{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:05:38Z","timestamp":1783530338002,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":42,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFC3300200"],"award-info":[{"award-number":["2021YFC3300200"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Joint Funds of the National Natural Science Foundation of China","award":["U2336211 and U23A20318"],"award-info":[{"award-number":["U2336211 and U23A20318"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681253","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"1943-1951","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["PrimKD: Primary Modality Guided Multimodal Fusion for RGB-D Semantic Segmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6237-7028","authenticated-orcid":false,"given":"Zhiwei","family":"Hao","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1313-4297","authenticated-orcid":false,"given":"Zhongyu","family":"Xiao","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2296-6370","authenticated-orcid":false,"given":"Yong","family":"Luo","sequence":"additional","affiliation":[{"name":"Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2981-1953","authenticated-orcid":false,"given":"Jianyuan","family":"Guo","sequence":"additional","affiliation":[{"name":"The University of Sydney, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3653-7013","authenticated-orcid":false,"given":"Jing","family":"Wang","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5659-3464","authenticated-orcid":false,"given":"Li","family":"Shen","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7532-0496","authenticated-orcid":false,"given":"Han","family":"Hu","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00700"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049332"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_33"},{"key":"e_1_3_2_2_5_1","unstructured":"Yudong Chen Sen Wang Jiajun Liu Xuwei Xu Frank de Hoog and Zi Huang. 2022. Improved Feature Distillation via Projector Ensemble. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00219"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00268"},{"key":"e_1_3_2_2_10_1","volume-title":"Vanillakd: Revisit the power of vanilla knowledge distillation from small scale to large scale. arXiv preprint arXiv:2305.15781","author":"Hao Zhiwei","year":"2023","unstructured":"Zhiwei Hao, Jianyuan Guo, Kai Han, Han Hu, Chang Xu, and Yunhe Wang. 2023. Vanillakd: Revisit the power of vanilla knowledge distillation from small scale to large scale. arXiv preprint arXiv:2305.15781 (2023)."},{"key":"e_1_3_2_2_11_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Hao Zhiwei","year":"2024","unstructured":"Zhiwei Hao, Jianyuan Guo, Kai Han, Yehui Tang, Han Hu, Yunhe Wang, and Chang Xu. 2024. One-for-all: Bridge the gap between heterogeneous architectures in knowledge distillation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_12_1","first-page":"9164","article-title":"Learning efficient vision transformers via fine-grained manifold distillation","volume":"35","author":"Hao Zhiwei","year":"2022","unstructured":"Zhiwei Hao, Jianyuan Guo, Ding Jia, Kai Han, Yehui Tang, Chao Zhang, Han Hu, and Yunhe Wang. 2022. Learning efficient vision transformers via fine-grained manifold distillation. Advances in Neural Information Processing Systems, Vol. 35 (2022), 9164--9175.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3192663"},{"key":"e_1_3_2_2_14_1","volume-title":"Masked Autoencoders Are Scalable Vision Learners. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022","author":"He Kaiming","year":"2022","unstructured":"Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Doll\u00e1r, and Ross B. Girshick. 2022. Masked Autoencoders Are Scalable Vision Learners. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18--24, 2022. IEEE, 15979--15988."},{"key":"e_1_3_2_2_15_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"e_1_3_2_2_17_1","first-page":"33716","article-title":"Knowledge distillation from a stronger teacher","volume":"35","author":"Huang Tao","year":"2022","unstructured":"Tao Huang, Shan You, Fei Wang, Chen Qian, and Chang Xu. 2022. Knowledge distillation from a stronger teacher. Advances in Neural Information Processing Systems, Vol. 35 (2022), 33716--33727.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_18_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_19_1","volume-title":"International conference on machine learning. PMLR, 3519--3529","author":"Kornblith Simon","year":"2019","unstructured":"Simon Kornblith, Mohammad Norouzi, Honglak Lee, and Geoffrey Hinton. 2019. Similarity of neural network representations revisited. In International conference on machine learning. PMLR, 3519--3529."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"e_1_3_2_2_21_1","volume-title":"Correlation Congruence for Knowledge Distillation. In International Conference on Computer Vision.","author":"Peng Baoyun","year":"2019","unstructured":"Baoyun Peng, Xiao Jin, Jiaheng Liu, Dongsheng Li, Yichao Wu, Yu Liu, Shunfeng Zhou, and Zhaoning Zhang. 