{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:04:40Z","timestamp":1750309480810,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":34,"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\/3664647.3688989","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"11404-11406","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["The ACM Multimedia 2024 Viual Spatial Description Grand Challenge"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8714-4151","authenticated-orcid":false,"given":"Yu","family":"Zhao","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3026-6347","authenticated-orcid":false,"given":"Hao","family":"Fei","sequence":"additional","affiliation":[{"name":"Skywork AI Lab & National University of Songalpore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0513-5540","authenticated-orcid":false,"given":"Bobo","family":"Li","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6335-1340","authenticated-orcid":false,"given":"Meishan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4659-1822","authenticated-orcid":false,"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.329"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00730"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the International Conference on Machine Learning.","author":"Fei Hao","year":"2024","unstructured":"Hao Fei, Shengqiong Wu, Wei Ji, Hanwang Zhang, Meishan Zhang, Mong-Li Lee, and Wynne Hsu. 2024. Video-of-thought: Step-by-step video reasoning from perception to cognition. In Proceedings of the International Conference on Machine Learning."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the International Conference on Machine Learning. 6373--6391","author":"Fei Hao","year":"2022","unstructured":"Hao Fei, Shengqiong Wu, Yafeng Ren, and Meishan Zhang. 2022. Matching structure for dual learning. In Proceedings of the International Conference on Machine Learning. 6373--6391."},{"key":"e_1_3_2_1_7_1","volume-title":"VITRON: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing.","author":"Fei Hao","year":"2024","unstructured":"Hao Fei, Shengqiong Wu, Hanwang Zhang, Tat-Seng Chua, and Shuicheng Yan. 2024. VITRON: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing. (2024)."},{"key":"e_1_3_2_1_8_1","volume-title":"2024 d. Enhancing video-language representations with structural spatio-temporal alignment","author":"Fei Hao","year":"2024","unstructured":"Hao Fei, Shengqiong Wu, Meishan Zhang, Min Zhang, Tat-Seng Chua, and Shuicheng Yan. 2024 d. Enhancing video-language representations with structural spatio-temporal alignment. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3689171"},{"key":"e_1_3_2_1_10_1","volume-title":"Zachary Seymour, Han-Pang Chiu, Supun Samarasekera, and Rakesh Kumar.","author":"Irshad Muhammad Zubair","year":"2021","unstructured":"Muhammad Zubair Irshad, Niluthpol Chowdhury Mithun, Zachary Seymour, Han-Pang Chiu, Supun Samarasekera, and Rakesh Kumar. 2021. SASRA: Semantically-aware Spatio-temporal Reasoning Agent for Vision-and-Language Navigation in Continuous Environments. CoRR, Vol. abs\/2108.11945 (2021). showeprint[arXiv]2108.11945"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3183434"},{"key":"e_1_3_2_1_13_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 Vol. 123 (2017) 32--73.","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612053"},{"key":"e_1_3_2_1_15_1","volume-title":"Fine-grained semantically aligned vision-language pre-training. Advances in neural information processing systems","author":"Li Juncheng","year":"2022","unstructured":"Juncheng Li, Xin He, Longhui Wei, Long Qian, Linchao Zhu, Lingxi Xie, Yueting Zhuang, Qi Tian, and Siliang Tang. 2022. Fine-grained semantically aligned vision-language pre-training. Advances in neural information processing systems, Vol. 35 (2022), 7290--7303."},{"key":"e_1_3_2_1_16_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Li Juncheng","year":"2023","unstructured":"Juncheng Li, Kaihang Pan, Zhiqi Ge, Minghe Gao, Hanwang Zhang, Wei Ji, Wenqiao Zhang, Tat-Seng Chua, Siliang Tang, and Yueting Zhuang. 2023. Fine-tuning multimodal llms to follow zero-shot demonstrative instructions. