{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T16:37:37Z","timestamp":1776357457918,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2025QC1593"],"award-info":[{"award-number":["ZR2025QC1593"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,4]]},"DOI":"10.1145\/3798065.3798088","type":"proceedings-article","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T19:30:21Z","timestamp":1775676621000},"page":"155-160","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Resolution-Aware Multimodal System Design via Multi-Level Neural Architecture Search for Real-Time 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":"Shandong University of Finance and Economics, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3954-9095","authenticated-orcid":false,"given":"Dongsheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Shandong University of Finance and Economics, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7396-1683","authenticated-orcid":false,"given":"Chuanjin","family":"Xu","sequence":"additional","affiliation":[{"name":"Shandong University of Finance and Economics, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2582-6340","authenticated-orcid":false,"given":"Yenan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Air Force Early Warning Academy, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-026-01851-x"},{"key":"e_1_3_2_1_2_1","volume-title":"Shenzhen","author":"Bae W.","year":"2019","unstructured":"W. Bae, S. Lee, Y. Lee, et al. 2019. Resource optimized neural architecture search for 3d medical image segmentation. In Medical Image Computing and Computer Assisted Intervention-MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13-17, 2019, Proceedings, Part II 22. Springer, 228\u2013236."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"N. Bentaher S. Lafraxo Y. Kabbadj et al. 2025. R2A-UNET: double attention mechanisms with residual blocks for enhanced MRI image segmentation. Multimedia Tools and Applications (2025) 1\u201331.","DOI":"10.1007\/s11042-025-20617-4"},{"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\/TIP.2021.3049332"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_33"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801872"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00756"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.optlastec.2025.114329"},{"key":"e_1_3_2_1_10_1","unstructured":"F. Fooladgar and S. Kasaei. 2019. Multi-modal attention-based fusion model for semantic segmentation of rgb-depth images. arXiv preprint arXiv:1912.11691 (2019). arXiv:1912.11691 https:\/\/arxiv.org\/abs\/1912.11691"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.107122"},{"key":"e_1_3_2_1_12_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","author":"Hazirbas C.","year":"2017","unstructured":"C. Hazirbas, L. Ma, C. Domokos, et al. 2017. Fusenet: Incorporating depth into semantic segmentation via fusion-based cnn architecture. In Computer Vision-ACCV 2016: 13th Asian Conference on Computer Vision, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers, Part 113. Springer, 213\u2013228. https:\/\/link.springer.com\/chapter\/10.1007\/978-3-319-54181-5_14"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"e_1_3_2_1_14_1","volume-title":"Rednet: Residual encoder-decoder network for indoor rgb-d semantic segmentation. arXiv preprint arXiv:1806.01054","author":"Jiang J.","year":"2018","unstructured":"J. Jiang, L. Zheng, F. Luo, et al. 2018. Rednet: Residual encoder-decoder network for indoor rgb-d semantic segmentation. arXiv preprint arXiv:1806.01054 (2018). arXiv:1806.01054 https:\/\/arxiv.org\/abs\/1806.01054"},{"key":"e_1_3_2_1_15_1","volume-title":"Shenzhen","author":"Kim S.","year":"2019","unstructured":"S. Kim, I. Kim, S. Lim, et al. 2019. Scalable neural architecture search for 3d medical image segmentation. In Medical Image Computing and Computer Assisted Intervention-MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13-17, 2019, Proceedings, Part III 22. Springer, 220\u2013228."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00426"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00017"},{"key":"e_1_3_2_1_18_1","volume-title":"Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055","author":"Liu H.","year":"2018","unstructured":"H. Liu, K. Simonyan, and Y. Yang. 2018. Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018)."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the IEEE international conference on computer vision. 4980\u20134989","author":"Park S.J.","unstructured":"S.J. Park, K. S. Hong, and S. 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\u20134989."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892852"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561675"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 567\u2013576","author":"Song S.","unstructured":"S. Song, S. P. Lichtenberg, and J. Xiao. 2015. Sun rgb-d: A rgb-d scene understanding benchmark suite. In Proceedings of the IEEE conference on computer vision and pattern recognition. 567\u2013576."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"L. Sun K. Yang X. Hu et al. 2020. Real-time fusion network for RGB-D semantic segmentation incorporating unexpected obstacle detection for road-driving images. IEEE robotics and automation letters 5 4 (2020) 5558\u20135565.","DOI":"10.1109\/LRA.2020.3007457"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs14163864"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.104962"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803146"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113885"},{"key":"e_1_3_2_1_29_1","volume-title":"Cmx: Cross-modal fusion for rgb-x semantic segmentation with transformers","author":"Zhang J.","year":"2023","unstructured":"J. Zhang, H. Liu, K. Yang, et al. 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_30_1","doi-asserted-by":"publisher","DOI":"10.3390\/s20185292"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01191"}],"event":{"name":"NOSSDAV '26: ACM Multimedia Systems Conference 2026","location":"Hong Kong Hong Kong","acronym":"NOSSDAV '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 36th Workshop on Network and Operating System Support for Digital Audio and Video"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3798065.3798088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T15:32:48Z","timestamp":1776353568000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3798065.3798088"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,4]]},"references-count":31,"alternative-id":["10.1145\/3798065.3798088","10.1145\/3798065"],"URL":"https:\/\/doi.org\/10.1145\/3798065.3798088","relation":{},"subject":[],"published":{"date-parts":[[2026,4,4]]},"assertion":[{"value":"2026-04-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}