{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:05:33Z","timestamp":1761897933134,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Shandong Excellent Young Scientists Fund Program (Overseas)","award":["Grants 2023HWYQ-114"],"award-info":[{"award-number":["Grants 2023HWYQ-114"]}]},{"name":"National Natural Science Foundation of Shaanxi province","award":["Grants 2021KWZ-03, 2022JQ-686"],"award-info":[{"award-number":["Grants 2021KWZ-03, 2022JQ-686"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["Grants 61971356, 62002188, U19B2037, 62201467"],"award-info":[{"award-number":["Grants 61971356, 62002188, U19B2037, 62201467"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612288","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"3777-3786","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Automatic Network Architecture Search for RGB-D Semantic Segmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1387-1256","authenticated-orcid":false,"given":"Wenna","family":"Wang","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4854-8772","authenticated-orcid":false,"given":"Tao","family":"Zhuo","sequence":"additional","affiliation":[{"name":"Shandong Artificial Intelligence Institute, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7230-1476","authenticated-orcid":false,"given":"Xiuwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1361-6185","authenticated-orcid":false,"given":"Mingjun","family":"Sun","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1086-2873","authenticated-orcid":false,"given":"Hanlin","family":"Yin","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6021-8261","authenticated-orcid":false,"given":"Yinghui","family":"Xing","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2977-8057","authenticated-orcid":false,"given":"Yanning","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"DCANet: Differential Convolution Attention Network for RGB-D Semantic Segmentation. arXiv preprint arXiv:2210.06747","author":"Bai Lizhi","year":"2022","unstructured":"Lizhi Bai, Jun Yang, Chunqi Tian, Yaoru Sun, Maoyu Mao, Yanjun Xu, and Weirong Xu. 2022. DCANet: Differential Convolution Attention Network for RGB-D Semantic Segmentation. arXiv preprint arXiv:2210.06747 (2022)."},{"key":"e_1_3_2_1_2_1","volume-title":"Designing neural network architectures using reinforcement learning. arXiv preprint arXiv:1611.02167","author":"Baker Bowen","year":"2016","unstructured":"Bowen Baker, Otkrist Gupta, Nikhil Naik, and Ramesh Raskar. 2016. Designing neural network architectures using reinforcement learning. arXiv preprint arXiv:1611.02167 (2016)."},{"key":"e_1_3_2_1_3_1","volume-title":"HS3: Learning with Proper Task Complexity in Hierarchically Supervised Semantic Segmentation. arXiv preprint arXiv:2111.02333","author":"Borse Shubhankar","year":"2021","unstructured":"Shubhankar Borse, Hong Cai, Yizhe Zhang, and Fatih Porikli. 2021. HS3: Learning with Proper Task Complexity in Hierarchically Supervised Semantic Segmentation. arXiv preprint arXiv:2111.02333 (2021)."},{"volume-title":"Medical Imaging 2022: Image Processing","author":"Bosma Martijn MA","key":"e_1_3_2_1_4_1","unstructured":"Martijn MA Bosma, Arkadiy Dushatskiy, Monika Grewal, Tanja Alderliesten, and Peter Bosman. 2022. Mixed-block neural architecture search for medical image segmentation. In Medical Imaging 2022: Image Processing, Vol. 12032. SPIE, 193--199."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00700"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.12614"},{"key":"e_1_3_2_1_7_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. 2017. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049332"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_33"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/3322706.3361996"},{"key":"e_1_3_2_1_12_1","volume-title":"Multi-modal attention-based fusion model for semantic segmentation of rgb-depth images. arXiv preprint arXiv:1912.11691","author":"Fooladgar Fahimeh","year":"2019","unstructured":"Fahimeh Fooladgar and Shohreh Kasaei. 2019. Multi-modal attention-based fusion model for semantic segmentation of rgb-depth images. arXiv preprint arXiv:1912.11691 (2019)."},{"key":"e_1_3_2_1_13_1","volume-title":"CI-Net: Contextual information for joint semantic segmentation and depth estimation. arXiv preprint arXiv:2107.13800","author":"Gao Tianxiao","year":"2021","unstructured":"Tianxiao Gao, Wu Wei, Zhongbin Cai, Zhun Fan, Shane Xie, Xinmei Wang, and Qiuda Yu. 2021. CI-Net: Contextual information for joint semantic segmentation and depth estimation. arXiv preprint arXiv:2107.13800 (2021)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.01.126"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"e_1_3_2_1_17_1","volume-title":"Rednet: Residual encoder-decoder network for indoor rgb-d semantic segmentation. arXiv preprint arXiv:1806.01054","author":"Jiang Jindong","year":"2018","unstructured":"Jindong Jiang, Lunan Zheng, Fei Luo, and Zhijun Zhang. 2018. Rednet: Residual encoder-decoder network for indoor rgb-d semantic segmentation. arXiv preprint arXiv:1806.01054 (2018)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.4018\/IJVAR.307063"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00298"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00192"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00169"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00017"},{"key":"e_1_3_2_1_23_1","volume-title":"Pyramid-Context Guided Feature Fusion for RGB-D Semantic Segmentation. In 2022 IEEE International Conference on Multimedia and Expo Workshops (ICMEW). IEEE, 1--6.","author":"Liu Haoming","year":"2022","unstructured":"Haoming Liu, Li Guo, Zhongwen Zhou, and Hanyuan Zhang. 