{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:42:59Z","timestamp":1772905379305,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031734632","type":"print"},{"value":"9783031734649","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"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\/978-3-031-73464-9_19","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T09:38:20Z","timestamp":1733218700000},"page":"311-327","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Stepping Stones: A Progressive Training Strategy for\u00a0Audio-Visual Semantic Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9027-3111","authenticated-orcid":false,"given":"Juncheng","family":"Ma","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3016-8554","authenticated-orcid":false,"given":"Peiwen","family":"Sun","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5724-5698","authenticated-orcid":false,"given":"Yaoting","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7118-6733","authenticated-orcid":false,"given":"Di","family":"Hu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"19_CR1","unstructured":"Arandjelovic, R., Zisserman, A.: Objects that sound. CoRR abs\/1712.06651 (2017), http:\/\/arxiv.org\/abs\/1712.06651"},{"key":"19_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: CVPR, pp. 16867\u201316876 (2021)","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"19_CR3","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: CVPR, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"19_CR4","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation, vol. 34, pp. 17864\u201317875 (2021)"},{"key":"19_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale (2021), https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Gao, S., Chen, Z., Chen, G., Wang, W., Lu, T.: Avsegformer: audio-visual segmentation with transformer (2024)","DOI":"10.1609\/aaai.v38i11.29104"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: ICASSP, pp. 776\u2013780. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"19_CR8","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":"19_CR9","doi-asserted-by":"crossref","unstructured":"Hershey, S., et\u00a0al.: CNN architectures for large-scale audio classification. In: ICASSP, pp. 131\u2013135. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"19_CR10","unstructured":"Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. In: ICML, pp. 2790\u20132799. PMLR (2019)"},{"issue":"12","key":"19_CR11","first-page":"9844","volume":"44","author":"D Hu","year":"2021","unstructured":"Hu, D., Wei, Y., Qian, R., Lin, W., Song, R., Wen, J.R.: Class-aware sounding objects localization via audiovisual correspondence 44(12), 9844\u20139859 (2021)","journal-title":"Class-aware sounding objects localization via audiovisual correspondence"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Huang, S., et al.: Discovering sounding objects by audio queries for audio visual segmentation. In: IJCAI, pp. 875\u2013883 (2023)","DOI":"10.24963\/ijcai.2023\/97"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Jain, J., Li, J., Chiu, M., Hassani, A., Orlov, N., Shi, H.: Oneformer: one transformer to rule universal image segmentation (2022). https:\/\/arxiv.org\/abs\/2211.06220","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Li, K., Yang, Z., Chen, L., Yang, Y., Xiao, J.: CATR: combinatorial-dependence audio-queried transformer for audio-visual video segmentation. In: ACM MM, pp. 1485\u20131494 (2023)","DOI":"10.1145\/3581783.3611724"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: OMG-Seg: is one model good enough for all segmentation? (2024). https:\/\/arxiv.org\/abs\/2401.10229","DOI":"10.1109\/CVPR52733.2024.02640"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: Audio-visual segmentation by exploring cross-modal mutual semantics. In: ACM MM, pp. 7590\u20137598 (2023)","DOI":"10.1145\/3581783.3612373"},{"key":"19_CR19","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":"19_CR20","unstructured":"Liu, J., Wang, Y., Ju, C., Ma, C., Zhang, Y., Xie, W.: Annotation-free audio-visual segmentation, pp. 5604\u20135614 (2023)"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"19_CR23","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":"19_CR24","doi-asserted-by":"crossref","unstructured":"Mao, Y., Zhang, J., Xiang, M., Zhong, Y., Dai, Y.: Multimodal variational auto-encoder based audio-visual segmentation. In: CVPR, pp. 954\u2013965 (2023)","DOI":"10.1109\/ICCV51070.2023.00094"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.A.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 565\u2013571. IEEE (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Owens, A., Efros, A.A.: Audio-visual scene analysis with self-supervised multisensory features. In: ECCV, pp. 631\u2013648 (2018)","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"19_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1007\/978-3-030-58565-5_18","volume-title":"Computer Vision \u2013 ECCV 2020","author":"R Qian","year":"2020","unstructured":"Qian, R., Hu, D., Dinkel, H., Wu, M., Xu, N., Lin, W.: Multiple sound sources localization from coarse to fine. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 292\u2013308. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_18"},{"key":"19_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015 Part III. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Senocak, A., Oh, T.H., Kim, J., Yang, M.H., Kweon, I.S.: Learning to localize sound source in visual scenes. In: CVPR, pp. 4358\u20134366 (2018)","DOI":"10.1109\/CVPR.2018.00458"},{"key":"19_CR30","unstructured":"Song, Z., Wang, Y., Fan, J., Tan, T., Zhang, Z.: Self-supervised predictive learning: a negative-free method for sound source localization in visual scenes. In: CVPR, pp. 3222\u20133231 (2022)"},{"key":"19_CR31","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 (2024)","DOI":"10.1609\/aaai.v38i6.28378"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Wang, Y., Sun, P., Li, Y., Zhang, H., Hu, D.: Can textual semantics mitigate sounding object segmentation preference? In: IEEE European Conference on Computer Vision (ECCV) (2024)","DOI":"10.1007\/978-3-031-72904-1_20"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Y., Sun, P., Zhou, D., Li, G., Zhang, H., Hu, D.: Ref-AVS: refer and segment objects in audio-visual scenes. In: IEEE European Conference on Computer Vision (ECCV) (2024)","DOI":"10.1007\/978-3-031-72904-1_12"},{"key":"19_CR34","unstructured":"Wei, Y., Hu, D., Tian, Y., Li, X.: Learning in audio-visual context: a review, analysis, and new perspective. arXiv preprint arXiv:2208.09579 (2022)"},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Yan, S., et al.: Referred by multi-modality: a unified temporal transformer for video object segmentation. In: AAAI (2023)","DOI":"10.1609\/aaai.v38i6.28465"},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: CVPR, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"19_CR37","unstructured":"Zhou, J., et\u00a0al.: Audio-visual segmentation with semantics. arXiv preprint arXiv:2301.13190 (2023)"},{"key":"19_CR38","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1007\/978-3-031-19836-6_22","volume-title":"ECCV 2022","author":"J Zhou","year":"2022","unstructured":"Zhou, J., et al.: Audio-visual segmentation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13697, pp. 386\u2013403. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_22"}],"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\/978-3-031-73464-9_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T10:11:41Z","timestamp":1733220701000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73464-9_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031734632","9783031734649"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73464-9_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"4 December 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"}}]}}