{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:01:00Z","timestamp":1765310460059,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 62306320, 61976217"],"award-info":[{"award-number":["No. 62306320, 61976217"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Project Program of the State Key Laboratory of CAD&CG","award":["No. A2424"],"award-info":[{"award-number":["No. A2424"]}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["No. BK20231063"],"award-info":[{"award-number":["No. BK20231063"]}],"id":[{"id":"10.13039\/501100004608","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\/3746027.3755157","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"3702-3711","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Seeing the Undefined: Chain-of-Action for Generative Semantic Labels"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3836-6487","authenticated-orcid":false,"given":"Meng","family":"Wei","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology \/ School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, China and Mine Digitization Engineering Research Center of the Ministry of Education, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3364-8703","authenticated-orcid":false,"given":"Zhongnian","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology \/ School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, China and Mine Digitization Engineering Research Center of the Ministry of Education, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8007-5583","authenticated-orcid":false,"given":"Peng","family":"Ying","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology \/ School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, China and Mine Digitization Engineering Research Center of the Ministry of Education, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6973-799X","authenticated-orcid":false,"given":"Xinzheng","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology \/ School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, China, The State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China, and Mine Digitization Engineering Research Center of the Ministry of Education, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac Jean-Baptiste","year":"2022","unstructured":"Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in Neural Information Processing Systems 35 (2022), 23716--23736.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"volume-title":"Proceedings of Annual Conference on Neural Information Processing Systems.","author":"Bar Amir","key":"e_1_3_2_1_3_1","unstructured":"Amir Bar, Yossi Gandelsman, Trevor Darrell, Amir Globerson, and Alexei A. Efros. 2022. Visual Prompting via Image Inpainting. In Proceedings of Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29720"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of Annual Conference on Neural Information Processing Systems.","author":"Brown Tom B.","year":"2020","unstructured":"Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Proceedings of Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of Annual Conference on Neural Information Processing Systems.","author":"Conti Alessandro","year":"2023","unstructured":"Alessandro Conti, Enrico Fini, Massimiliano Mancini, Paolo Rota, Yiming Wang, and Elisa Ricci. 2023. Vocabulary-free Image Classification. In Proceedings of Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_8_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven C. H. 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 C. H. Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. In Proceedings of Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of International Conference on Machine Learning. 8469--8488","author":"Driess Danny","year":"2023","unstructured":"Danny Driess, Fei Xia, Mehdi S. M. Sajjadi, Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, Wenlong Huang, Yevgen Chebotar, Pierre Sermanet, Daniel Duckworth, Sergey Levine, Vincent Vanhoucke, Karol Hausman, Marc Toussaint, Klaus Greff, Andy Zeng, Igor Mordatch, and Pete Florence. 2023. PaLM-E: An Embodied Multimodal Language Model. In Proceedings of International Conference on Machine Learning. 8469--8488."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"e_1_3_2_1_11_1","unstructured":"M Everingham L Van Gool CKI Williams J Winn and A Zisserman. 2012. The PASCAL visual object classes challenge 2012 (VOC2012) results. 2012 http:\/\/www. pascal-network.org\/challenges. In VOC\/voc2012\/workshop\/index. html."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29760"},{"key":"e_1_3_2_1_13_1","first-page":"6704","article-title":"Cyclip: Cyclic contrastive language-image pretraining","volume":"35","author":"Goel Shashank","year":"2022","unstructured":"Shashank Goel, Hritik Bansal, Sumit Bhatia, Ryan Rossi, Vishwa Vinay, and Aditya Grover. 2022. Cyclip: Cyclic contrastive language-image pretraining. Advances in Neural Information Processing Systems 35 (2022), 6704--6719.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"volume-title":"OUTFOX: LLMGenerated Essay Detection Through In-Context Learning with Adversarially Generated Examples. In Proceedings of the AAAI Conference on Artificial Intelligence. 21258--21266","author":"Koike Ryuto","key":"e_1_3_2_1_15_1","unstructured":"Ryuto Koike, Masahiro Kaneko, and Naoaki Okazaki. [n.d.]. OUTFOX: LLMGenerated Essay Detection Through In-Context Learning with Adversarially Generated Examples. In Proceedings of the AAAI Conference on Artificial Intelligence. 21258--21266."},{"key":"e_1_3_2_1_16_1","unstructured":"Bin Lei Chunhua Liao Caiwen Ding et al. 2023. Boosting logical reasoning in large language models through a new framework: The graph of thought. arXiv preprint arXiv:2308.08614 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of 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 Proceedings of International Conference on Machine Learning. PMLR, 19730--19742."},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of 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 Proceedings of International Conference on Machine Learning. PMLR, 12888--12900."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings, Part V 13","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision--ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6--12, 2014, Proceedings, Part V 13. Springer, 740--755."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_2_1_22_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_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01454"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01367"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29848"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of 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 Proceedings of International Conference on Machine Learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_27_1","unstructured":"Alec Radford JeffreyWu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_2_1_28_1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research 21, 140 (2020), 1--67.