{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:36:23Z","timestamp":1765308983911,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","funder":[{"name":"National Key R&D Program of China","award":["No.2022ZD0160601"],"award-info":[{"award-number":["No.2022ZD0160601"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276260"],"award-info":[{"award-number":["62276260"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation","award":["4244099"],"award-info":[{"award-number":["4244099"]}]},{"DOI":"10.13039\/501100004750","name":"Aeronautical Science Foundation of China","doi-asserted-by":"publisher","award":["2024M0710M0002"],"award-info":[{"award-number":["2024M0710M0002"]}],"id":[{"id":"10.13039\/501100004750","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755457","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:50:47Z","timestamp":1761371447000},"page":"4464-4473","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Referring Expression Instance Retrieval and A Strong End-to-End Baseline"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5667-8929","authenticated-orcid":false,"given":"Xiangzhao","family":"Hao","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1670-944X","authenticated-orcid":false,"given":"Kuan","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2282-5086","authenticated-orcid":false,"given":"Hongyu","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Traffic and Transportation, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9241-6211","authenticated-orcid":false,"given":"Haiyun","family":"Guo","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4549-6372","authenticated-orcid":false,"given":"Ning","family":"Jiang","sequence":"additional","affiliation":[{"name":"AI Research Institution, Mashang Consumer Finance Co, Ltd, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4115-3068","authenticated-orcid":false,"given":"Quan","family":"Lu","sequence":"additional","affiliation":[{"name":"AI Research Institution, Mashang Financial Institution, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4976-3095","authenticated-orcid":false,"given":"Ming","family":"Tang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9118-2780","authenticated-orcid":false,"given":"Jinqiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"OpenAI:Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya FlorenciaLeoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat Red Avila Igor Babuschkin Suchir Balaji Valerie Balcom Paul Baltescu Haiming Bao Mo Bavarian Jeff Belgum Irwan Bello Jake Berdine Gabriel Bernadett-Shapiro Christopher Berner Lenny Bogdonoff Oleg Boiko Madelaine Boyd Anna-Luisa Brakman Greg Brockman Tim Brooks Miles Brundage Kevin Button Trevor Cai Rosie Campbell Andrew Cann Brittany Carey Chelsea Carlson Rory Carmichael Brooke Chan Che Chang Fotis Chantzis Derek Chen Sully Chen Ruby Chen Jason Chen Mark Chen Ben Chess Chester Cho Casey Chu HyungWon Chung Dave Cummings and Jeremiah Currier. 2023. GPT-4 Technical Report. (Dec 2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Localization, Text Reading, and Beyond. 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. 2023. Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond. arXiv preprint arXiv:2308.12966 (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/icccs49678.2020.9276855"},{"key":"e_1_3_2_1_4_1","volume-title":"Shikra: Unleashing multimodal llm's referential dialogue magic. arXiv preprint arXiv:2306.15195","author":"Chen Keqin","year":"2023","unstructured":"Keqin Chen, Zhao Zhang, Weili Zeng, Richong Zhang, Feng Zhu, and Rui Zhao. 2023. Shikra: Unleashing multimodal llm's referential dialogue magic. arXiv preprint arXiv:2306.15195 (2023)."},{"key":"e_1_3_2_1_5_1","volume-title":"Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325","author":"Chen Xinlei","year":"2015","unstructured":"Xinlei Chen, Hao Fang, Tsung-Yi Lin, Ramakrishna Vedantam, Saurabh Gupta, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2015. Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 24185-24198","author":"Chen Zhe","year":"2024","unstructured":"Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, et al., 2024. Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 24185-24198."},{"key":"e_1_3_2_1_8_1","volume-title":"Simvg: A simple framework for visual grounding with decoupled multi-modal fusion. Advances in neural information processing systems","author":"Dai Ming","year":"2024","unstructured":"Ming Dai, Lingfeng Yang, Yihao Xu, Zhenhua Feng, and Wankou Yang. 2024. Simvg: A simple framework for visual grounding with decoupled multi-modal fusion. Advances in neural information processing systems, Vol. 37 (2024), 121670-121698."