{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:23:02Z","timestamp":1771698182961,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":47,"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":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176155"],"award-info":[{"award-number":["62176155"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Munici- pal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681183","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"6103-6112","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Task-Interaction-Free Multi-Task Learning with Efficient Hierarchical Feature Representation"],"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\/0000-0002-1553-932X","authenticated-orcid":false,"given":"Bayram","family":"Bayramli","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":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5405-5096","authenticated-orcid":false,"given":"Yuwen","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0323-0464","authenticated-orcid":false,"given":"Tamam","family":"Alsarhan","sequence":"additional","affiliation":[{"name":"University of Jordan, Amman, Jordan"}],"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"}]},{"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"}]}],"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\/ICCV48922.2021.01557"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.254"},{"key":"e_1_3_2_1_3_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_4_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2021. An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_5_1","volume-title":"Christopher KI Williams, John Winn, and Andrew Zisserman.","author":"Everingham Mark","year":"2010","unstructured":"Mark Everingham, Luc Van Gool, Christopher KI Williams, John Winn, and Andrew Zisserman. 2010. The pascal visual object classes (voc) challenge. International journal of computer vision, Vol. 88 (2010), 303--338."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479231"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00332"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00847"},{"key":"e_1_3_2_1_10_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_11_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. 2021. Towards impartial multi-task learning. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611928"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3349865"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00026"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014822"},{"key":"e_1_3_2_1_18_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_19_1","volume-title":"International Conference on Machine Learning. PMLR, 30613--30632","author":"Seo Younggyo","year":"2023","unstructured":"Younggyo Seo, Junsu Kim, Stephen James, Kimin Lee, Jinwoo Shin, and Pieter Abbeel. 2023. Multi-view masked world models for visual robotic manipulation. In International Conference on Machine Learning. PMLR, 30613--30632."},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings, Part V 12","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_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3399613"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00319"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00818"},{"key":"e_1_3_2_1_24_1","volume-title":"International Conference on Machine Learning (ICML). PMLR, 10347--10357","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image transformers & distillation through attention. In International Conference on Machine Learning (ICML). PMLR, 10347--10357."},{"key":"e_1_3_2_1_25_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_26_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_27_1","volume-title":"Proceedings, Part IV 16","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_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00741"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01277"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Jingdong Wang Ke Sun Tianheng Cheng Borui Jiang Chaorui Deng Yang Zhao Dong Liu Yadong Mu Mingkui Tan Xinggang Wang et al. 2020. Deep high-resolution representation learning for visual recognition. IEEE transactions on pattern analysis and machine intelligence Vol. 43 10 (2020) 3349--3364.","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_3_2_1_32_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Xie Sirui","year":"2019","unstructured":"Sirui Xie, Hehui Zheng, Chunxiao Liu, and Liang Lin. 2019. SNAS: stochastic neural architecture search. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00077"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01871"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00983"},{"key":"e_1_3_2_1_36_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. 2023. 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_37_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25411"},{"key":"e_1_3_2_1_38_1","first-page":"4203","article-title":"Focal modulation networks","volume":"35","author":"Yang Jianwei","year":"2022","unstructured":"Jianwei Yang, Chunyuan Li, Xiyang Dai, and Jianfeng Gao. 2022. Focal modulation networks. Advances in Neural Information Processing Systems, Vol. 35 (2022), 4203--4217.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Yuqi Yang Peng-Tao Jiang Qibin Hou Hao Zhang Jinwei Chen and Bo Li. 2024. Multi-Task Dense Prediction via Mixture of Low-Rank Experts. 27927--27937.","DOI":"10.1109\/CVPR52733.2024.02638"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_30"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01995"},{"key":"e_1_3_2_1_42_1","unstructured":"Hanrong Ye and Dan Xu. 2023. 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_43_1","volume-title":"Volo: Vision outlooker for visual recognition","author":"Yuan Li","year":"2022","unstructured":"Li Yuan, Qibin Hou, Zihang Jiang, Jiashi Feng, and Shuicheng Yan. 2022. Volo: Vision outlooker for visual recognition. IEEE transactions on pattern analysis and machine intelligence, Vol. 45, 5 (2022), 6575--6586."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_15"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00423"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_25"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00457"}],"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\/3664647.3681183","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681183","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:02Z","timestamp":1750295882000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681183"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":47,"alternative-id":["10.1145\/3664647.3681183","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681183","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"}}]}}