{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T16:59:37Z","timestamp":1791910777989,"version":"4.3.4"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","funder":[{"name":"Natural Science Foundation of China","award":["No.62306241"],"award-info":[{"award-number":["No.62306241"]}]},{"name":"Innovation Foundation for Doctor Dissertation of Northwestern Polytechnical University","award":["No.CX2025109"],"award-info":[{"award-number":["No.CX2025109"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755110","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"1308-1317","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":21,"title":["StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6444-0453","authenticated-orcid":false,"given":"Bingyu","family":"Li","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China and Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9248-2941","authenticated-orcid":false,"given":"Da","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China and Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7666-4020","authenticated-orcid":false,"given":"Zhiyuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6000-8168","authenticated-orcid":false,"given":"Junyu","family":"Gao","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0019-4197","authenticated-orcid":false,"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"e_1_3_2_1_2_1","volume-title":"Segnet: A deep convolutional encoder-decoder architecture for image segmentation","author":"Badrinarayanan Vijay","year":"2017","unstructured":"Vijay Badrinarayanan, Alex Kendall, and Roberto Cipolla. 2017. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE transactions on pattern analysis and machine intelligence, Vol. 39, 12 (2017), 2481-2495."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27852"},{"key":"e_1_3_2_1_4_1","volume-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","author":"Chen Liang-Chieh","year":"2017","unstructured":"Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L Yuille. 2017a. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence, Vol. 40, 4 (2017), 834-848."},{"key":"e_1_3_2_1_5_1","volume-title":"Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587","author":"Chen Liang-Chieh","year":"2017","unstructured":"Liang-Chieh Chen, George Papandreou, Florian Schroff, and Hartwig Adam. 2017b. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_3_2_1_7_1","volume-title":"ComKD-CLIP: Comprehensive Knowledge Distillation for Contrastive Language-Image Pre-traning Model. arXiv preprint arXiv:2408.04145","author":"Chen Yifan","year":"2024","unstructured":"Yifan Chen, Xiaozhen Qiao, Zhe Sun, and Xuelong Li. 2024. ComKD-CLIP: Comprehensive Knowledge Distillation for Contrastive Language-Image Pre-traning Model. arXiv preprint arXiv:2408.04145 (2024)."},{"key":"e_1_3_2_1_8_1","first-page":"4467","volume-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Fuqin","year":"2021","unstructured":"Fuqin Deng and et al., 2021. FEANet: Feature-enhanced attention network for RGB-thermal real-time semantic segmentation. IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2021), 4467-4473."},{"key":"e_1_3_2_1_9_1","volume-title":"Efficient multimodal semantic segmentation via dual-prompt learning. arXiv preprint arXiv:2312.00360","author":"Dong Shaohua","year":"2023","unstructured":"Shaohua Dong, Yunhe Feng, Qing Yang, Yan Huang, Dongfang Liu, and Heng Fan. 2023a. Efficient multimodal semantic segmentation via dual-prompt learning. arXiv preprint arXiv:2312.00360 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"EGFNet: Edge-aware guidance fusion network for RGB-thermal urban scene parsing","author":"Dong Shaohua","year":"2023","unstructured":"Shaohua Dong, Wujie Zhou, Caie Xu, and Weiqing Yan. 2023b. EGFNet: Edge-aware guidance fusion network for RGB-thermal urban scene parsing. IEEE Transactions on Intelligent Transportation Systems (2023)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Xiaoyu Dong and Naoto Yokoya. 2024. Understanding Dark Scenes by Contrasting Multi-Modal Observations. In WACV.","DOI":"10.1109\/WACV57701.2024.00089"},{"key":"e_1_3_2_1_12_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_13_1","volume-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. 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, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR (2021)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206396"},{"key":"e_1_3_2_1_17_1","volume-title":"Asian conference on computer vision. Springer, 213-228","author":"Hazirbas Caner","year":"2016","unstructured":"Caner Hazirbas, Lingni Ma, Csaba Domokos, and Daniel Cremers. 2016. Fusenet: Incorporating depth into semantic segmentation via fusion-based cnn architecture. In Asian conference on computer vision. Springer, 213-228."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27981"},{"key":"e_1_3_2_1_19_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"e_1_3_2_1_21_1","volume-title":"GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer. arXiv preprint arXiv:2406.01210","author":"Jia Ding","year":"2024","unstructured":"Ding Jia, Jianyuan Guo, Kai Han, Han Wu, Chao Zhang, Chang Xu, and Xinghao Chen. 2024. GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer. arXiv preprint arXiv:2406.01210 (2024)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01330"},{"key":"e_1_3_2_1_23_1","unstructured":"Md Reza Kaykobad and et al. 2023. Multimodal Transformer for Material Segmentation. arXiv e-prints (2023) arXiv-2309."