{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:59:50Z","timestamp":1777568390908,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","funder":[{"name":"NSF of China","award":["Grants 62222214, 62102399, U22A2028, 62341411, 62102398, 62302478, 62302482, 62302483, 62302480?62302481"],"award-info":[{"award-number":["Grants 62222214, 62102399, U22A2028, 62341411, 62102398, 62302478, 62302482, 62302483, 62302480?62302481"]}]},{"name":"Youth Innovation Promotion Association CAS"},{"name":"CAS Project for Young Scientists in Basic Research","award":["YSBR-029"],"award-info":[{"award-number":["YSBR-029"]}]},{"name":"Strategic Priority Research Program of the Chinese Academy of Sciences","award":["Grant No.XDB0660300, XDB0660301, XDB0660302"],"award-info":[{"award-number":["Grant No.XDB0660300, XDB0660301, XDB0660302"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733282","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:31:04Z","timestamp":1750876264000},"page":"889-898","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Bottom-Up and Top-Down Thoughts for Visual Intention Grounding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8273-0289","authenticated-orcid":false,"given":"Liu","family":"Kangcheng","sequence":"first","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5573-6195","authenticated-orcid":false,"given":"Xiao","family":"Junbin","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8691-8549","authenticated-orcid":false,"given":"Zhang","family":"Rui","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4490-4318","authenticated-orcid":false,"given":"Lv","family":"Hanqi","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7603-4210","authenticated-orcid":false,"given":"Du","family":"Zidong","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and Shanghai Innovation Center for Processor Technologies, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"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 versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966 1, 2","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, ShijieWang, Sinan Tan, PengWang, 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 1, 2 (2023), 3."},{"key":"e_1_3_2_1_3_1","volume-title":"Language models are few-shot learners. arXiv preprint arXiv:2005.14165","author":"Brown Tom B","year":"2020","unstructured":"Tom B Brown. 2020. Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020)."},{"key":"e_1_3_2_1_4_1","volume-title":"The evolution of multimodal large language models: A survey. arXiv:2402.12451","author":"Caffagni Davide","year":"2024","unstructured":"Davide Caffagni, Federico Cocchi, Luca Barsellotti, Nicholas Moratelli, Sara Sarto, Lorenzo Baraldi, Marcella Cornia, and Rita Cucchiara. 2024. The evolution of multimodal large language models: A survey. arXiv:2402.12451 (2024)."},{"key":"e_1_3_2_1_5_1","volume-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning. arXiv preprint arXiv:2310.09478","author":"Chen Jun","year":"2023","unstructured":"Jun Chen, Deyao Zhu, Xiaoqian Shen, Xiang Li, Zechun Liu, Pengchuan Zhang, Raghuraman Krishnamoorthi, Vikas Chandra, Yunyang Xiong, and Mohamed Elhoseiny. 2023. Minigpt-v2: large language model as a unified interface for vision-language multi-task learning. arXiv preprint arXiv:2310.09478 (2023)."},{"key":"e_1_3_2_1_6_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_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01444"},{"key":"e_1_3_2_1_8_1","volume-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See https:\/\/vicuna. lmsys. org (accessed","author":"Chiang Wei-Lin","year":"2023","unstructured":"Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E Gonzalez, et al. 2023. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See https:\/\/vicuna. lmsys. org (accessed 14 April 2023) 2, 3 (2023), 6."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00108"},{"key":"e_1_3_2_1_10_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_11_1","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_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479232"},{"key":"e_1_3_2_1_13_1","volume-title":"Joint Visual and Text Prompting for Improved Object-Centric Perception with Multimodal Large Language Models. arXiv preprint arXiv:2404.04514","author":"Jiang Songtao","year":"2024","unstructured":"Songtao Jiang, Yan Zhang, Chenyi Zhou, Yeying Jin, Yang Feng, Jian Wu, and Zuozhu Liu. 2024. Joint Visual and Text Prompting for Improved Object-Centric Perception with Multimodal Large Language Models. arXiv preprint arXiv:2404.04514 (2024)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00718"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Ranjay Krishna Yuke Zhu Oliver Groth Justin Johnson Kenji Hata Joshua Kravitz Stephanie Chen Yannis Kalantidis Li-Jia Li David A Shamma et al. 2017. Visual genome: Connecting language and vision using crowdsourced dense image annotations. International journal of computer vision 123 (2017) 32--73.","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_18_1","volume-title":"Lisa: Reasoning segmentation via large language model. In Computer Vision and Pattern Recognition (CVPR). 9579--9589.","author":"Lai Xin","year":"2024","unstructured":"Xin Lai, Zhuotao Tian, Yukang Chen, Yanwei Li, Yuhui Yuan, Shu Liu, and Jiaya Jia. 2024. Lisa: Reasoning segmentation via large language model. In Computer Vision and Pattern Recognition (CVPR). 9579--9589."},{"key":"e_1_3_2_1_19_1","first-page":"17597","article-title":"Toist: Task oriented instance segmentation transformer with noun-pronoun distillation","volume":"35","author":"Li Pengfei","year":"2022","unstructured":"Pengfei Li, Beiwen Tian, Yongliang Shi, Xiaoxue Chen, Hao Zhao, Guyue Zhou, and Ya-Qin Zhang. 2022. Toist: Task oriented instance segmentation transformer with noun-pronoun distillation. Advances in Neural Information Processing Systems 35 (2022), 17597--17611.