{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T15:31:04Z","timestamp":1778167864308,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3688992","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"11420-11425","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["LLaVA-VSD: Large Language-and-Vision Assistant for Visual Spatial Description"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6892-2964","authenticated-orcid":false,"given":"Yizhang","family":"Jin","sequence":"first","affiliation":[{"name":"Tencent & Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0242-6481","authenticated-orcid":false,"given":"Jian","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8891-6766","authenticated-orcid":false,"given":"Jiangning","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8629-2101","authenticated-orcid":false,"given":"Jianlong","family":"Hu","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2431-1159","authenticated-orcid":false,"given":"Zhenye","family":"Gan","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9346-1196","authenticated-orcid":false,"given":"Xin","family":"Tan","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9945-8131","authenticated-orcid":false,"given":"Yong","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6592-8411","authenticated-orcid":false,"given":"Yabiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4216-8090","authenticated-orcid":false,"given":"Chengjie","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1653-4341","authenticated-orcid":false,"given":"Lizhuang","family":"Ma","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"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","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02506"},{"key":"e_1_3_2_1_4_1","volume-title":"SpatialRGPT: Grounded Spatial Reasoning in Vision Language Model. arXiv preprint arXiv:2406.01584","author":"Cheng An-Chieh","year":"2024","unstructured":"An-Chieh Cheng, Hongxu Yin, Yang Fu, Qiushan Guo, Ruihan Yang, Jan Kautz, Xiaolong Wang, and Sifei Liu. 2024. SpatialRGPT: Grounded Spatial Reasoning in Vision Language Model. arXiv preprint arXiv:2406.01584 (2024)."},{"key":"e_1_3_2_1_5_1","volume-title":"Xing","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, Ion Stoica, and Eric P. Xing. 2023. Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality. https:\/\/lmsys.org\/blog\/2023-03--30-vicuna\/"},{"key":"e_1_3_2_1_6_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Cho Jaemin","year":"2021","unstructured":"Jaemin Cho, Jie Lei, Hao Tan, and Mohit Bansal. 2021. Unifying vision-andlanguage tasks via text generation. In International Conference on Machine Learning. PMLR, 1931--1942."},{"key":"e_1_3_2_1_7_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_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01309"},{"key":"e_1_3_2_1_9_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_10_1","unstructured":"Yizhang Jin Jian Li Yexin Liu Tianjun Gu Kai Wu Zhengkai Jiang Muyang He Bo Zhao Xin Tan Zhenye Gan et al. 2024. Efficient multimodal large language models: A survey. arXiv preprint arXiv:2405.10739 (2024)."},{"key":"e_1_3_2_1_11_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_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_2_1_13_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems 36","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024. Visual instruction tuning. Advances in neural information processing systems 36 (2024)."},{"key":"e_1_3_2_1_14_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_15_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Yonghui Wu Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_16_1","unstructured":"An Yang Baosong Yang Binyuan Hui Bo Zheng Bowen Yu Chang Zhou Chengpeng Li Chengyuan Li Dayiheng Liu Fei Huang et al. 2024. Qwen2 technical report. arXiv preprint arXiv:2407.10671 (2024)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"e_1_3_2_1_18_1","volume-title":"Generating visual spatial description via holistic 3D scene understanding. arXiv preprint arXiv:2305.11768","author":"Zhao Yu","year":"2023","unstructured":"Yu Zhao, Hao Fei, Wei Ji, Jianguo Wei, Meishan Zhang, Min Zhang, and Tat- Seng Chua. 2023. Generating visual spatial description via holistic 3D scene understanding. arXiv preprint arXiv:2305.11768 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"Visual spatial description: Controlled spatial-oriented image-to-text generation. arXiv preprint arXiv:2210.11109","author":"Zhao Yu","year":"2022","unstructured":"Yu Zhao, Jianguo Wei, Zhichao Lin, Yueheng Sun, Meishan Zhang, and Min Zhang. 2022. Visual spatial description: Controlled spatial-oriented image-to-text generation. arXiv preprint arXiv:2210.11109 (2022)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3688992","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3688992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:29Z","timestamp":1750295849000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3688992"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":19,"alternative-id":["10.1145\/3664647.3688992","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3688992","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}