2019. Correlation Congruence for Knowledge Distillation. In International Conference on Computer Vision."},{"key":"e_1_3_2_2_22_1","volume-title":"Antoine Chassang, Carlo Gatta, and Yoshua Bengio.","author":"Romero Adriana","year":"2014","unstructured":"Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2014. Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550 (2014)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein et al. 2015. Imagenet large scale visual recognition challenge. International journal of computer vision Vol. 115 (2015) 211--252.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892852"},{"key":"e_1_3_2_2_25_1","volume-title":"Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis. In IEEE International Conference on Robotics and Automation, ICRA 2021","author":"Seichter Daniel","year":"2021","unstructured":"Daniel Seichter, Mona K\u00f6hler, Benjamin Lewandowski, Tim Wengefeld, and Horst-Michael Gross. 2021. Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis. In IEEE International Conference on Robotics and Automation, ICRA 2021, Xi'an, China, May 30 - June 5, 2021. IEEE, 13525--13531."},{"key":"e_1_3_2_2_26_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_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"e_1_3_2_2_30_1","volume-title":"Deep multimodal fusion by channel exchanging. Advances in neural information processing systems","author":"Wang Yikai","year":"2020","unstructured":"Yikai Wang, Wenbing Huang, Fuchun Sun, Tingyang Xu, Yu Rong, and Junzhou Huang. 2020. Deep multimodal fusion by channel exchanging. Advances in neural information processing systems, Vol. 33 (2020), 4835--4845."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3263111"},{"key":"e_1_3_2_2_32_1","volume-title":"Transformer fusion for indoor rgb-d semantic segmentation. Available at SSRN 4251286","author":"Zhuyun Zhou Zongwei WU","year":"2022","unstructured":"Zongwei WU, Zhuyun Zhou, Guillaume Allibert, Christophe Stolz, C\u00e9dric Demonceaux, and Chao Ma. 2022. Transformer fusion for indoor rgb-d semantic segmentation. Available at SSRN 4251286 (2022)."},{"key":"e_1_3_2_2_33_1","volume-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in neural information processing systems","author":"Xie Enze","year":"2021","unstructured":"Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M Alvarez, and Ping Luo. 2021. SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in neural information processing systems, Vol. 34 (2021), 12077--12090."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_4"},{"key":"e_1_3_2_2_35_1","volume-title":"Dformer: Rethinking rgbd representation learning for semantic segmentation. arXiv preprint arXiv:2309.09668","author":"Yin Bowen","year":"2023","unstructured":"Bowen Yin, Xuying Zhang, Zhongyu Li, Li Liu, Ming-Ming Cheng, and Qibin Hou. 2023. Dformer: Rethinking rgbd representation learning for semantic segmentation. arXiv preprint arXiv:2309.09668 (2023)."},{"key":"e_1_3_2_2_36_1","volume-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928","author":"Zagoruyko Sergey","year":"2016","unstructured":"Sergey Zagoruyko and Nikos Komodakis. 2016. Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928 (2016)."},{"key":"e_1_3_2_2_37_1","volume-title":"CMX: Cross-modal fusion for RGB-X semantic segmentation with transformers","author":"Zhang Jiaming","year":"2023","unstructured":"Jiaming Zhang, Huayao Liu, Kailun Yang, Xinxin Hu, Ruiping Liu, and Rainer Stiefelhagen. 2023. CMX: Cross-modal fusion for RGB-X semantic segmentation with transformers. IEEE Transactions on Intelligent Transportation Systems (2023)."},{"key":"e_1_3_2_2_38_1","volume-title":"Delivering Arbitrary-Modal Semantic Segmentation. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023","author":"Zhang Jiaming","year":"2023","unstructured":"Jiaming Zhang, Ruiping Liu, Hao Shi, Kailun Yang, Simon Rei\u00df, Kunyu Peng, Haodong Fu, Kaiwei Wang, and Rainer Stiefelhagen. 2023. Delivering Arbitrary-Modal Semantic Segmentation. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17--24, 2023. IEEE, 1136--1147."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"e_1_3_2_2_40_1","volume-title":"Proceedings of the Asian conference on computer vision.","author":"Zhou Hao","year":"2020","unstructured":"Hao Zhou, Lu Qi, Zhaoliang Wan, Hai Huang, and Xu Yang. 2020. RGB-D co-attention network for semantic segmentation. In Proceedings of the Asian conference on computer vision."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3161852"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3174338"}],"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\/3664647.3681253","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681253","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\/3664647.3681253"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":42,"alternative-id":["10.1145\/3664647.3681253","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681253","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"}}]}}