},{"key":"e_1_3_2_1_9_1","volume-title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. (Jan","author":"AI","year":"2025","unstructured":"DeepSeek-AI DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z.F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, Aixin Liu, Bing Xue, Bingxuan Wang, Bochao Wu, Bei Feng, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, Fuli Luo, Guangbo Hao, Guanting Chen, Guowei Li, H. Zhang, Han Bao, Hanwei Xu, Haocheng Wang, Honghui Ding, Huajian Xin, Huazuo Gao, Hui Qu, Hui Li, Jianzhong Guo, Jiashi Li, Jiawei Wang, Jingchang Chen, Jingyang Yuan, Junjie Qiu, Junlong Li, J.L. Cai, Jiaqi Ni, Jian Liang, Jin Chen, Kai Dong, Kai Hu, Kaige Gao, Kang Guan, Kexin Huang, Kuai Yu, Lean Wang, Lecong Zhang, Liang Zhao, Litong Wang, Liyue Zhang, Lei Xu, Leyi Xia, Mingchuan Zhang, Minghua Zhang, Minghui Tang, Meng Li, Miaojun Wang, Mingming Li, Ning Tian, Panpan Huang, Peng Zhang, Qiancheng Wang, Qinyu Chen, Qiushi Du, Ruiqi Ge, Ruisong Zhang, Ruizhe Pan, Runji Wang, R.J. Chen, R.L. Jin, Ruyi Chen, Shanghao Lu, Shangyan Zhou, Shanhuang Chen, Shengfeng Ye, Shiyu Wang, Shuiping Yu, Shunfeng Zhou, Shuting Pan, S.S. Li, Shuang Zhou, Shaoqing Wu, Shengfeng Ye, Tao Yun, Tian Pei, Tianyu Sun, T. Wang, Wangding Zeng, Wanjia Zhao, Wen Liu, Wenfeng Liang, Wenjun Gao, Wenqin Yu, Wentao Zhang, W.L. Xiao, Wei An, Xiaodong Liu, Xiaohan Wang, Xiaokang Chen, Xiaotao Nie, Xin Cheng, Xin Liu, Xin Xie, Xingchao Liu, Xinyu Yang, Xinyuan Li, Xuecheng Su, Xuheng Lin, X.Q. Li, Xiangyue Jin, Xiaojin Shen, Xiaosha Chen, Xiaowen Sun, Xiaoxiang Wang, Xinnan Song, Xinyi Zhou, Xianzu Wang, Xinxia Shan, Y.K. Li, Y.Q. Wang, Y.X. Wei, Yang Zhang, Yanhong Xu, Yao Li, Yao Zhao, Yaofeng Sun, Yaohui Wang, Yi Yu, Yichao Zhang, Yifan Shi, Yiliang Xiong, Ying He, Yishi Piao, Yisong Wang, Yixuan Tan, Yiyang Ma, Yiyuan Liu, Yongqiang Guo, Yuan Ou, Yuduan Wang, Yue Gong, Yuheng Zou, Yujia He, Yunfan Xiong, Yuxiang Luo, Yuxiang You, Yuxuan Liu, Yuyang Zhou, Y.X. Zhu, Yanhong Xu, Yanping Huang, Yaohui Li, Yi Zheng, Yuchen Zhu, Yunxian Ma, Ying Tang, Yukun Zha, Yuting Yan, Z.Z. Ren, Zehui Ren, Zhangli Sha, Zhe Fu, Zhean Xu, Zhenda Xie, Zhengyan Zhang, Zhewen Hao, Zhicheng Ma, Zhigang Yan, Zhiyu Wu, Zihui Gu, Zijia Zhu, Zijun Liu, Zilin Li, Ziwei Xie, Ziyang Song, Zizheng Pan, Zhen Huang, Zhipeng Xu, Zhongyu Zhang, and Zhen Zhang. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. (Jan 2025)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"e_1_3_2_1_11_1","volume-title":"VSE: Improving Visual-Semantic Embeddings with Hard Negatives. arXiv: Learning,arXiv: Learning (Jul","author":"Faghri Fartash","year":"2017","unstructured":"Fartash Faghri, DavidJ. Fleet, Jamie Kiros, and Sanja Fidler. 2017. VSE: Improving Visual-Semantic Embeddings with Hard Negatives. arXiv: Learning,arXiv: Learning (Jul 2017)."},{"key":"e_1_3_2_1_12_1","volume-title":"DeViSE: A Deep Visual-Semantic Embedding Model. Neural Information Processing Systems,Neural Information Processing Systems (Dec","author":"Frome Andrea","year":"2013","unstructured":"Andrea Frome, GregS. Corrado, Jon Shlens, Samy Bengio, Jeff Dean, Marc'Aurelio Ranzato, and Tomas Mikolov. 2013. DeViSE: A Deep Visual-Semantic Embedding Model. Neural Information Processing Systems,Neural Information Processing Systems (Dec 2013)."},{"key":"e_1_3_2_1_13_1","volume-title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning. Neural Information Processing Systems,Neural Information Processing Systems (Jun","author":"Gan Zhe","year":"2020","unstructured":"Zhe Gan, Yen-Chun Chen, Pingqing Fu, Chen Zhu, Yu Cheng, and Jingjing Liu. 2020. Large-Scale Adversarial Training for Vision-and-Language Representation Learning. Neural Information Processing Systems,Neural Information Processing Systems (Jun 2020)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2911066"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Andrew Howard Mark Sandler Grace Chu Liang-Chieh Chen Bo Chen Mingxing Tan Weijun Wang Yukun Zhu Ruoming Pang Vijay Vasudevan et al. 2019. Searching for mobilenetv3. In ICCV.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01278"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"e_1_3_2_1_20_1","volume-title":"International Conference on Machine Learning,International Conference on Machine Learning (Feb","author":"Kim Won-Jae","year":"2021","unstructured":"Won-Jae Kim, Bokyung Son, and Ildoo Kim. 2021. ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision. International Conference on Machine Learning,International Conference on Machine Learning (Feb 2021)."},{"key":"e_1_3_2_1_21_1","volume-title":"Semi-Supervised Classification with Graph Convolutional Networks. arXiv: Learning,arXiv: Learning (Sep","author":"Kipf Thomas","year":"2016","unstructured":"Thomas Kipf and Max Welling. 