{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:42:44Z","timestamp":1778258564440,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":70,"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"}],"funder":[{"name":"Agency for Science, Technol- ogy and Research (A*STAR)","award":["SERC Central Research Fund (CRF)"],"award-info":[{"award-number":["SERC Central Research Fund (CRF)"]}]},{"name":"National Research Foundation, Singapore","award":["NRF-NRFF14-2022-000"],"award-info":[{"award-number":["NRF-NRFF14-2022-000"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681244","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"9455-9464","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["RCA: Region Conditioned Adaptation for Visual Abductive Reasoning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1664-8739","authenticated-orcid":false,"given":"Hao","family":"Zhang","sequence":"first","affiliation":[{"name":"Centre for Frontier AI Research, Agency for Science Technology and Research (A*STAR), Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6935-3101","authenticated-orcid":false,"given":"Yeo Keat","family":"Ee","sequence":"additional","affiliation":[{"name":"Centre for Frontier AI Research, Agency for Science Technology and Research (A*STAR), Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6920-9916","authenticated-orcid":false,"given":"Basura","family":"Fernando","sequence":"additional","affiliation":[{"name":"Centre for Frontier AI Research, Agency for Science Technology and Research (A*STAR), Singapore, Singapore"}],"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":"10.1109\/ICCV51070.2023.01984"},{"key":"e_1_3_2_1_2_1","unstructured":"Hyojin Bahng Ali Jahanian Swami Sankaranarayanan and Phillip Isola. 2022. Exploring Visual Prompts for Adapting Large-Scale Models. https:\/\/api.semanticscholar.org\/CorpusID:249375187"},{"key":"e_1_3_2_1_3_1","volume-title":"Abductive Commonsense Reasoning. In International Conference on Learning Representations.","author":"Bhagavatula Chandra","year":"2020","unstructured":"Chandra Bhagavatula, Ronan Le Bras, Chaitanya Malaviya, Keisuke Sakaguchi, Ari Holtzman, Hannah Rashkin, Doug Downey, Wen tau Yih, and Yejin Choi. 2020. Abductive Commonsense Reasoning. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_4_1","volume-title":"IEMask R-CNN: Information-Enhanced Mask R-CNN","author":"Bi Xiuli","year":"2022","unstructured":"Xiuli Bi, Jinwu Hu, Bin Xiao, Weisheng Li, and Xinbo Gao. 2022. IEMask R-CNN: Information-Enhanced Mask R-CNN. IEEE Transactions on Big Data (2022)."},{"key":"e_1_3_2_1_5_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems (2020)."},{"key":"e_1_3_2_1_6_1","volume-title":"Knowledge-routed visual question reasoning: Challenges for deep representation embedding","author":"Cao Qingxing","year":"2021","unstructured":"Qingxing Cao, Bailin Li, Xiaodan Liang, Keze Wang, and Liang Lin. 2021. Knowledge-routed visual question reasoning: Challenges for deep representation embedding. IEEE Transactions on Neural Networks and Learning Systems (TNNLS) (2021)."},{"key":"e_1_3_2_1_7_1","volume-title":"Faisal Ahmed, Zhe Gan, Yu Cheng, and Jingjing Liu.","author":"Chen Yen-Chun","year":"2020","unstructured":"Yen-Chun Chen, Linjie Li, Licheng Yu, Ahmed El Kholy, Faisal Ahmed, Zhe Gan, Yu Cheng, and Jingjing Liu. 2020. Uniter: Universal image-text representation learning. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020."},{"key":"e_1_3_2_1_8_1","volume-title":"Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning. arXiv preprint arXiv:2406.11161","author":"Cheng Zebang","year":"2024","unstructured":"Zebang Cheng, Zhi-Qi Cheng, Jun-Yan He, Jingdong Sun, Kai Wang, Yuxiang Lin, Zheng Lian, Xiaojiang Peng, and Alexander Hauptmann. 2024. Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning. arXiv preprint arXiv:2406.11161 (2024)."},{"key":"e_1_3_2_1_9_1","volume-title":"Reproducible Scaling Laws for Contrastive Language-Image Learning. In 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Cherti Mehdi","year":"2023","unstructured":"Mehdi Cherti, Romain Beaumont, Ross Wightman, Mitchell Wortsman, Gabriel Ilharco, Cade Gordon, Christoph Schuhmann, Ludwig Schmidt, and Jenia Jitsev. 