{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:16:28Z","timestamp":1765307788064,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","funder":[{"name":"NSFC","award":["62176155"],"award-info":[{"award-number":["62176155"]}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["YG2024ZD06"],"award-info":[{"award-number":["YG2024ZD06"]}],"id":[{"id":"10.13039\/501100012226","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\/3746027.3755539","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:44:48Z","timestamp":1761371088000},"page":"6986-6995","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CLIP-MT: Multi-Modal Knowledge-Driven Adaptive Scale Feature Allocation for Multi-Task Dense Prediction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1255-4994","authenticated-orcid":false,"given":"Shalayiding","family":"Sirejiding","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2911-1244","authenticated-orcid":false,"given":"Yue","family":"Ding","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6344-3880","authenticated-orcid":false,"given":"Yuxiang","family":"Lu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9649-621X","authenticated-orcid":false,"given":"Xinyi","family":"Hou","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0531-1120","authenticated-orcid":false,"given":"Shaokai","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1973-9529","authenticated-orcid":false,"given":"Qichen","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5561-2053","authenticated-orcid":false,"given":"Chunlin","family":"Wang","sequence":"additional","affiliation":[{"name":"Chuxiong Normal University, Chuxiong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2300-6627","authenticated-orcid":false,"given":"Wenqiang","family":"Guo","sequence":"additional","affiliation":[{"name":"Xinjiang University of Finance and Economics, Urumqi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2300-3039","authenticated-orcid":false,"given":"Hongtao","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00130"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"e_1_3_2_1_3_1","volume-title":"Delving deeper into convolutional networks for learning video representations. arXiv preprint arXiv:1511.06432","author":"Ballas Nicolas","year":"2015","unstructured":"Nicolas Ballas, Li Yao, Chris Pal, and Aaron Courville. 2015. Delving deeper into convolutional networks for learning video representations. arXiv preprint arXiv:1511.06432 (2015)."},{"key":"e_1_3_2_1_4_1","volume-title":"Beit: Bert pre-training of image transformers. arXiv preprint arXiv:2106.08254","author":"Bao Hangbo","year":"2021","unstructured":"Hangbo Bao, Li Dong, Songhao Piao, and Furu Wei. 2021. Beit: Bert pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)."},{"key":"e_1_3_2_1_5_1","first-page":"32897","article-title":"Vlmo: Unified vision-language pre-training with mixture-of-modality-experts","volume":"35","author":"Bao Hangbo","year":"2022","unstructured":"Hangbo Bao, Wenhui Wang, Li Dong, Qiang Liu, Owais Khan Mohammed, Kriti Aggarwal, Subhojit Som, Songhao Piao, and Furu Wei. 2022. Vlmo: Unified vision-language pre-training with mixture-of-modality-experts. Advances in Neural Information Processing Systems, Vol. 35 (2022), 32897-32912.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01557"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3223131"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00678"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.254"},{"key":"e_1_3_2_1_10_1","volume-title":"International conference on machine learning (ICML). PMLR, 794-803","author":"Chen Zhao","year":"2018","unstructured":"Zhao Chen, Vijay Badrinarayanan, Chen-Yu Lee, and Andrew Rabinovich. 2018. Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks. In International conference on machine learning (ICML). PMLR, 794-803."},{"key":"e_1_3_2_1_11_1","unstructured":"Zi-Yi Dou Aishwarya Kamath Zhe Gan Pengchuan Zhang Jianfeng Wang Linjie Li Zicheng Liu Ce Liu Yann LeCun Nanyun Peng et al. 2022. Coarse-to-fine vision-language pre-training with fusion in the backbone. Advances in neural information processing systems Vol. 35 (2022) 32942-32956."