2016. Semi-Supervised Classification with Graph Convolutional Networks. arXiv: Learning,arXiv: Learning (Sep 2016)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","unstructured":"Kuang-Huei Lee Xi Chen Gang Hua Houdong Hu and Xiaodong He. 2018. Stacked Cross Attention for Image-Text Matching. 212-228. doi:10.1007\/978-3-030-01225-0_13","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_1_23_1","unstructured":"Feng Li Hao Zhang Shilong Liu Jian Guo Lionel M Ni and Lei Zhang. 2022b. DN-DETR: Accelerate detr training by introducing query denoising. In CVPR."},{"key":"e_1_3_2_1_24_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. 2022a. 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_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00475"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Liunian Harold Li Pengchuan Zhang Haotian Zhang Jianwei Yang Chunyuan Li Yiwu Zhong Lijuan Wang Lu Yuan Lei Zhang Jenq-Neng Hwang et al. 2022c. Grounded language-image pre-training. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00049-8"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350869"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"e_1_3_2_1_32_1","volume-title":"Learning (Nov","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled Weight Decay Regularization. Learning, Learning (Nov 2017)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.232"},{"key":"e_1_3_2_1_34_1","volume-title":"Learning Transferable Visual Models From Natural Language Supervision","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, JongWook Kim, Chris Hallacy, A. Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Askell Amanda, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021a. Learning Transferable Visual Models From Natural Language Supervision. Cornell University - arXiv,Cornell University - arXiv (Feb 2021)."},{"key":"e_1_3_2_1_35_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., 2021b. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748-8763."},{"key":"e_1_3_2_1_36_1","unstructured":"Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Advances in Neural Information Processing Systems (NIPS)."},{"key":"e_1_3_2_1_37_1","volume-title":"Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding. (Sep","author":"Shi Fengyuan","year":"2022","unstructured":"Fengyuan Shi, Ruopeng Gao, Weilin Huang, and Limin Wang. 2022. Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding. (Sep 2022)."},{"key":"e_1_3_2_1_38_1","volume-title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale. arXiv preprint arXiv:2303.15389","author":"Sun Quan","year":"2023","unstructured":"Quan Sun, Yuxin Fang, Ledell Wu, Xinlong Wang, and Yue Cao. 2023. EVA-CLIP: Improved Training Techniques for CLIP at Scale. arXiv preprint arXiv:2303.15389 (2023)."},{"key":"e_1_3_2_1_39_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems (NeurIPS), Vol. 30 (2017)."},{"key":"e_1_3_2_1_40_1","volume-title":"Saksham Singhal, Subhojit Som, et al.","author":"Wang Wenhui","year":"2022","unstructured":"Wenhui Wang, Hangbo Bao, Li Dong, Johan Bjorck, Zhiliang Peng, Qiang Liu, Kriti Aggarwal, Owais Khan Mohammed, Saksham Singhal, Subhojit Som, et al., 2022a. Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks. arXiv preprint arXiv:2208.10442 (2022)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/526"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00586"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"e_1_3_2_1_44_1","unstructured":"Zhiyu Wu Xiaokang Chen Zizheng Pan Xingchao Liu Wen Liu Damai Dai Huazuo Gao Yiyang Ma Chengyue Wu Bingxuan Wang Zhenda Xie Yu Wu Kai Hu Jiawei Wang Yaofeng Sun Yukun Li Yishi Piao Kang Guan Aixin Liu Xin Xie Yuxiang You Kai Dong Xingkai Yu Haowei Zhang Liang Zhao Yisong Wang and Chong Ruan. 2024. DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding. arXiv:2412.10302 [cs.CV] https:\/\/arxiv.org\/abs\/2412.10302"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"e_1_3_2_1_48_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_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"e_1_3_2_1_52_1","unstructured":"Kun Zhang Zhendong Mao Quan Wang and Yongdong Zhang. [n.d.]. Negative-Aware Attention Framework for Image-Text Matching. ([n.d.])."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"e_1_3_2_1_54_1","volume-title":"Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159","author":"Zhu Xizhou","year":"2020","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2020. Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755457","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:32:52Z","timestamp":1765308772000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755457"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":54,"alternative-id":["10.1145\/3746027.3755457","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755457","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"}}]}}