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00799-022-00329-y"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01269"},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of International Conference on Learning Representations.","author":"Tay Yi","year":"2023","unstructured":"Yi Tay, Mostafa Dehghani, Vinh Q. Tran, Xavier Garcia, Jason Wei, Xuezhi Wang, Hyung Won Chung, Dara Bahri, Tal Schuster, Huaixiu Steven Zheng, Denny Zhou, Neil Houlsby, and Donald Metzler. 2023. UL2: Unifying Language Learning Paradigms. In Proceedings of International Conference on Learning Representations."},{"key":"e_1_3_2_1_32_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_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29884"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of International Conference on Learning Representations.","author":"Schuurmans Dale","year":"2023","unstructured":"XuezhiWang, JasonWei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023. Self-Consistency Improves Chain of Thought Reasoning in Language Models. In Proceedings of International Conference on Learning Representations."},{"volume-title":"Proceedings of International Conference on Learning Representations.","author":"Wei Jason","key":"e_1_3_2_1_35_1","unstructured":"Jason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M. Dai, and Quoc V. Le. 2022. Finetuned Language Models are Zero-Shot Learners. In Proceedings of International Conference on Learning Representations."},{"key":"e_1_3_2_1_36_1","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems 35 (2022), 24824--24837.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00671"},{"key":"e_1_3_2_1_38_1","volume-title":"Tree of thoughts: Deliberate problem solving with large language models. Advances in Neural Information Processing Systems 36","author":"Yao Shunyu","year":"2024","unstructured":"Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2024. Tree of thoughts: Deliberate problem solving with large language models. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_39_1","volume-title":"Effective Graph-of-Thought Reasoning in Language Models. arXiv preprint arXiv:2305.16582","author":"Yao Yao","year":"2023","unstructured":"Yao Yao, Zuchao Li, and Hai Zhao. 2023. Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language Models. arXiv preprint arXiv:2305.16582 (2023)."},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of International Conference on Learning Representations.","author":"Zeng Aohan","year":"2023","unstructured":"Aohan Zeng, Xiao Liu, Zhengxiao Du, Zihan Wang, Hanyu Lai, Ming Ding, Zhuoyi Yang, Yifan Xu, Wendi Zheng, Xiao Xia, Weng Lam Tam, Zixuan Ma, Yufei Xue, Jidong Zhai, Wenguang Chen, Zhiyuan Liu, Peng Zhang, Yuxiao Dong, and Jie Tang. 2023. GLM-130B: An Open Bilingual Pre-trained Model. In Proceedings of International Conference on Learning Representations."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_2_1_42_1","volume-title":"Xi Victoria Lin, et al","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al. 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)."},{"key":"e_1_3_2_1_43_1","volume-title":"Recognize Anything: A Strong Image Tagging Model. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024 - Workshops","author":"Zhang Youcai","year":"2024","unstructured":"Youcai Zhang, Xinyu Huang, Jinyu Ma, Zhaoyang Li, Zhaochuan Luo, Yanchun Xie, Yuzhuo Qin, Tong Luo, Yaqian Li, Shilong Liu, Yandong Guo, and Lei Zhang. 2024. Recognize Anything: A Strong Image Tagging Model. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024 - Workshops, Seattle, WA, USA, June 17--18, 2024. 1724--1732."},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of Annual Conference on Neural Information Processing Systems.","author":"Zhang Yuanhan","year":"2023","unstructured":"Yuanhan Zhang, Kaiyang Zhou, and Ziwei Liu. 2023. What Makes Good Examples for Visual In-Context Learning?. In Proceedings of Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_45_1","volume-title":"Proceedings of International Conference on Learning Representations.","author":"Zhang Zhuosheng","year":"2023","unstructured":"Zhuosheng Zhang, Aston Zhang, Mu Li, and Alex Smola. 2023. Automatic Chain of Thought Prompting in Large Language Models. In Proceedings of International Conference on Learning Representations."},{"key":"e_1_3_2_1_46_1","volume-title":"Multimodal Chain-of-Thought Reasoning in Language Models. Trans. Mach. Learn. Res. 2024","author":"Zhang Zhuosheng","year":"2024","unstructured":"Zhuosheng Zhang, Aston Zhang, Mu Li, Hai Zhao, George Karypis, and Alex Smola. 2024. Multimodal Chain-of-Thought Reasoning in Language Models. Trans. Mach. Learn. Res. 2024 (2024)."},{"key":"e_1_3_2_1_47_1","first-page":"5168","article-title":"Ddcot: Duty-distinct chain-of-thought prompting for multimodal reasoning in language models","volume":"36","author":"Zheng Ge","year":"2023","unstructured":"Ge Zheng, Bin Yang, Jiajin Tang, Hong-Yu Zhou, and Sibei Yang. 2023. Ddcot: Duty-distinct chain-of-thought prompting for multimodal reasoning in language models. Advances in Neural Information Processing Systems 36 (2023), 5168--5191.","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"Proceedings of International Conference on Learning Representations.","author":"Zhou Denny","key":"e_1_3_2_1_48_1","unstructured":"Denny Zhou, Nathanael Sch\u00e4rli, Le Hou, JasonWei, Nathan Scales, XuezhiWang, Dale Schuurmans, Claire Cui, Olivier Bousquet, Quoc V. Le, and Ed H. Chi. 2023. Least-to-Most Prompting Enables Complex Reasoning in Large Language Models. In Proceedings of International Conference on Learning Representations."},{"key":"e_1_3_2_1_49_1","volume-title":"Proceedings of International Conference on Learning Representations.","author":"Zhu Deyao","year":"2024","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2024. MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models. In Proceedings of International Conference on Learning Representations."},{"key":"e_1_3_2_1_50_1","volume-title":"Proceedings of International Conference on Learning Representations.","author":"Zhu Deyao","year":"2024","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2024. MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models. In Proceedings of International Conference on Learning Representations."}],"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\/3746027.3755157","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:58:52Z","timestamp":1765310332000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755157"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":50,"alternative-id":["10.1145\/3746027.3755157","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755157","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"}}]}}