{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T19:08:29Z","timestamp":1762110509471,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":44,"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":["U23A20386, 62276045, 62293540, 62293542"],"award-info":[{"award-number":["U23A20386, 62276045, 62293540, 62293542"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Dalian Science and Technology Talent Innovation Support Plan","award":["2022RY17, 2023JJ11CG001"],"award-info":[{"award-number":["2022RY17, 2023JJ11CG001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681698","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"1915-1923","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["MaskMentor: Unlocking the Potential of Masked Self-Teaching for Missing Modality RGB-D Semantic Segmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0773-5106","authenticated-orcid":false,"given":"Zhida","family":"Zhao","sequence":"first","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5365-8198","authenticated-orcid":false,"given":"Jia","family":"Li","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2538-8358","authenticated-orcid":false,"given":"Lijun","family":"Wang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1911-2526","authenticated-orcid":false,"given":"Yifan","family":"Wang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-9758","authenticated-orcid":false,"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders. In European Conference on Computer Vision","volume":"13697","author":"Bachmann Roman","year":"2022","unstructured":"Roman Bachmann, David Mizrahi, Andrei Atanov, and Amir Zamir. 2022. MultiMAE: Multi-modal Multi-task Masked Autoencoders. In European Conference on Computer Vision, Vol. 13697. 348--367."},{"key":"e_1_3_2_1_2_1","volume-title":"Multimodal Machine Learning: A Survey and Taxonomy","author":"Baltrusaitis Tadas","year":"2019","unstructured":"Tadas Baltrusaitis, Chaitanya Ahuja, and Louis-Philippe Morency. 2019. Multimodal Machine Learning: A Survey and Taxonomy. IEEE transactions on pattern analysis and machine intelligence, Vol. 41, 2 (2019), 423--443."},{"key":"e_1_3_2_1_3_1","volume-title":"BEiT: BERT Pre-Training of Image Transformers. In The International Conference on Learning Representations.","author":"Bao Hangbo","year":"2022","unstructured":"Hangbo Bao, Li Dong, Songhao Piao, and Furu Wei. 2022. BEiT: BERT Pre-Training of Image Transformers. In The International Conference on Learning Representations."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00700"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049332"},{"key":"e_1_3_2_1_7_1","volume-title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. In European Conference on Computer Vision. 833--851","author":"Chen Liang-Chieh","year":"2018","unstructured":"Liang-Chieh Chen, Yukun Zhu, George Papandreou, Florian Schroff, and Hartwig Adam. 2018. Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. In European Conference on Computer Vision. 833--851."},{"key":"e_1_3_2_1_8_1","volume-title":"Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation. In European Conference on Computer Vision. 561--577","author":"Chen Xiaokang","year":"2020","unstructured":"Xiaokang Chen, Kwan-Yee Lin, Jingbo Wang, Wayne Wu, Chen Qian, Hongsheng Li, and Gang Zeng. 2020. Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation. In European Conference on Computer Vision. 561--577."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"e_1_3_2_1_10_1","volume-title":"The International Conference on Learning Representations.","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, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In The International Conference on Learning Representations."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 16081--16091","author":"Girdhar Rohit","key":"e_1_3_2_1_12_1","unstructured":"Rohit Girdhar, Mannat Singh, Nikhila Ravi, Laurens van der Maaten, Armand Joulin, and Ishan Misra. 2022. Omnivore: A Single Model for Many Visual Modalities. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 16081--16091."},{"key":"e_1_3_2_1_13_1","first-page":"1140","article-title":"Segnext: Rethinking convolutional attention design for semantic segmentation","volume":"35","author":"Guo Meng-Hao","year":"2022","unstructured":"Meng-Hao Guo, Cheng-Ze Lu, Qibin Hou, Zhengning Liu, Ming-Ming Cheng, and Shi-Min Hu. 2022. Segnext: Rethinking convolutional attention design for semantic segmentation. In Advances in Neural Information Processing Systems, Vol. 35. 1140--1156.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_14_1","volume-title":"Fusenet: Incorporating depth into semantic segmentation via fusion-based cnn architecture. In Computer Vision--ACCV 2016: 13th Asian Conference on Computer Vision. 213--228.","author":"Hazirbas Caner","year":"2017","unstructured":"Caner Hazirbas, Lingni Ma, Csaba Domokos, and Daniel Cremers. 2017. Fusenet: Incorporating depth into semantic segmentation via fusion-based cnn architecture. In Computer Vision--ACCV 2016: 13th Asian Conference on Computer Vision. 213--228."},{"volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 15979--15988","author":"He Kaiming","key":"e_1_3_2_1_15_1","unstructured":"Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Doll\u00e1r, and Ross B. Girshick. 2022. Masked Autoencoders Are Scalable Vision Learners. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 15979--15988."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00201"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013779"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01052"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01435"},{"key":"e_1_3_2_1_20_1","volume-title":"RefineNet: Multi-Path Refinement Networks for Dense Prediction","author":"Lin Guosheng","year":"2020","unstructured":"Guosheng Lin, Fayao Liu, Anton Milan, Chunhua Shen, and Ian Reid. 2020. RefineNet: Multi-Path Refinement Networks for Dense Prediction. IEEE transactions on pattern analysis and machine intelligence, Vol. 42, 5 (2020), 1228--1242."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_1_22_1","volume-title":"Decoupled Weight Decay Regularization. In The International Conference on Learning Representations.","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In The International Conference on Learning Representations."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01764"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00106"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision. 4980--4989","author":"Park Seong-Jin","year":"2017","unstructured":"Seong-Jin Park, Ki-Sang Hong, and Seungyong Lee. 2017. Rdfnet: Rgb-d multi-level residual feature fusion for indoor semantic segmentation. In Proceedings of the IEEE\/CVF international conference on computer vision. 4980--4989."},{"key":"e_1_3_2_1_27_1","volume-title":"Beit v2: Masked image modeling with vector-quantized visual tokenizers. arXiv preprint","author":"Peng Zhiliang","year":"2022","unstructured":"Zhiliang Peng, Li Dong, Hangbo Bao, Qixiang Ye, and Furu Wei. 2022. Beit v2: Masked image modeling with vector-quantized visual tokenizers. arXiv preprint (2022)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01140"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01188-y"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"e_1_3_2_1_35_1","first-page":"4835","article-title":"Deep Multimodal Fusion by Channel Exchanging","volume":"33","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. In Advances in Neural Information Processing Systems, Vol. 33. 4835--4845.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413621"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00325"},{"key":"e_1_3_2_1_38_1","unstructured":"Enze Xie Wenhai Wang Zhiding Yu Anima Anandkumar Jos\u00e9 M. \u00c1lvarez and Ping Luo. 2021. SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers. In Advances in Neural Information Processing Systems. 12077--12090."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01675"},{"key":"e_1_3_2_1_40_1","volume-title":"DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation. In The International Conference on Learning Representations.","author":"Yin Bowen","year":"2024","unstructured":"Bowen Yin, Xuying Zhang, Zhongyu Li, Li Liu, Ming-Ming Cheng, and Qibin Hou. 2024. DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation. In The International Conference on Learning Representations."},{"key":"e_1_3_2_1_41_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_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00116"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3161852"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681698","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681698","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:50Z","timestamp":1750295870000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681698"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":44,"alternative-id":["10.1145\/3664647.3681698","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681698","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"}}]}}