhang. 2020. Products-10k: A large-scale product recognition dataset. arXiv preprint arXiv:2008.10545 (2020)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680753"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543873.3584632"},{"key":"e_1_3_2_1_10_1","volume-title":"IJCAI","volume":"21","author":"Chen Delong","year":"2021","unstructured":"Delong Chen, Fan Liu, Xiaoyu Du, Ruizhuo Gao, and Feng Xu. 2021. MEP-3M: A Large-scale Multi-modal E-Commerce Products Dataset. In IJCAI, Vol. 21."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612408"},{"key":"e_1_3_2_1_12_1","unstructured":"Zhe Chen Weiyun Wang Yue Cao Yangzhou Liu Zhangwei Gao Erfei Cui Jinguo Zhu Shenglong Ye Hao Tian Zhaoyang Liu et al. 2024. Expanding performance boundaries of open-source multimodal models with model data and test-time scaling. arXiv preprint arXiv:2412.05271 (2024)."},{"key":"e_1_3_2_1_13_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi.","author":"Dai Wenliang","year":"2023","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. arXiv:2305.06500 [cs.CV] https:\/\/arxiv.org\/abs\/2305.06500"},{"key":"e_1_3_2_1_14_1","first-page":"4171","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 4171-4186."},{"key":"e_1_3_2_1_15_1","first-page":"21252","article-title":"M5product: Self-harmonized contrastive learning for e-commercial multi-modal pretraining","author":"Dong Xiao","year":"2022","unstructured":"Xiao Dong, Xunlin Zhan, Yangxin Wu, Yunchao Wei, Michael C Kampffmeyer, Xiaoyong Wei, Minlong Lu, Yaowei Wang, and Xiaodan Liang. 2022. M5product: Self-harmonized contrastive learning for e-commercial multi-modal pretraining. In CVPR. 21252-21262.","journal-title":"CVPR."},{"key":"e_1_3_2_1_16_1","first-page":"1678","article-title":"MovingFashion: a Benchmark for the Video-to-Shop Challenge","author":"Godi Marco","year":"2022","unstructured":"Marco Godi, Christian Joppi, Geri Skenderi, and Marco Cristani. 2022. MovingFashion: a Benchmark for the Video-to-Shop Challenge. In WACV. 1678-1686.","journal-title":"WACV."},{"key":"e_1_3_2_1_17_1","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Alex Vaughan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_18_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00377"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02613"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"e_1_3_2_1_23_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_1_24_1","unstructured":"Kenneth C Laudon and Carol Guercio Traver. 2020. E-commerce 2019: Business technology society. Pearson."},{"key":"e_1_3_2_1_25_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_26_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_27_1","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_28_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00952-2"},{"key":"e_1_3_2_1_29_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024b. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_31_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_32_1","unstructured":"Haoyu Lu Wen Liu Bo Zhang Bingxuan Wang Kai Dong Bo Liu Jingxiang Sun Tongzheng Ren Zhuoshu Li Hao Yang et al. 2024. Deepseek-vl: towards real-world vision-language understanding. arXiv preprint arXiv:2403.05525 (2024)."},{"key":"e_1_3_2_1_33_1","volume-title":"Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)."},{"key":"e_1_3_2_1_34_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."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591643"},{"key":"e_1_3_2_1_36_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)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463032"},{"key":"e_1_3_2_1_38_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024. 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","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_40_1","volume-title":"Ferret: Refer and ground anything anywhere at any granularity. arXiv preprint arXiv:2310.07704","author":"You Haoxuan","year":"2023","unstructured":"Haoxuan You, Haotian Zhang, Zhe Gan, Xianzhi Du, Bowen Zhang, Zirui Wang, Liangliang Cao, Shih-Fu Chang, and Yinfei Yang. 2023. Ferret: Refer and ground anything anywhere at any granularity. arXiv preprint arXiv:2310.07704 (2023)."},{"key":"e_1_3_2_1_41_1","volume-title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts. In International Conference on Machine Learning. PMLR, 25994-26009","author":"Zeng Yan","year":"2022","unstructured":"Yan Zeng, Xinsong Zhang, and Hang Li. 2022. Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts. In International Conference on Machine Learning. PMLR, 25994-26009."},{"key":"e_1_3_2_1_42_1","volume-title":"All-in-One Pre-Trained Model for Vision-Language Tasks","author":"Zeng Yan","year":"2023","unstructured":"Yan Zeng, Xinsong Zhang, Hang Li, Jiawei Wang, Jipeng Zhang, and Wangchunshu Zhou. 2023. X^2-VLM: All-in-One Pre-Trained Model for Vision-Language Tasks. IEEE transactions on pattern analysis and machine intelligence, Vol. 46, 5 (2023), 3156-3168."},{"key":"e_1_3_2_1_43_1","first-page":"11782","article-title":"Product1m: Towards weakly supervised instance-level product retrieval via cross-modal pretraining","author":"Zhan Xunlin","year":"2021","unstructured":"Xunlin Zhan, Yangxin Wu, Xiao Dong, Yunchao Wei, Minlong Lu, Yichi Zhang, Hang Xu, and Xiaodan Liang. 2021. Product1m: Towards weakly supervised instance-level product retrieval via cross-modal pretraining. In ICCV. 11782-11791.","journal-title":"ICCV."},{"key":"e_1_3_2_1_44_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Zhou Yixuan","year":"2025","unstructured":"Yixuan Zhou, Long Bai, Sijia Cai, Bing Deng, Xing Xu, and Heng Tao Shen. 2025. TAU-106K: A New Dataset for Comprehensive Understanding of Traffic Accident. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_45_1","volume-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592","author":"Zhu Deyao","year":"2023","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475648"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117128"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754835","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:41:24Z","timestamp":1765309284000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754835"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":47,"alternative-id":["10.1145\/3746027.3754835","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754835","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"}}]}}