2023. Reproducible Scaling Laws for Contrastive Language-Image Learning. In 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Morris R Cohen. 1933. The Collected Papers of Charles Sanders Peirce.","DOI":"10.1086\/208072"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT.","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01637"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"e_1_3_2_1_15_1","volume-title":"Attention in natural language processing","author":"Galassi Andrea","year":"2020","unstructured":"Andrea Galassi, Marco Lippi, and Paolo Torroni. 2020. Attention in natural language processing. IEEE Transactions on Neural Networks and Learning Systems (TNNLS) (2020)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_3_2_1_17_1","volume-title":"Benchmarking Micro-action Recognition: Dataset, Method, and Application","author":"Guo Dan","year":"2024","unstructured":"Dan Guo, Kun Li, Bin Hu, Yan Zhang, and Meng Wang. 2024. Benchmarking Micro-action Recognition: Dataset, Method, and Application. IEEE Transactions on Circuits and Systems for Video Technology (2024)."},{"key":"e_1_3_2_1_18_1","volume-title":"Attention in attention: Modeling context correlation for efficient video classification","author":"Hao Yanbin","year":"2022","unstructured":"Yanbin Hao, Shuo Wang, Pei Cao, Xinjian Gao, Tong Xu, Jinmeng Wu, and Xiangnan He. 2022. Attention in attention: Modeling context correlation for efficient video classification. IEEE Transactions on Circuits and Systems for Video Technology (2022)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00100"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_21_1","volume-title":"The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning. In European Conference on Computer Vision.","author":"Hessel Jack","year":"2022","unstructured":"Jack Hessel, Jena D. Hwang, Jae Sung Park, Rowan Zellers, Chandra Bhagavatula, Anna Rohrbach, Kate Saenko, and Yejin Choi. 2022. The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning. In European Conference on Computer Vision."},{"key":"e_1_3_2_1_22_1","volume-title":"International Conference on Machine Learning.","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International Conference on Machine Learning."},{"key":"e_1_3_2_1_23_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations.","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_24_1","volume-title":"SFA-Net: A selective features absorption network for object detection in rainy weather conditions","author":"Huang Shih-Chia","year":"2022","unstructured":"Shih-Chia Huang, Quoc-Viet Hoang, and Trung-Hieu Le. 2022. SFA-Net: A selective features absorption network for object detection in rainy weather conditions. IEEE Transactions on Neural Networks and Learning Systems (TNNLS) (2022)."},{"key":"e_1_3_2_1_25_1","volume-title":"International Conference on Machine Learning.","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision-language representation learning with noisy text supervision. In International Conference on Machine Learning."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"e_1_3_2_1_27_1","volume-title":"New generation deep learning for video object detection: A survey","author":"Jiao Licheng","year":"2021","unstructured":"Licheng Jiao, Ruohan Zhang, Fang Liu, Shuyuan Yang, Biao Hou, Lingling Li, and Xu Tang. 2021. New generation deep learning for video object detection: A survey. IEEE Transactions on Neural Networks and Learning Systems (TNNLS) (2021)."},{"key":"e_1_3_2_1_28_1","volume-title":"Abductive inference: Computation, philosophy, technology","author":"Josephson John R","unstructured":"John R Josephson and Susan G Josephson. 1996. Abductive inference: Computation, philosophy, technology. Cambridge University Press."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"e_1_3_2_1_30_1","volume-title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations. Int. J. Comput. Vis.","author":"Krishna Ranjay","year":"2017","unstructured":"Ranjay Krishna, Yuke Zhu, Oliver Groth, Justin Johnson, Kenji Hata, Joshua Kravitz, Stephanie Chen, Yannis Kalantidis, Li-Jia Li, David A. Shamma, Michael S. Bernstein, and Li Fei-Fei. 2017. Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations. Int. J. Comput. Vis. (2017)."},{"key":"e_1_3_2_1_31_1","volume-title":"The Power of Scale for Parameter-Efficient Prompt Tuning. In Conference on Empirical Methods in Natural Language Processing.","author":"Lester Brian","year":"2021","unstructured":"Brian Lester, Rami Al-Rfou, and Noah Constant. 2021. The Power of Scale for Parameter-Efficient Prompt Tuning. In Conference on Empirical Methods in Natural Language Processing."},{"key":"e_1_3_2_1_32_1","volume-title":"International conference on machine learning.","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 International conference on machine learning."},{"key":"e_1_3_2_1_33_1","volume-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In ICML.","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 ICML."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01512"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_36_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","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, Vol. 36 (2024)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"e_1_3_2_1_38_1","volume-title":"A survey of visual transformers","author":"Liu Yang","year":"2023","unstructured":"Yang Liu, Yao Zhang, Yixin Wang, Feng Hou, Jin Yuan, Jiang Tian, Yang Zhang, Zhongchao Shi, Jianping Fan, and Zhiqiang He. 2023. A survey of visual transformers. IEEE Transactions on Neural Networks and Learning Systems (TNNLS) (2023)."},{"key":"e_1_3_2_1_39_1","volume-title":"FedHPL: Efficient Heterogeneous Federated Learning with Prompt Tuning and Logit Distillation. arXiv preprint arXiv:2405.17267","author":"Ma Yuting","year":"2024","unstructured":"Yuting Ma, Lechao Cheng, Yaxiong Wang, Zhun Zhong, Xiaohua Xu, and Meng Wang. 2024. FedHPL: Efficient Heterogeneous Federated Learning with Prompt Tuning and Logit Distillation. arXiv preprint arXiv:2405.17267 (2024)."},{"key":"e_1_3_2_1_40_1","volume-title":"Multi-label contrastive learning for abstract visual reasoning","author":"Ma\u0142ki'nski Miko\u0142aj","year":"2022","unstructured":"Miko\u0142aj Ma\u0142ki'nski and Jacek Ma'ndziuk. 2022. Multi-label contrastive learning for abstract visual reasoning. IEEE Transactions on Neural Networks and Learning Systems (TNNLS) (2022)."},{"key":"e_1_3_2_1_41_1","volume-title":"Robust Adaptation of Foundation Models with Black-Box Visual Prompting. arXiv preprint arXiv:2407.17491","author":"Oh Changdae","year":"2024","unstructured":"Changdae Oh, Gyeongdeok Seo, Geunyoung Jung, Zhi-Qi Cheng, Hosik Choi, Jiyoung Jung, and Kyungwoo Song. 2024. Robust Adaptation of Foundation Models with Black-Box Visual Prompting. arXiv preprint arXiv:2407.17491 (2024)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979670"},{"key":"e_1_3_2_1_43_1","volume-title":"International Conference on Machine Learning.","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."},{"key":"e_1_3_2_1_44_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, Vol. 28 (2015)."},{"key":"e_1_3_2_1_45_1","volume-title":"PEFT-Ref: A Modular Reference Architecture and Typology for Parameter-Efficient Finetuning Techniques. arXiv preprint arXiv:2304.12410","author":"Sabry Mohammed","year":"2023","unstructured":"Mohammed Sabry and Anya Belz. 2023. PEFT-Ref: A Modular Reference Architecture and Typology for Parameter-Efficient Finetuning Techniques. arXiv preprint arXiv:2304.12410 (2023)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3152990"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"e_1_3_2_1_50_1","volume-title":"Prompt-Tuning Can Be Much Better Than Fine-Tuning on Cross-lingual Understanding With Multilingual Language Models. In Findings of the Association for Computational Linguistics: EMNLP","author":"Tu Lifu","year":"2022","unstructured":"Lifu Tu, Caiming Xiong, and Yingbo Zhou. 2022. Prompt-Tuning Can Be Much Better Than Fine-Tuning on Cross-lingual Understanding With Multilingual Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2022."