},{"key":"e_1_3_2_1_24_1","volume-title":"U3M: Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation. arXiv preprint arXiv:2405.15365","author":"Li Bingyu","year":"2024","unstructured":"Bingyu Li, Da Zhang, Zhiyuan Zhao, Junyu Gao, and Xuelong Li. 2024b. U3M: Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation. arXiv preprint arXiv:2405.15365 (2024)."},{"key":"e_1_3_2_1_25_1","volume-title":"HAPNet: Toward Superior RGB-Thermal Scene Parsing via Hybrid, Asymmetric, and Progressive Heterogeneous Feature Fusion. arXiv preprint arXiv:2404.03527","author":"Li Jiahang","year":"2024","unstructured":"Jiahang Li, Peng Yun, Qijun Chen, and Rui Fan. 2024a. HAPNet: Toward Superior RGB-Thermal Scene Parsing via Hybrid, Asymmetric, and Progressive Heterogeneous Feature Fusion. arXiv preprint arXiv:2404.03527 (2024)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3272269"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01918"},{"key":"e_1_3_2_1_28_1","first-page":"5802","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Jinyuan","year":"2022","unstructured":"Jinyuan Liu and et al., 2022. TarDAL: Target-aware dual adversarial learning and a multi-scenario multi-modality benchmark to fuse infrared and visible for object detection. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022), 5802-5811."},{"key":"e_1_3_2_1_29_1","volume-title":"International Conference on Computer Vision (ICCV)","author":"Jinyuan","year":"2023","unstructured":"Jinyuan Liu and et al., 2023. SegMiF: Multi-interactive feature learning and a full-time multi-modality benchmark for image fusion and segmentation. International Conference on Computer Vision (ICCV) (2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00745"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_1_33_1","volume-title":"ShareCMP: Polarization-Aware RGB-P Semantic Segmentation. arXiv preprint arXiv:2312.03430","author":"Liu Zhuoyan","year":"2023","unstructured":"Zhuoyan Liu, Bo Wang, Lizhi Wang, Chenyu Mao, and Ye Li. 2023b. ShareCMP: Polarization-Aware RGB-P Semantic Segmentation. arXiv preprint arXiv:2312.03430 (2023)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3349072"},{"key":"e_1_3_2_1_36_1","volume-title":"Derek Hoiem and Rob Fergus","author":"Nathan Silberman Pushmeet Kohli","year":"2012","unstructured":"Pushmeet Kohli Nathan Silberman, Derek Hoiem and Rob Fergus. 2012. Indoor Segmentation and Support Inference from RGBD Images. In ECCV."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_1_38_1","first-page":"1","article-title":"Efficient multi-task rgb-d scene analysis for indoor environments. In 2022 International joint conference on neural networks (IJCNN)","author":"Seichter Daniel","year":"2022","unstructured":"Daniel Seichter, S\u00f6hnke Benedikt Fischedick, Mona K\u00f6hler, and Horst-Michael Gro\u00df. 2022. Efficient multi-task rgb-d scene analysis for indoor environments. In 2022 International joint conference on neural networks (IJCNN). IEEE, 1-10.","journal-title":"IEEE"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196831"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2904733"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.2993143"},{"key":"e_1_3_2_1_43_1","volume-title":"SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images. arXiv preprint arXiv:2403.10662","author":"Taghavi Pardis","year":"2024","unstructured":"Pardis Taghavi, Reza Langari, and Gaurav Pandey. 2024. SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images. arXiv preprint arXiv:2403.10662 (2024)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"e_1_3_2_1_45_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_1_46_1","volume-title":"U2Fusion: A unified unsupervised image fusion network","author":"Xu Han","year":"2020","unstructured":"Han Xu, Jiayi Ma, Junjun Jiang, Xiaojie Guo, and Haibin Ling. 2020. U2Fusion: A unified unsupervised image fusion network. IEEE Transactions on Pattern Analysis and Machine Intelligence (2020)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00109"},{"key":"e_1_3_2_1_48_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_1_49_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. 2023b. CMX: Cross-modal fusion for RGB-X semantic segmentation with transformers. IEEE Transactions on Intelligent Transportation Systems (2023)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00116"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00266"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"e_1_3_2_1_53_1","volume-title":"Mitigating modality discrepancies for RGB-T semantic segmentation","author":"Zhao Shuai","year":"2023","unstructured":"Shuai Zhao, Yu Liu, Qing Jiao, Qichang Zhang, and Junwei Han. 2023. Mitigating modality discrepancies for RGB-T semantic segmentation. IEEE Transactions on Neural Networks and Learning Systems (2023)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"e_1_3_2_1_55_1","volume-title":"CACFNet: Cross-modal attention cascaded fusion network for RGB-T urban scene parsing","author":"Zhou Wujie","year":"2023","unstructured":"Wujie Zhou, Shaohua Dong, Meixin Fang, and Lu Yu. 2023a. CACFNet: Cross-modal attention cascaded fusion network for RGB-T urban scene parsing. IEEE Transactions on Intelligent Vehicles (2023)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20269"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3242651"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:06:10Z","timestamp":1765310770000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755110"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":57,"alternative-id":["10.1145\/3746027.3755110","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755110","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"}}]}}