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00332"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00562"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_15_1","volume-title":"Squeeze-and-Excitation Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Hu Jie","year":"2018","unstructured":"Jie Hu, Li Shen, and Gang Sun. 2018. Squeeze-and-Excitation Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02662"},{"key":"e_1_3_2_1_18_1","volume-title":"International conference on machine learning. PMLR, 4904-4916","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. PMLR, 4904-4916."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 7482-7491","author":"Kendall Alex","year":"2018","unstructured":"Alex Kendall, Yarin Gal, and Roberto Cipolla. 2018. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In Proceedings of the IEEE conference on computer vision and pattern recognition. 7482-7491."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00131"},{"key":"e_1_3_2_1_21_1","volume-title":"The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=TwBY17Hgiy","author":"Li Wei-Hong","year":"2024","unstructured":"Wei-Hong Li, Steven McDonagh, Ales Leonardis, and Hakan Bilen. 2024. Multi-task Learning with 3D-Aware Regularization. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=TwBY17Hgiy"},{"key":"e_1_3_2_1_22_1","volume-title":"European Conference on Computer Vision. Springer, 314-330","author":"Lin Baijiong","year":"2024","unstructured":"Baijiong Lin, Weisen Jiang, Pengguang Chen, Yu Zhang, Shu Liu, and Ying-Cong Chen. 2024. MTMamba: Enhancing multi-task dense scene understanding by mamba-based decoders. In European Conference on Computer Vision. Springer, 314-330."},{"key":"e_1_3_2_1_23_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Liu Liyang","year":"2021","unstructured":"Liyang Liu, Yi Li, Zhanghui Kuang, J Xue, Yimin Chen, Wenming Yang, Qingmin Liao, and Wayne Zhang. 2021a. Towards impartial multi-task learning. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02497"},{"key":"e_1_3_2_1_27_1","volume-title":"The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=eePww5u7J3","author":"Lu Yuxiang","year":"2025","unstructured":"Yuxiang Lu, Shengcao Cao, and Yu-Xiong Wang. 2025. Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=eePww5u7J3"},{"key":"e_1_3_2_1_28_1","volume-title":"DiTASK: Multi-Task Fine-Tuning with Diffeomorphic Transformations. arXiv preprint arXiv:2502.06029","author":"Ipsit Mantri Krishna Sri","year":"2025","unstructured":"Krishna Sri Ipsit Mantri, Carola-Bibiane Sch\u00f6nlieb, Bruno Ribeiro, Chaim Baskin, and Moshe Eliasof. 2025. DiTASK: Multi-Task Fine-Tuning with Diffeomorphic Transformations. arXiv preprint arXiv:2502.06029 (2025)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"e_1_3_2_1_30_1","volume-title":"International Conference on Machine Learning. PMLR, 26342-26362","author":"Novack Zachary","year":"2023","unstructured":"Zachary Novack, Julian McAuley, Zachary Chase Lipton, and Saurabh Garg. 2023. Chils: Zero-shot image classification with hierarchical label sets. In International Conference on Machine Learning. PMLR, 26342-26362."},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748-8763."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01187"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014822"},{"key":"e_1_3_2_1_35_1","volume-title":"Multi-task learning as multi-objective optimization. Advances in neural information processing systems","author":"Sener Ozan","year":"2018","unstructured":"Ozan Sener and Vladlen Koltun. 2018. Multi-task learning as multi-objective optimization. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_36_1","first-page":"746","volume-title":"Florence","author":"Silberman Nathan","year":"2012","unstructured":"Nathan Silberman, Derek Hoiem, Pushmeet Kohli, and Rob Fergus. 2012. Indoor segmentation and support inference from rgbd images. In Computer Vision-ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part V 12. Springer, 746-760."},{"key":"e_1_3_2_1_37_1","volume-title":"Adaptive Task-Wise Message Passing for Multi-Task Learning: A Spatial Interaction Perspective","author":"Sirejiding Shalayiding","year":"2024","unstructured":"Shalayiding Sirejiding, Bayram Bayramli, Yuxiang Lu, Suizhi Huang, Hongtao Lu, and Yue Ding. 2024a. Adaptive Task-Wise Message Passing for Multi-Task Learning: A Spatial Interaction Perspective. IEEE Transactions on Circuits and Systems for Video Technology (2024), 1-1."