{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T15:11:24Z","timestamp":1777734684647,"version":"3.51.4"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726835","type":"print"},{"value":"9783031726842","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72684-2_25","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:03:55Z","timestamp":1730574235000},"page":"438-456","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["CPM: Class-Conditional Prompting Machine for\u00a0Audio-Visual Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8983-2895","authenticated-orcid":false,"given":"Yuanhong","family":"Chen","sequence":"first","affiliation":[]},{"given":"Chong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yuyuan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Hu","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Gustavo","family":"Carneiro","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"25_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Chen, H., Xie, W., Afouras, T., Nagrani, A., Vedaldi, A., Zisserman, A.: Localizing visual sounds the hard way. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16867\u201316876 (2021)","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Chen, J., Lu, J., Zhu, X., Zhang, L.: Generative semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7111\u20137120 (2023)","DOI":"10.1109\/CVPR52729.2023.00687"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 801\u2013818 (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Chen, T., et al.: Bootstrapping audio-visual segmentation by strengthening audio cues. arXiv preprint arXiv:2402.02327 (2024)","DOI":"10.1109\/TCSVT.2024.3486344"},{"key":"25_CR6","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"25_CR7","unstructured":"Chen, Y., Liu, Y., Wang, H., Liu, F., Wang, C., Carneiro, G.: A closer look at audio-visual semantic segmentation. arXiv e-prints pp. arXiv\u20132304 (2023)"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"25_CR9","first-page":"17864","volume":"34","author":"B Cheng","year":"2021","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. Adv. Neural. Inf. Process. Syst. 34, 17864\u201317875 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"1","key":"25_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"AP Dempster","year":"1977","unstructured":"Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. J. Roy. Stat. Soc.: Ser. B (Methodol.) 39(1), 1\u201322 (1977)","journal-title":"J. Roy. Stat. Soc.: Ser. B (Methodol.)"},{"key":"25_CR11","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vision 111, 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"25_CR12","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vision 88, 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vision"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Gao, R., Grauman, K.: Co-separating sounds of visual objects. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3879\u20133888 (2019)","DOI":"10.1109\/ICCV.2019.00398"},{"key":"25_CR14","unstructured":"Gao, S., Chen, Z., Chen, G., Wang, W., Lu, T.: Avsegformer: audio-visual segmentation with transformer. arXiv preprint arXiv:2307.01146 (2023)"},{"issue":"2","key":"25_CR15","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/MASSP.1984.1162229","volume":"1","author":"R Gray","year":"1984","unstructured":"Gray, R.: Vector quantization. IEEE Assp Mag. 1(2), 4\u201329 (1984)","journal-title":"IEEE Assp Mag."},{"key":"25_CR16","unstructured":"Hao, D., Mao, Y., He, B., Han, X., Dai, Y., Zhong, Y.: Improving audio-visual segmentation with bidirectional generation. arXiv preprint arXiv:2308.08288 (2023)"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Hu, X., Chen, Z., Owens, A.: Mix and localize: localizing sound sources in mixtures. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10483\u201310492 (2022)","DOI":"10.1109\/CVPR52688.2022.01023"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Huang, S., et al.: Discovering sounding objects by audio queries for audio visual segmentation. arXiv preprint arXiv:2309.09501 (2023)","DOI":"10.24963\/ijcai.2023\/97"},{"key":"25_CR20","unstructured":"Jaegle, A., et\u00a0al.: Perceiver IO: a general architecture for structured inputs & outputs. arXiv preprint arXiv:2107.14795 (2021)"},{"key":"25_CR21","first-page":"18661","volume":"33","author":"P Khosla","year":"2020","unstructured":"Khosla, P., et al.: Supervised contrastive learning. Adv. Neural. Inf. Process. Syst. 33, 18661\u201318673 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR22","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., Zhang, L.: DN-DETR: accelerate detr training by introducing query denoising. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13619\u201313627 (2022)","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Li, K., Yang, Z., Chen, L., Yang, Y., Xun, J.: Catr: combinatorial-dependence audio-queried transformer for audio-visual video segmentation. arXiv preprint arXiv:2309.09709 (2023)","DOI":"10.1145\/3581783.3611724"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Li, T., et al.: Targeted supervised contrastive learning for long-tailed recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6918\u20136928 (2022)","DOI":"10.1109\/CVPR52688.2022.00679"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Towards robust audiovisual segmentation in complex environments with quantization-based semantic decomposition. arXiv preprint arXiv:2310.00132 (2023)","DOI":"10.1109\/CVPR52733.2024.00327"},{"key":"25_CR27","first-page":"31360","volume":"35","author":"C Liang","year":"2022","unstructured":"Liang, C., Wang, W., Miao, J., Yang, Y.: Gmmseg: gaussian mixture based generative semantic segmentation models. Adv. Neural. Inf. Process. Syst. 35, 31360\u201331375 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Liu, C., Ding, H., Jiang, X.: Gres: generalized referring expression segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23592\u201323601 (2023)","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: Audio-visual segmentation by exploring cross-modal mutual semantics (2023)","DOI":"10.1145\/3581783.3612373"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: Bavs: bootstrapping audio-visual segmentation by integrating foundation knowledge. arXiv preprint arXiv:2308.10175 (2023)","DOI":"10.1109\/TMM.2024.3405622"},{"key":"25_CR31","doi-asserted-by":"crossref","unstructured":"Liu, J., Ju, C., Ma, C., Wang, Y., Wang, Y., Zhang, Y.: Audio-aware query-enhanced transformer for audio-visual segmentation. arXiv preprint arXiv:2307.13236 (2023)","DOI":"10.1109\/WACV57701.2024.00551"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Liu, J., Wang, Y., Ju, C., Zhang, Y., Xie, W.: Annotation-free audio-visual segmentation. arXiv preprint arXiv:2305.11019 (2023)","DOI":"10.1109\/WACV57701.2024.00551"},{"key":"25_CR33","unstructured":"Liu, S., et al.: Dab-detr: dynamic anchor boxes are better queries for detr. arXiv preprint arXiv:2201.12329 (2022)"},{"key":"25_CR34","doi-asserted-by":"crossref","unstructured":"Liu, X., Carrington, P., Chen, X., Pavel, A.: What makes videos accessible to blind and visually impaired people? In: Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, pp. 1\u201314 (2021)","DOI":"10.1145\/3411764.3445233"},{"key":"25_CR35","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"25_CR36","unstructured":"Mao, Y., Zhang, J., Xiang, M., Lv, Y., Zhong, Y., Dai, Y.: Contrastive conditional latent diffusion for audio-visual segmentation. arXiv preprint arXiv:2307.16579 (2023)"},{"key":"25_CR37","doi-asserted-by":"crossref","unstructured":"Mao, Y., Zhang, J., Xiang, M., Zhong, Y., Dai, Y.: Multimodal variational auto-encoder based audio-visual segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 954\u2013965 (2023)","DOI":"10.1109\/ICCV51070.2023.00094"},{"issue":"5","key":"25_CR38","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1109\/TPAMI.2004.1273918","volume":"26","author":"DR Martin","year":"2004","unstructured":"Martin, D.R., Fowlkes, C.C., Malik, J.: Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Trans. Pattern Anal. Mach. Intell. 26(5), 530\u2013549 (2004)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Meng, D., et al.: Conditional detr for fast training convergence. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3651\u20133660 (2021)","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"25_CR40","unstructured":"Mo, S., Morgado, P.: A closer look at weakly-supervised audio-visual source localization. arXiv preprint arXiv:2209.09634 (2022)"},{"key":"25_CR41","doi-asserted-by":"publisher","unstructured":"Mo, S., Morgado, P.: Localizing visual sounds the easy way. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022, ECCV 2022, LNCS, vol. 13697, pp. 218\u2013234. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_13","DOI":"10.1007\/978-3-031-19836-6_13"},{"key":"25_CR42","doi-asserted-by":"crossref","unstructured":"Mo, S., Tian, Y.: Audio-visual grouping network for sound localization from mixtures. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10565\u201310574 (2023)","DOI":"10.1109\/CVPR52729.2023.01018"},{"key":"25_CR43","unstructured":"Mo, S., Tian, Y.: Av-sam: segment anything model meets audio-visual localization and segmentation. arXiv preprint arXiv:2305.01836 (2023)"},{"key":"25_CR44","doi-asserted-by":"crossref","unstructured":"Murray, M.M., Wallace, M.T.: The neural bases of multisensory processes. Frontiers in Neuroscience (2011)","DOI":"10.1201\/b11092"},{"key":"25_CR45","doi-asserted-by":"crossref","unstructured":"Reynolds, D.A., et\u00a0al.: Gaussian mixture models. Encyclopedia Biometr. 741(659-663) (2009)","DOI":"10.1007\/978-0-387-73003-5_196"},{"key":"25_CR46","doi-asserted-by":"crossref","unstructured":"Senocak, A., Ryu, H., Kim, J., Oh, T.H., Pfister, H., Chung, J.S.: Sound source localization is all about cross-modal alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7777\u20137787 (2023)","DOI":"10.1109\/ICCV51070.2023.00715"},{"key":"25_CR47","doi-asserted-by":"crossref","unstructured":"Siam, M., Oreshkin, B.N., Jagersand, M.: Amp: adaptive masked proxies for few-shot segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5249\u20135258 (2019)","DOI":"10.1109\/ICCV.2019.00535"},{"key":"25_CR48","doi-asserted-by":"crossref","unstructured":"Sun, Z., Cao, S., Yang, Y., Kitani, K.M.: Rethinking transformer-based set prediction for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3611\u20133620 (2021)","DOI":"10.1109\/ICCV48922.2021.00359"},{"key":"25_CR49","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"25_CR50","doi-asserted-by":"crossref","unstructured":"Wang, W., Zhou, T., Yu, F., Dai, J., Konukoglu, E., Van\u00a0Gool, L.: Exploring cross-image pixel contrast for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7303\u20137313 (2021)","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"25_CR51","doi-asserted-by":"crossref","unstructured":"Wang, Y., Liu, W., Li, G., Ding, J., Hu, D., Li, X.: Prompting segmentation with sound is generalizable audio-visual source localizer. arXiv preprint arXiv:2309.07929 (2023)","DOI":"10.1609\/aaai.v38i6.28378"},{"key":"25_CR52","doi-asserted-by":"crossref","unstructured":"Wu, J., Jiang, Y., Sun, P., Yuan, Z., Luo, P.: Language as queries for referring video object segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4974\u20134984 (2022)","DOI":"10.1109\/CVPR52688.2022.00492"},{"issue":"10","key":"25_CR53","doi-asserted-by":"publisher","first-page":"12113","DOI":"10.1109\/TPAMI.2023.3275156","volume":"45","author":"P Xu","year":"2023","unstructured":"Xu, P., Zhu, X., Clifton, D.A.: Multimodal learning with transformers: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 45(10), 12113\u201312132 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR54","doi-asserted-by":"crossref","unstructured":"Yang, Q., et al.: Cooperation does matter: exploring multi-order bilateral relations for audio-visual segmentation. arXiv preprint arXiv:2312.06462 (2023)","DOI":"10.1109\/CVPR52733.2024.02562"},{"key":"25_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: MP-former: mask-piloted transformer for image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18074\u201318083 (2023)","DOI":"10.1109\/CVPR52729.2023.01733"},{"key":"25_CR56","unstructured":"Zhou, J., et\u00a0al.: Audio-visual segmentation with semantics. arXiv preprint arXiv:2301.13190 (2023)"},{"key":"25_CR57","doi-asserted-by":"publisher","unstructured":"Zhou, J., et al.: Audio-visual segmentation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022, ECCV 2022, LNCS, vol. 13697, pp. 386\u2013403. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_22","DOI":"10.1007\/978-3-031-19836-6_22"},{"key":"25_CR58","doi-asserted-by":"crossref","unstructured":"Zhou, T., Zhang, M., Zhao, F., Li, J.: Regional semantic contrast and aggregation for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4299\u20134309 (2022)","DOI":"10.1109\/CVPR52688.2022.00426"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72684-2_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:12:08Z","timestamp":1730574728000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72684-2_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031726835","9783031726842"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72684-2_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}