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3274139"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00304"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of ACL. 311--318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a Method for Automatic Evaluation of Machine Translation. In Proceedings of ACL. 311--318."},{"key":"e_1_3_2_1_21_1","volume-title":"Momentor: Advancing video large language model with fine-grained temporal reasoning. arXiv preprint arXiv:2402.11435","author":"Qian Long","year":"2024","unstructured":"Long Qian, Juncheng Li, Yu Wu, Yaobo Ye, Hao Fei, Tat-Seng Chua, Yueting Zhuang, and Siliang Tang. 2024. Momentor: Advancing video large language model with fine-grained temporal reasoning. arXiv preprint arXiv:2402.11435 (2024)."},{"key":"e_1_3_2_1_22_1","volume-title":"Chang","author":"Raychaudhuri Sonia","year":"2021","unstructured":"Sonia Raychaudhuri, Saim Wani, Shivansh Patel, Unnat Jain, and Angel X. Chang. 2021. Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments. CoRR, Vol. abs\/2109.15207 (2021). showeprint[arXiv]2109.15207"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3047929"},{"key":"e_1_3_2_1_24_1","volume-title":"ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models. arXiv preprint arXiv:2407.21534","author":"Wu Mingrui","year":"2024","unstructured":"Mingrui Wu, Xinyue Cai, Jiayi Ji, Jiale Li, Oucheng Huang, Gen Luo, Hao Fei, Xiaoshuai Sun, and Rongrong Ji. 2024. ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models. arXiv preprint arXiv:2407.21534 (2024)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.146"},{"key":"e_1_3_2_1_26_1","volume-title":"Towards Semantic Equivalence of Tokenization in Multimodal LLM. arXiv preprint arXiv:2406.05127","author":"Wu Shengqiong","year":"2024","unstructured":"Shengqiong Wu, Hao Fei, Xiangtai Li, Jiayi Ji, Hanwang Zhang, Tat-Seng Chua, and Shuicheng Yan. 2024. Towards Semantic Equivalence of Tokenization in Multimodal LLM. arXiv preprint arXiv:2406.05127 (2024)."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the International Conference on Machine Learning.","author":"Wu Shengqiong","year":"2024","unstructured":"Shengqiong Wu, Hao Fei, Leigang Qu, Wei Ji, and Tat-Seng Chua. 2024. NExT-GPT: Any-to-Any Multimodal LLM. In Proceedings of the International Conference on Machine Learning."},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems. 79240--79259","author":"Wu Shengqiong","year":"2023","unstructured":"Shengqiong Wu, Hao Fei, Hanwang Zhang, and Tat-Seng Chua. 2023. Imagine that! abstract-to-intricate text-to-image synthesis with scene graph hallucination diffusion. In Proceedings of the 37th International Conference on Neural Information Processing Systems. 79240--79259."},{"key":"e_1_3_2_1_29_1","volume-title":"Faithful Logical Reasoning via Symbolic Chain-of-Thought. arXiv preprint arXiv:2405.18357","author":"Xu Jundong","year":"2024","unstructured":"Jundong Xu, Hao Fei, Liangming Pan, Qian Liu, Mong-Li Lee, and Wynne Hsu. 2024. Faithful Logical Reasoning via Symbolic Chain-of-Thought. arXiv preprint arXiv:2405.18357 (2024)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00214"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Zhen Zeng Zheming Zhou Zhiqiang Sui and Odest Chadwicke Jenkins. 2018. Semantic Robot Programming for Goal-Directed Manipulation in Cluttered Scenes. In ICRA. 7462--7469.","DOI":"10.1109\/ICRA.2018.8460538"},{"key":"e_1_3_2_1_32_1","volume-title":"Chen Change Loy, and Shuicheng Yan","author":"Zhang Tao","year":"2024","unstructured":"Tao Zhang, Xiangtai Li, Hao Fei, Haobo Yuan, Shengqiong Wu, Shunping Ji, Chen Change Loy, and Shuicheng Yan. 2024. Omg-llava: Bridging image-level, object-level, pixel-level reasoning and understanding. arXiv preprint arXiv:2406.19389 (2024)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.442"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.93"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3688989","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3688989","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\/3664647.3688989"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":34,"alternative-id":["10.1145\/3664647.3688989","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3688989","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"}}]}}