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_20_1","volume-title":"Van Tu Vu, et al","author":"Li Zhaowei","year":"2024","unstructured":"Zhaowei Li, Qi Xu, Dong Zhang, Hang Song, Yiqing Cai, Qi Qi, Ran Zhou, Junting Pan, Zefeng Li, Van Tu Vu, et al. 2024. Groundinggpt: Language enhanced multimodal grounding model. arXiv preprint arXiv:2401.06071 (2024)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_22_1","volume-title":"Sphinx: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models. arXiv preprint arXiv:2311.07575","author":"Lin Ziyi","year":"2023","unstructured":"Ziyi Lin, Chris Liu, Renrui Zhang, Peng Gao, Longtian Qiu, Han Xiao, Han Qiu, Chen Lin, Wenqi Shao, Keqin Chen, et al. 2023. Sphinx: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models. arXiv preprint arXiv:2311.07575 (2023)."},{"key":"e_1_3_2_1_23_1","unstructured":"Shilong Liu Zhaoyang Zeng Tianhe Ren Feng Li Hao Zhang Jie Yang Qing Jiang Chunyuan Li Jianwei Yang Hang Su et al. 2023. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3199190"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_24"},{"key":"e_1_3_2_1_26_1","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray et al. 2022. Training language models to follow instructions with human feedback. Advances in neural information processing systems 35 (2022) 27730--27744."},{"key":"e_1_3_2_1_27_1","volume-title":"Kosmos-2: Grounding multimodal large language models to the world. arXiv preprint arXiv:2306.14824","author":"Peng Zhiliang","year":"2023","unstructured":"Zhiliang Peng, Wenhui Wang, Li Dong, Yaru Hao, Shaohan Huang, Shuming Ma, and Furu Wei. 2023. Kosmos-2: Grounding multimodal large language models to the world. arXiv preprint arXiv:2306.14824 (2023)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"e_1_3_2_1_29_1","volume-title":"RIO: A benchmark for reasoning intention-oriented objects in open environments. NeurIPS 36","author":"Qu Mengxue","year":"2024","unstructured":"Mengxue Qu, Yu Wu, Wu Liu, Xiaodan Liang, Jingkuan Song, Yao Zhao, and Yunchao Wei. 2024. RIO: A benchmark for reasoning intention-oriented objects in open environments. NeurIPS 36 (2024)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"e_1_3_2_1_31_1","volume-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"Ren Shaoqing","year":"2016","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2016. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE transactions on pattern analysis and machine intelligence 39, 6 (2016), 1137--1149."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"e_1_3_2_1_34_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_35_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2018.11.014"},{"key":"e_1_3_2_1_37_1","volume-title":"One-peace: Exploring one general representation model toward unlimited modalities. arXiv preprint arXiv:2305.11172","author":"Wang Peng","year":"2023","unstructured":"Peng Wang, Shijie Wang, Junyang Lin, Shuai Bai, Xiaohuan Zhou, Jingren Zhou, Xinggang Wang, and Chang Zhou. 2023. One-peace: Exploring one general representation model toward unlimited modalities. arXiv preprint arXiv:2305.11172 (2023)."},{"key":"e_1_3_2_1_38_1","volume-title":"Visionllm: Large language model is also an open-ended decoder for vision-centric tasks. Advances in Neural Information Processing Systems 36","author":"Wang Wenhai","year":"2024","unstructured":"Wenhai Wang, Zhe Chen, Xiaokang Chen, Jiannan Wu, Xizhou Zhu, Gang Zeng, Ping Luo, Tong Lu, Jie Zhou, Yu Qiao, et al. 2024. Visionllm: Large language model is also an open-ended decoder for vision-centric tasks. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_39_1","volume-title":"RelationLMM: Large Multimodal Model as Open and Versatile Visual Relationship Generalist","author":"Xie Chi","year":"2025","unstructured":"Chi Xie, Shuang Liang, Jie Li, Zhao Zhang, Feng Zhu, Rui Zhao, and Yichen Wei. 2025. RelationLMM: Large Multimodal Model as Open and Versatile Visual Relationship Generalist. IEEE Transactions on Pattern Analysis and Machine Intelligence (2025)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"e_1_3_2_1_41_1","volume-title":"Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v. arXiv preprint arXiv:2310.11441","author":"Yang Jianwei","year":"2023","unstructured":"Jianwei Yang, Hao Zhang, Feng Li, Xueyan Zou, Chunyuan Li, and Jianfeng Gao. 2023. Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v. arXiv preprint arXiv:2310.11441 (2023)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01642-4"},{"key":"e_1_3_2_1_43_1","volume-title":"Shih-Fu Chang, Zhe Gan, et al.","author":"Zhang Haotian","year":"2024","unstructured":"Haotian Zhang, Haoxuan You, Philipp Dufter, Bowen Zhang, Chen Chen, Hong-You Chen, Tsu-Jui Fu, William Yang Wang, Shih-Fu Chang, Zhe Gan, et al. 2024. Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models. arXiv preprint arXiv:2404.07973 (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"An open and comprehensive pipeline for unified object grounding and detection. arXiv preprint arXiv:2401.02361","author":"Zhao Xiangyu","year":"2024","unstructured":"Xiangyu Zhao, Yicheng Chen, Shilin Xu, Xiangtai Li, Xinjiang Wang, Yining Li, and Haian Huang. 2024. An open and comprehensive pipeline for unified object grounding and detection. arXiv preprint arXiv:2401.02361 (2024)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics. 1136--1149","author":"Zhu HaiXiang","year":"2025","unstructured":"HaiXiang Zhu, Lixian Su, ShuangMing Mao, and Jing Ye. 2025. Read Before Grounding: Scene Knowledge Visual Grounding via Multi-step Parsing. In Proceedings of the 31st International Conference on Computational Linguistics. 1136--1149."},{"key":"e_1_3_2_1_47_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)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00621"}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","location":"Chicago IL USA","acronym":"ICMR '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733282","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:03:12Z","timestamp":1755748992000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733282"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":48,"alternative-id":["10.1145\/3731715.3733282","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733282","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}