{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T13:18:30Z","timestamp":1770556710482,"version":"3.49.0"},"reference-count":57,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2021,11,12]],"date-time":"2021-11-12T00:00:00Z","timestamp":1636675200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62076262, 61673402, 61273270, and 60802069"],"award-info":[{"award-number":["62076262, 61673402, 61273270, and 60802069"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"crossref","award":["2017A030311029"],"award-info":[{"award-number":["2017A030311029"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2021,11,30]]},"abstract":"<jats:p>\n            Most existing segmentation networks are built upon a \u201c\n            <jats:sans-serif>U<\/jats:sans-serif>\n            -shaped\u201d encoder\u2013decoder structure, where the multi-level features extracted by the encoder are gradually aggregated by the decoder. Although this structure has been proven to be effective in improving segmentation performance, there are two main drawbacks. On the one hand, the introduction of low-level features brings a significant increase in calculations without an obvious performance gain. On the other hand, general strategies of feature aggregation such as addition and concatenation fuse features without considering the usefulness of each feature vector, which mixes the useful information with massive noises. In this article, we abandon the traditional \u201c\n            <jats:sans-serif>U<\/jats:sans-serif>\n            -shaped\u201d architecture and propose Y-Net, a dual-branch joint network for accurate semantic segmentation. Specifically, it only aggregates the high-level features with low-resolution and utilizes the global context guidance generated by the first branch to refine the second branch. The dual branches are effectively connected through a Semantic Enhancing Module, which can be regarded as the combination of spatial attention and channel attention. We also design a novel Channel-Selective Decoder (CSD) to adaptively integrate features from different receptive fields by assigning specific channelwise weights, where the weights are input-dependent. Our Y-Net is capable of breaking through the limit of singe-branch network and attaining higher performance with less computational cost than \u201c\n            <jats:sans-serif>U<\/jats:sans-serif>\n            -shaped\u201d structure. The proposed CSD can better integrate useful information and suppress interference noises. Comprehensive experiments are carried out on three public datasets to evaluate the effectiveness of our method. Eventually, our Y-Net achieves state-of-the-art performance on PASCAL VOC 2012, PASCAL Person-Part, and ADE20K dataset without pre-training on extra datasets.\n          <\/jats:p>","DOI":"10.1145\/3460940","type":"journal-article","created":{"date-parts":[[2021,11,12]],"date-time":"2021-11-12T21:16:06Z","timestamp":1636751766000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Y-Net: Dual-branch Joint Network for Semantic Segmentation"],"prefix":"10.1145","volume":"17","author":[{"given":"Yizhen","family":"Chen","sequence":"first","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, People\u2019s Republic of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haifeng","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, People\u2019s Republic of China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,11,12]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2551698"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2777665"},{"key":"e_1_3_1_5_2","first-page":"633","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Bolei Zhou","year":"2017","unstructured":"Zhou Bolei, Zhao Hang, and Xavier Puig. 2017. Scene parsing through ade20k dataset. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 633\u2013641."},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"e_1_3_1_7_2","first-page":"1857","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Changqian Yu","year":"2018","unstructured":"Yu Changqian, Wang Jingbo, and Chao Peng. 2018. Learning a discriminative feature network for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1857\u20131866."},{"key":"e_1_3_1_8_2","unstructured":"C. Chen L. G. Papandreou and F. Schroff. 2017. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)."},{"key":"e_1_3_1_9_2","first-page":"801","volume-title":"Proceedingss of the European Conference on Computer Vision","author":"L C. Chen,","year":"2018","unstructured":"C. Chen, L. Y. Zhu, and G. Papandreou. 2018. Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedingss of the European Conference on Computer Vision. 801\u2013818."},{"key":"e_1_3_1_10_2","unstructured":"LiangChieh Chen Papandreou George and Kokkinos Iasonas. 2014. Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv preprint arXiv:1412.7062 (2014)."},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.396"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.254"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-019-10129-2"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1038\/356150a0"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298642"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2769801"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"e_1_3_1_25_2","first-page":"3146","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Jun Fu","year":"2019","unstructured":"Fu Jun, Liu Jing, and Tian Haijie. 2019. Dual attention network for scene segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3146\u20133154."},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.5555\/2986459.2986472"},{"key":"e_1_3_1_27_2","unstructured":"Hanchao Li Pengfei Xiong and Jie An. 2018. Pyramid attention network for semantic segmentation. arXiv preprint arXiv:1805.10180 (2018)."},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00060"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.347"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.549"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.348"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00271"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.162"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.189"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.89.17.8366"},{"key":"e_1_3_1_38_2","unstructured":"Rudra P. K. Poudel Ujwal Bonde and Stephan Liwicki. 2018. ContextNet: Exploring context and detail for semantic segmentation in real-time. arXiv preprint arXiv:1805.04554 (2018)."},{"key":"e_1_3_1_39_2","doi-asserted-by":"crossref","unstructured":"Huang Qin Chunyang Xia Chihao Wu Siyang Li and C. C. Jay Kuo. 2017. Semantic segmentation with reverse attention. arXiv preprint arXiv:1707.06426 (2017).","DOI":"10.5244\/C.31.18"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_1_41_2","first-page":"3431","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Shelhamer Evan","year":"2015","unstructured":"Evan Shelhamer, Jonathan Long, and Trevor Darrell. 2015. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3431\u20133440."},{"key":"e_1_3_1_42_2","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1167\/15.9.7"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00163"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2890360"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2545409"},{"key":"e_1_3_1_48_2","first-page":"648","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Xia Fangting","year":"2016","unstructured":"Fangting Xia, Peng Wang, Liang Chieh Chen, and Alan L. Yuille. 2016. Zoom better to see clearer: Huamn part segmentation with auto zoom net. In Proceedings of the European Conference on Computer Vision. 648\u2013663."},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"e_1_3_1_50_2","unstructured":"Fisher Yu and Vladlen Koltun. 2015. Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)."},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.75"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/AIM.2019.8868787"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00747"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.12.021"},{"key":"e_1_3_1_55_2","first-page":"669","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Zhang Ziyu","year":"2015","unstructured":"Ziyu Zhang, Sanja Fidler, and Raquel Urtasun. 2015. Instance-level segmentation for autonomous driving with deep densely connected MRFs. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 669\u2013677."},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.179"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3460940","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3460940","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:21Z","timestamp":1750193301000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3460940"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,12]]},"references-count":57,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,11,30]]}},"alternative-id":["10.1145\/3460940"],"URL":"https:\/\/doi.org\/10.1145\/3460940","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,12]]},"assertion":[{"value":"2020-08-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-04-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-11-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}