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681183"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00458"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01237"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01059"},{"key":"e_1_3_2_1_42_1","volume-title":"Bert De Brabandere, and Luc Van Gool","author":"Vandenhende Simon","year":"2019","unstructured":"Simon Vandenhende, Stamatios Georgoulis, Bert De Brabandere, and Luc Van Gool. 2019. Branched multi-task networks: deciding what layers to share. arXiv preprint arXiv:1904.02920 (2019)."},{"key":"e_1_3_2_1_43_1","volume-title":"Marc Proesmans, Dengxin Dai, and Luc Van Gool.","author":"Vandenhende Simon","year":"2021","unstructured":"Simon Vandenhende, Stamatios Georgoulis, Wouter Van Gansbeke, Marc Proesmans, Dengxin Dai, and Luc Van Gool. 2021. Multi-task learning for dense prediction tasks: A survey. IEEE transactions on pattern analysis and machine intelligence, Vol. 44, 7 (2021), 3614-3633."},{"key":"e_1_3_2_1_44_1","volume-title":"Mti-net: Multi-scale task interaction networks for multi-task learning. In Computer Vision-ECCV 2020: 16th European Conference","author":"Vandenhende Simon","year":"2020","unstructured":"Simon Vandenhende, Stamatios Georgoulis, and Luc Van Gool. 2020. Mti-net: Multi-scale task interaction networks for multi-task learning. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part IV 16. Springer, 527-543."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00314"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00097"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01868"},{"key":"e_1_3_2_1_48_1","volume-title":"MTSAM: Multi-Task Fine-Tuning for Segment Anything Model. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=6N4QMbeVaO","author":"Wang Xuehao","year":"2025","unstructured":"Xuehao Wang, Zhan Zhuang, Feiyang Ye, and Yu Zhang. 2025. MTSAM: Multi-Task Fine-Tuning for Segment Anything Model. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=6N4QMbeVaO"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00077"},{"key":"e_1_3_2_1_51_1","volume-title":"Multi-task learning with multi-query transformer for dense prediction","author":"Xu Yangyang","year":"2023","unstructured":"Yangyang Xu, Xiangtai Li, Haobo Yuan, Yibo Yang, and Lefei Zhang. 2023a. Multi-task learning with multi-query transformer for dense prediction. IEEE Transactions on Circuits and Systems for Video Technology (2023)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25411"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25424"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02638"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_30"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01995"},{"key":"e_1_3_2_1_57_1","unstructured":"Hanrong Ye and Dan Xu. 2023b. TaskPrompter: Spatial-Channel Multi-Task Prompting for Dense Scene Understanding. In The Eleventh International Conference on Learning Representations (ICLR). https:\/\/openreview.net\/forum?id=-CwPopPJda"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3397031"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_2_1_60_1","volume-title":"Meta-transformer: A unified framework for multimodal learning. arXiv preprint arXiv:2307.10802","author":"Zhang Yiyuan","year":"2023","unstructured":"Yiyuan Zhang, Kaixiong Gong, Kaipeng Zhang, Hongsheng Li, Yu Qiao, Wanli Ouyang, and Xiangyu Yue. 2023. Meta-transformer: A unified framework for multimodal learning. arXiv preprint arXiv:2307.10802 (2023)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00423"},{"key":"e_1_3_2_1_63_1","volume-title":"Chen Change Loy, and Bo Dai","author":"Zhou Chong","year":"2022","unstructured":"Chong Zhou, Chen Change Loy, and Bo Dai. 2022. Extract Free Dense Labels from CLIP. In Computer Vision - ECCV 2022. Springer Nature Switzerland, Cham, 696-712."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00457"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"}],"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\/3746027.3755539","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:14:49Z","timestamp":1765307689000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755539"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":65,"alternative-id":["10.1145\/3746027.3755539","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755539","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"}}]}}