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"e_1_3_2_1_52_1","volume-title":"Revisiting the Power of Prompt for Visual Tuning. ArXiv","author":"Wang Yuzhu","year":"2024","unstructured":"Yuzhu Wang, Lechao Cheng, Chaowei Fang, Dingwen Zhang, Manni Duan, and Meng Wang. 2024. Revisiting the Power of Prompt for Visual Tuning. ArXiv, Vol. abs\/2402.02382 (2024). https:\/\/api.semanticscholar.org\/CorpusID:267412630"},{"key":"e_1_3_2_1_53_1","volume-title":"AIM: Adapting Image Models for Efficient Video Action Recognition. In The Eleventh International Conference on Learning Representations.","author":"Yang Taojiannan","year":"2023","unstructured":"Taojiannan Yang, Yi Zhu, Yusheng Xie, Aston Zhang, Chen Chen, and Mu Li. 2023. AIM: Adapting Image Models for Efficient Video Action Recognition. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_54_1","volume-title":"Cpt: Colorful prompt tuning for pre-trained vision-language models. AI Open","author":"Yao Yuan","year":"2024","unstructured":"Yuan Yao, Ao Zhang, Zhengyan Zhang, Zhiyuan Liu, Tat-Seng Chua, and Maosong Sun. 2024. Cpt: Colorful prompt tuning for pre-trained vision-language models. AI Open (2024)."},{"key":"e_1_3_2_1_55_1","volume-title":"CoCa: Contrastive Captioners are Image-Text Foundation Models. Transactions on Machine Learning Research","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, Zirui Wang, Vijay Vasudevan, Legg Yeung, Mojtaba Seyedhosseini, and Yonghui Wu. 2022. CoCa: Contrastive Captioners are Image-Text Foundation Models. Transactions on Machine Learning Research (2022)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"e_1_3_2_1_58_1","volume-title":"Florence: A new foundation model for computer vision. arXiv preprint arXiv:2111.11432","author":"Yuan Lu","year":"2021","unstructured":"Lu Yuan, Dongdong Chen, Yi-Ling Chen, Noel Codella, Xiyang Dai, Jianfeng Gao, Houdong Hu, Xuedong Huang, Boxin Li, Chunyuan Li, et al. 2021. Florence: A new foundation model for computer vision. arXiv preprint arXiv:2111.11432 (2021)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"e_1_3_2_1_60_1","volume-title":"Jize Cao, Ali Farhadi, and Yejin Choi.","author":"Zellers Rowan","year":"2021","unstructured":"Rowan Zellers, Ximing Lu, Jack Hessel, Youngjae Yu, Jae Sung Park, Jize Cao, Ali Farhadi, and Yejin Choi. 2021. MERLOT: Multimodal Neural Script Knowledge Models. In Advances in Neural Information Processing Systems 34."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2884478"},{"key":"e_1_3_2_1_62_1","volume-title":"Xiyang Dai, Lijuan Wang, Lu Yuan, Jenq-Neng Hwang, and Jianfeng Gao.","author":"Zhang Haotian","year":"2022","unstructured":"Haotian Zhang, Pengchuan Zhang, Xiaowei Hu, Yen-Chun Chen, Liunian Harold Li, Xiyang Dai, Lijuan Wang, Lu Yuan, Jenq-Neng Hwang, and Jianfeng Gao. 2022. Glipv2: Unifying localization and vision-language understanding. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_63_1","volume-title":"Tiny-Attention Adapter: Contexts Are More Important Than the Number of Parameters. In Conference on Empirical Methods in Natural Language Processing.","author":"Zhao Hongyu","year":"2022","unstructured":"Hongyu Zhao, Hao Tan, and Hongyuan Mei. 2022. Tiny-Attention Adapter: Contexts Are More Important Than the Number of Parameters. In Conference on Empirical Methods in Natural Language Processing."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205207"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2876865"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.398"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_2_1_69_1","volume-title":"Chen Change Loy, and Ziwei Liu","author":"Zhou Kaiyang","year":"2022","unstructured":"Kaiyang Zhou, Jingkang Yang, Chen Change Loy, and Ziwei Liu. 2022. Learning to Prompt for Vision-Language Models. International Journal of Computer Vision (IJCV) (2022)."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"}],"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\/3664647.3681244","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681244","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:42Z","timestamp":1750295862000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681244"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":70,"alternative-id":["10.1145\/3664647.3681244","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681244","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"}}]}}