2022a. Pyramid-Context Guided Feature Fusion for RGB-D Semantic Segmentation. In 2022 IEEE International Conference on Multimedia and Expo Workshops (ICMEW). IEEE, 1--6."},{"key":"e_1_3_2_1_24_1","volume-title":"Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055","author":"Liu Hanxiao","year":"2018","unstructured":"Hanxiao Liu, Karen Simonyan, and Yiming Yang. 2018. Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3100554"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the Asian Conference on Computer Vision. 1245--1264","author":"Liu Yunlong","year":"2022","unstructured":"Yunlong Liu, Osamu Yoshie, and Hiroshi Watanabe. 2022b. Application of Multi-modal Fusion Attention Mechanism in Semantic Segmentation. In Proceedings of the Asian Conference on Computer Vision. 1245--1264."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the IEEE 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 international conference on computer vision. 4980--4989."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00713"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"e_1_3_2_1_30_1","volume-title":"Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments. In 2022 International Joint Conference on Neural Networks (IJCNN). IEEE, 1--10","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."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561675"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00146"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3211086"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413621"},{"key":"e_1_3_2_1_38_1","volume-title":"2022 NAS-based Recursive Stage Partial Network (RSPNet) for Light-Weight Semantic Segmentation. arXiv preprint arXiv:2210.00698","author":"Wang Yi-Chun","year":"2022","unstructured":"Yi-Chun Wang, Jun-Wei Hsieh, and Ming-Ching Chang. 2022 NAS-based Recursive Stage Partial Network (RSPNet) for Light-Weight Semantic Segmentation. arXiv preprint arXiv:2210.00698 (2022)."},{"key":"e_1_3_2_1_39_1","volume-title":"CROON: Automatic Multi-LiDAR Calibration and Refinement Method in Road Scene. arXiv preprint arXiv:2203.03182","author":"Wei Pengjin","year":"2022","unstructured":"Pengjin Wei, Guohang Yan, Yikang Li, Kun Fang, Wei Liu, Xinyu Cai, and Jie Yang. 2022. CROON: Automatic Multi-LiDAR Calibration and Refinement Method in Road Scene. arXiv preprint arXiv:2203.03182 (2022)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.154"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803757"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00077"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01581"},{"key":"e_1_3_2_1_44_1","volume-title":"Pc-darts: Partial channel connections for memory-efficient architecture search. arXiv preprint arXiv:1907.05737","author":"Xu Yuhui","year":"2019","unstructured":"Yuhui Xu, Lingxi Xie, Xiaopeng Zhang, Xin Chen, Guo-Jun Qi, Qi Tian, and Hongkai Xiong. 2019. Pc-darts: Partial channel connections for memory-efficient architecture search. arXiv preprint arXiv:1907.05737 (2019)."},{"key":"e_1_3_2_1_45_1","volume-title":"Pixel Difference Convolutional Network for RGB-D Semantic Segmentation. arXiv preprint arXiv:2302.11951","author":"Yang Jun","year":"2023","unstructured":"Jun Yang, Lizhi Bai, Yaoru Sun, Chunqi Tian, Maoyu Mao, and Guorun Wang. 2023. Pixel Difference Convolutional Network for RGB-D Semantic Segmentation. arXiv preprint arXiv:2302.11951 (2023)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140611"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3532342.3532352"},{"key":"e_1_3_2_1_48_1","volume-title":"Tel Aviv","author":"Ye Hanrong","year":"2022","unstructured":"Hanrong Ye and Dan Xu. 2022. Inverted pyramid multi-task transformer for dense scene understanding. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXVII. Springer, 514--530."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20872"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413977"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3066071"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01374"},{"key":"e_1_3_2_1_53_1","volume-title":"Attention-based Dual Supervised Decoder for RGBD Semantic Segmentation. arXiv preprint arXiv:2201.01427","author":"Zhang Yang","year":"2022","unstructured":"Yang Zhang, Yang Yang, Chenyun Xiong, Guodong Sun, and Yanwen Guo. 2022. Attention-based Dual Supervised Decoder for RGBD Semantic Segmentation. arXiv preprint arXiv:2201.01427 (2022)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00423"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108468"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00457"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11395-w"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612288","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:08:19Z","timestamp":1755821299000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612288"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":57,"alternative-id":["10.1145\/3581783.3612288","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612288","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}