{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T21:21:42Z","timestamp":1762377702280,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031723377"},{"type":"electronic","value":"9783031723384"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72338-4_3","type":"book-chapter","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T10:03:01Z","timestamp":1726480981000},"page":"31-44","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Integrating Audio-Visual Contexts with\u00a0Refinement for\u00a0Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1981-9005","authenticated-orcid":false,"given":"Qingwei","family":"Geng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7096-1830","authenticated-orcid":false,"given":"Xiaodong","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,17]]},"reference":[{"key":"3_CR1","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1007\/s11633-021-1293-0","volume":"18","author":"H Zhu","year":"2021","unstructured":"Zhu, H., Luo, M.D., Wang, R., Zheng, A.H., He, R.: Deep audio-visual learning: a survey. Int. J. Autom. Comput. 18, 351\u2013376 (2021)","journal-title":"Int. J. Autom. Comput."},{"key":"3_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1007\/978-3-030-01216-8_16","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Tian","year":"2018","unstructured":"Tian, Y., Shi, J., Li, B., Duan, Z., Xu, C.: Audio-visual event localization in unconstrained videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 252\u2013268. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_16"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Wu, Y., Zhu, L., Yan, Y., Yang, Y.: Dual attention matching for audio-visual event localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6292\u20136300 (2019)","DOI":"10.1109\/ICCV.2019.00639"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Lin, Y.B., Wang, Y.C.F.: Audiovisual transformer with instance attention for audio-visual event localization. In: Proceedings of the Asian Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-69544-6_17"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Zisserman, A.: Look, listen and learn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 609\u2013617 (2017)","DOI":"10.1109\/ICCV.2017.73"},{"key":"3_CR6","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":"3_CR7","doi-asserted-by":"crossref","unstructured":"Zhao, H., Gan, C., Rouditchenko, A., Vondrick, C., McDermott, J., Torralba, A.: The sound of pixels. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 570\u2013586 (2018)","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"3_CR8","doi-asserted-by":"publisher","unstructured":"Zhou, J., et al.: Audio\u2013visual segmentation. In: European Conference on Computer Vision. pp. 386\u2013403. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_22","DOI":"10.1007\/978-3-031-19836-6_22"},{"key":"3_CR9","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"3_CR10","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Qin, X., Zhang, Z., Huang, C., Gao, C., Dehghan, M., Jagersand, M.: Basnet: Boundary-aware salient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7479\u20137489 (2019)","DOI":"10.1109\/CVPR.2019.00766"},{"key":"3_CR12","unstructured":"Islam, M.A., Kalash, M., Rochan, M., Bruce, N.D., Wang, Y.: Salient object detection using a context-aware refinement network. In: BMVC (2017)"},{"key":"3_CR13","unstructured":"Hershey, J., Movellan, J.: Audio vision: Using audio-visual synchrony to locate sounds. Adv. Neural Inform. Process. Syst. 12 (1999)"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Kidron, E., Schechner, Y.Y., Elad, M.: Pixels that sound. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol.\u00a01, pp. 88\u201395. IEEE (2005)","DOI":"10.1109\/CVPR.2005.274"},{"issue":"2","key":"3_CR15","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1109\/TMM.2012.2228476","volume":"15","author":"H Izadinia","year":"2012","unstructured":"Izadinia, H., Saleemi, I., Shah, M.: Multimodal analysis for identification and segmentation of moving-sounding objects. IEEE Trans. Multimedia 15(2), 378\u2013390 (2012)","journal-title":"IEEE Trans. Multimedia"},{"key":"3_CR16","first-page":"10077","volume":"33","author":"D Hu","year":"2020","unstructured":"Hu, D., et al.: Discriminative sounding objects localization via self-supervised audiovisual matching. Adv. Neural. Inf. Process. Syst. 33, 10077\u201310087 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"3_CR18","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"issue":"8","key":"3_CR19","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"3_CR20","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"3_CR21","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":"3_CR22","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"3_CR23","unstructured":"Zhang, H., et al.: Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Zheng, S., et\u00a0al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6881\u20136890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"3_CR26","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Adv. Neural Inform. Process. Syst. 32 (2019)"},{"key":"3_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58577-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-C Chen","year":"2020","unstructured":"Chen, Y.-C., et al.: UNITER: universal image-text representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_7"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Wang, R., Pan, Z., Feng, R., Zhang, Y.: Look, listen, and attend: co-attention network for self-supervised audio-visual representation learning. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 3884\u20133892 (2020)","DOI":"10.1145\/3394171.3413869"},{"key":"3_CR29","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":"3_CR30","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"issue":"3","key":"3_CR31","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","volume":"8","author":"W Wang","year":"2022","unstructured":"Wang, W., et al.: Pvt v2: improved baselines with pyramid vision transformer. Comput. Visual Media 8(3), 415\u2013424 (2022)","journal-title":"Comput. Visual Media"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Hershey, S., et\u00a0al.: Cnn architectures for large-scale audio classification. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 131\u2013135. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Xu, P., Zhu, X., Clifton, D.A.: Multimodal learning with transformers: A survey. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"3_CR34","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":"3_CR35","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., et al.: Audio set: An ontology and human-labeled dataset for audio events. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 776\u2013780. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"3_CR37","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"3_CR38","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":"3_CR39","doi-asserted-by":"crossref","unstructured":"Mahadevan, S., Athar, A., O\u0161ep, A., Hennen, S., Leal-Taix\u00e9, L., Leibe, B.: Making a case for 3d convolutions for object segmentation in videos. arXiv preprint arXiv:2008.11516 (2020)","DOI":"10.5244\/C.34.65"},{"key":"3_CR40","doi-asserted-by":"crossref","unstructured":"Duke, B., Ahmed, A., Wolf, C., Aarabi, P., Taylor, G.W.: Sstvos: sparse spatiotemporal transformers for video object segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5912\u20135921 (2021)","DOI":"10.1109\/CVPR46437.2021.00585"},{"key":"3_CR41","unstructured":"Mao, Y., et al.: Transformer transforms salient object detection and camouflaged object detection 1(2), 5. arXiv preprint arXiv:2104.10127 (2021)"},{"key":"3_CR42","first-page":"15448","volume":"34","author":"J Zhang","year":"2021","unstructured":"Zhang, J., Xie, J., Barnes, N., Li, P.: Learning generative vision transformer with energy-based latent space for saliency prediction. Adv. Neural. Inf. Process. Syst. 34, 15448\u201315463 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72338-4_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T07:48:50Z","timestamp":1759996130000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72338-4_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723377","9783031723384"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72338-4_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"17 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lugano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","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":"17 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}