{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:55:48Z","timestamp":1781535348973,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810791","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"577-585","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Spatial-Channel Masked Reconstruction Knowledge Distillation for Dense Prediction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1857-4832","authenticated-orcid":false,"given":"Ziniu","family":"Liu","sequence":"first","affiliation":[{"name":"Tongji University, Shanghai, China and Ant Group, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9422-5233","authenticated-orcid":false,"given":"Shuheng","family":"Zhou","sequence":"additional","affiliation":[{"name":"Ant Group, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0180-7733","authenticated-orcid":false,"given":"Jin","family":"Zeng","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5658-7811","authenticated-orcid":false,"given":"Mingqing","family":"Liu","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0573-6561","authenticated-orcid":false,"given":"Yulong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4627-9110","authenticated-orcid":false,"given":"Hao","family":"Deng","sequence":"additional","affiliation":[{"name":"Tongji Univerdity, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Guobin Chen Wongun Choi Xiang Yu Tony Han and Manmohan Chandraker. 2017. Learning efficient object detection models with knowledge distillation. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_1_3_2","unstructured":"Kai Chen Jiaqi Wang Jiangmiao Pang Yuhang Cao Yu Xiong Xiaoxiao Li Shuyang Sun Wansen Feng Ziwei Liu Jiarui Xu et\u00a0al. 2019. MMDetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1906.07155 (2019)."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_3_3_1_5_2","unstructured":"MMSegmentation Contributors. 2020. MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00775"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Jiawei Fan Chao Li Xiaolong Liu Meina Song and Anbang Yao. 2023. Augmentation-free dense contrastive knowledge distillation for efficient semantic segmentation. Advances in Neural Information Processing Systems 36 (2023) 51359\u201351370.","DOI":"10.52202\/075280-2236"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00219"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_1_11_2","unstructured":"Geoffrey Hinton Oriol Vinyals and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1503.02531 (2015)."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Tao Huang Shan You Fei Wang Chen Qian and Chang Xu. 2025. DIST+: Knowledge Distillation From a Stronger Adaptive Teacher. IEEE Transactions on Pattern Analysis and Machine Intelligence (2025).","DOI":"10.1109\/TPAMI.2025.3554235"},{"key":"e_1_3_3_1_13_2","unstructured":"Tao Huang Yuan Zhang Shan You Fei Wang Chen Qian Jian Cao and Chang Xu. 2023. Masked distillation with receptive tokens. The Eleventh International Conference on Learning Representations (2023)."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Tao Huang Yuan Zhang Mingkai Zheng Shan You Fei Wang Chen Qian and Chang Xu. 2023. Knowledge diffusion for distillation. Advances in Neural Information Processing Systems 36 (2023) 65299\u201365316.","DOI":"10.52202\/075280-2849"},{"key":"e_1_3_3_1_15_2","unstructured":"Qizhen Lan and Qing Tian. 2025. ACAM-KD: Adaptive and Cooperative Attention Masking for Knowledge Distillation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.06307 (2025)."},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00060"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Hyejin Park Keonhee Ahn Hyesong Choi and Dongbo Min. 2025. Global Structural Knowledge Distillation for Semantic Segmentation. IEEE Access (2025).","DOI":"10.1109\/ACCESS.2025.3575066"},{"key":"e_1_3_3_1_20_2","unstructured":"Jiyong Rao Brian\u00a0Nlong Zhao and Yu Wang. 2025. Probabilistic Prompt Distribution Learning for Animal Pose Estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2025)."},{"key":"e_1_3_3_1_21_2","unstructured":"Adriana Romero Nicolas Ballas Samira\u00a0Ebrahimi Kahou Antoine Chassang Carlo Gatta and Yoshua Bengio. 2014. Fitnets: Hints for thin deep nets. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1412.6550 (2014)."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00526"},{"key":"e_1_3_3_1_24_2","unstructured":"Ruoyu Sun Fuhui Tang Xiaopeng Zhang Hongkai Xiong and Qi Tian. 2020. Distilling object detectors with task adaptive regularization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2006.13108 (2020)."},{"key":"e_1_3_3_1_25_2","unstructured":"Antti Tarvainen and Harri Valpola. 2017. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01563"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00507"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_21"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01200"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191080"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00460"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_4"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00975"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Haonan Zhang Longjun Liu Yi Zhang Xinyu Lei Fei Hui and Bihan Wen. 2025. DenseKD: Dense Knowledge Distillation by Exploiting Region and Sample Importance. IEEE Transactions on Neural Networks and Learning Systems (2025).","DOI":"10.1109\/TNNLS.2025.3525737"},{"key":"e_1_3_3_1_37_2","volume-title":"International conference on learning representations","author":"Zhang Linfeng","year":"2020","unstructured":"Linfeng Zhang and Kaisheng Ma. 2020. Improve object detection with feature-based knowledge distillation: Towards accurate and efficient detectors. In International conference on learning representations."},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01508"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"e_1_3_3_1_40_2","unstructured":"Du Zhixing Rui Zhang Ming Chang Shaoli Liu Tianshi Chen Yunji Chen et\u00a0al. 2021. Distilling object detectors with feature richness. Advances in Neural Information Processing Systems 34 (2021) 5213\u20135224."}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:43:18Z","timestamp":1781534598000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810791"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":39,"alternative-id":["10.1145\/3805622.3810791","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810791","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}