{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:02:42Z","timestamp":1750309362909,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T00:00:00Z","timestamp":1705622400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,1,19]]},"DOI":"10.1145\/3674225.3674394","type":"proceedings-article","created":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T18:23:05Z","timestamp":1722450185000},"page":"939-943","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Semi-AVS: Segmenting the Sounding Objects via Semi-supervised Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2324-3392","authenticated-orcid":false,"given":"Chengcheng","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Anhui University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3265-823X","authenticated-orcid":false,"given":"Zhengyi","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Anhui University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1799-5443","authenticated-orcid":false,"given":"Wei","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Anhui University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,7,31]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_2_1","first-page":"403","volume-title":"17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXVII. Springer","author":"Zhou Jinxing","year":"2022","unstructured":"Jinxing Zhou, Jianyuan Wang, Jiayi Zhang, Weixuan Sun, Jing Zhang, Stan Birchfield, Dan Guo, Lingpeng Kong, Meng Wang, and Yiran Zhong, \u201cAudio-visual segmentation,\u201d in Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXVII. Springer, 2022, pp.386\u2013403."},{"key":"e_1_3_2_1_3_1","volume-title":"Audiovisual segmentation with semantics","author":"Zhou Jinxing","year":"2023","unstructured":"Jinxing Zhou, Xuyang Shen, Jianyuan Wang, Jiayi Zhang, Weixuan Sun, Jing Zhang, Stan Birchfield, Dan Guo, Lingpeng Kong, Meng Wang, , \u201cAudiovisual segmentation with semantics,\u201d arXiv preprint arXiv:2301.13190, 2023."},{"key":"e_1_3_2_1_4_1","first-page":"4277","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Yang Lihe","year":"2022","unstructured":"Lihe Yang, Wei Zhuo, Lei Qi, Yinghuan Shi, and Yang Gao, \u201cSt++: Make self-training work better for semisupervised semantic segmentation,\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4268\u20134277."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3211188"},{"key":"e_1_3_2_1_6_1","first-page":"135","volume-title":"conference on acoustics, speech and signal processing (icassp). IEEE,2017","author":"Hershey Shawn","unstructured":"Shawn Hershey, Sourish Chaudhuri, Daniel PW Ellis, Jort F Gemmeke, Aren Jansen, R Channing Moore, Manoj Plakal, Devin Platt, Rif A Saurous, Bryan Seybold, , \u201cCNN architectures for large-scale audio classification,\u201d in 2017 ieee international conference on acoustics, speech and signal processing (icassp). IEEE,2017, pp. 131\u2013135."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"e_1_3_2_1_9_1","volume-title":"Learning aligned cross-modal representations for referring image segmentation","author":"Wei Zhichao","year":"2023","unstructured":"Zhichao Wei, Xiaohao Chen, Mingqiang Chen, and Siyu Zhu, \u201cLearning aligned cross-modal representations for referring image segmentation,\u201d arXiv preprint arXiv:2301.06429, 2023."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"e_1_3_2_1_12_1","first-page":"308","volume-title":"16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XX 16","author":"Qian Rui","year":"2020","unstructured":"Rui Qian, Di Hu, Heinrich Dinkel, Mengyue Wu, Ning Xu, and Weiyao Lin, \u201cMultiple sound sources localization from coarse to fine,\u201d in Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XX 16. Springer, 2020, pp. 292\u2013308."},{"key":"e_1_3_2_1_13_1","volume-title":"Making a case for 3d convolutions for object segmentation in videos","author":"Mahadevan Sabarinath","year":"2008","unstructured":"Sabarinath Mahadevan, Ali Athar, Aljo\u02c7sa O\u02c7sep, Sebastian Hennen, Laura Leal-Taix\u00b4e, and Bastian Leibe, \u201cMaking a case for 3d convolutions for object segmentation in videos,\u201d arXiv preprint arXiv:2008.11516, 2020."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00585"},{"key":"e_1_3_2_1_15_1","volume-title":"Transformer transforms salient object detection and camouflaged object detection","author":"Mao Yuxin","year":"2021","unstructured":"Yuxin Mao, Jing Zhang, Zhexiong Wan, Yuchao Dai, Aixuan Li, Yunqiu Lv, Xinyu Tian, Deng-Ping Fan, and Nick Barnes, \u201cTransformer transforms salient object detection and camouflaged object detection,\u201d arXiv preprint arXiv:2104.10127, 2021."},{"key":"e_1_3_2_1_16_1","first-page":"15448","article-title":"Learning generative vision transformer with energybased latent space for saliency prediction","volume":"34","author":"Zhang Jing","year":"2021","unstructured":"Jing Zhang, Jianwen Xie, Nick Barnes, and Ping Li, \u201cLearning generative vision transformer with energybased latent space for saliency prediction,\u201d Advances in Neural Information Processing Systems, vol. 34, pp.15448\u201315463, 2021.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_17_1","volume-title":"Av-sam: Segment anything model meets audio-visual localization and segmentation","author":"Mo Shentong","year":"1836","unstructured":"Shentong Mo and Yapeng Tian, \u201cAv-sam: Segment anything model meets audio-visual localization and segmentation,\u201d arXiv preprint arXiv:2305.01836, 2023."},{"key":"e_1_3_2_1_18_1","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","volume":"34","author":"Yang Zongxin","year":"2021","unstructured":"Zongxin Yang, Yunchao Wei, and Yi Yang, \u201cAssociating objects with transformers for video object segmentation,\u201d Advances in Neural Information Processing Systems, vol. 34, pp. 2491\u20132502, 2021.","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"PEAI 2024: 2024 International Conference on Power Electronics and Artificial Intelligence","acronym":"PEAI 2024","location":"Xiamen China"},"container-title":["2024 International Conference on Power Electronics and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3674225.3674394","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3674225.3674394","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:06:03Z","timestamp":1750291563000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3674225.3674394"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,19]]},"references-count":18,"alternative-id":["10.1145\/3674225.3674394","10.1145\/3674225"],"URL":"https:\/\/doi.org\/10.1145\/3674225.3674394","relation":{},"subject":[],"published":{"date-parts":[[2024,1,19]]},"assertion":[{"value":"2024-07-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}