{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T17:47:38Z","timestamp":1793123258940,"version":"4.5.0"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729799","type":"print"},{"value":"9783031729805","type":"electronic"}],"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\/978-3-031-72980-5_12","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:15:43Z","timestamp":1730106943000},"page":"200-217","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["OTSeg: Multi-Prompt Sinkhorn Attention for\u00a0Zero-Shot Semantic Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7508-7145","authenticated-orcid":false,"given":"Kwanyoung","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4319-8435","authenticated-orcid":false,"given":"Yujin","family":"Oh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9763-9609","authenticated-orcid":false,"given":"Jong Chul","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"12_CR1","unstructured":"Allingham, J.U., et al.: A simple zero-shot prompt weighting technique to improve prompt ensembling in text-image models. In: Krause, A., Brunskill, E., Cho, K., Engelhardt, B., Sabato, S., Scarlett, J. (eds.) Proceedings of the 40th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0202, pp. 547\u2013568. PMLR (2023). https:\/\/proceedings.mlr.press\/v202\/allingham23a.html"},{"key":"12_CR2","unstructured":"Bucher, M., Vu, T.H., Cord, M., P\u00e9rez, P.: Zero-shot semantic segmentation. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: COCO-stuff: thing and stuff classes in context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1209\u20131218 (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"12_CR5","unstructured":"Chen, G., Yao, W., Song, X., Li, X., Rao, Y., Zhang, K.: Prompt learning with optimal transport for vision-language models. arXiv preprint arXiv:2210.01253 (2022)"},{"key":"12_CR6","unstructured":"Chen, L., Gan, Z., Cheng, Y., Li, L., Carin, L., Liu, J.: Graph optimal transport for cross-domain alignment. In: International Conference on Machine Learning, pp. 1542\u20131553. PMLR (2020)"},{"key":"12_CR7","unstructured":"Contributors, M: MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark (2020). https:\/\/github.com\/open-mmlab\/mmsegmentation"},{"key":"12_CR8","unstructured":"Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. In: Advances in Neural Information Processing Systems, vol. 26 (2013)"},{"key":"12_CR9","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)"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Ding, J., Xue, N., Xia, G.S., Dai, D.: Decoupling zero-shot semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11583\u201311592 (2022)","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"12_CR11","unstructured":"Everingham, M., Winn, J.: The PASCAL visual object classes challenge 2012 (VOC2012) development kit. Pattern Anal. Stat. Model. Comput. Learn. Tech. Rep. 2007, 1\u201345 (2012)"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Flamary, R., Courty, N., Tuia, D., Rakotomamonjy, A.: Optimal transport for domain adaptation. IEEE Trans. Pattern Anal. Mach. Intell 1 (2016)","DOI":"10.1109\/TPAMI.2016.2615921"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Gu, Z., Zhou, S., Niu, L., Zhao, Z., Zhang, L.: Context-aware feature generation for zero-shot semantic segmentation. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1921\u20131929 (2020)","DOI":"10.1145\/3394171.3413593"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Guo, J., et al.: MVP-SEG: multi-view prompt learning for open-vocabulary semantic segmentation. arXiv preprint arXiv:2304.06957 (2023)","DOI":"10.1007\/978-981-99-8555-5_13"},{"key":"12_CR15","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1007\/978-3-031-19827-4_41","volume-title":"ECCV 2022","author":"M Jia","year":"2022","unstructured":"Jia, M., et al.: Visual prompt tuning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13693, pp. 709\u2013727. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19827-4_41"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Kim, J., El-Khamy, M., Lee, J.: T-GSA: transformer with Gaussian-weighted self-attention for speech enhancement. In: 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2020, pp. 6649\u20136653. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053591"},{"key":"12_CR17","unstructured":"Li, B., Weinberger, K.Q., Belongie, S., Koltun, V., Ranftl, R.: Language-driven semantic segmentation. arXiv preprint arXiv:2201.03546 (2022)"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Liang, F., et al.: Open-vocabulary semantic segmentation with mask-adapted clip. arXiv preprint arXiv:2210.04150 (2022)","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhu, L., Yamada, M., Yang, Y.: Semantic correspondence as an optimal transport problem. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4463\u20134472 (2020)","DOI":"10.1109\/CVPR42600.2020.00452"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., et al.: The role of context for object detection and semantic segmentation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 891\u2013898 (2014)","DOI":"10.1109\/CVPR.2014.119"},{"key":"12_CR21","unstructured":"Nguyen, T.M., et al.: Improving transformers with probabilistic attention keys. In: International Conference on Machine Learning, pp. 16595\u201316621. PMLR (2022)"},{"key":"12_CR22","unstructured":"Nguyen, T., et al.: Improving transformer with an admixture of attention heads. In: Advances in Neural Information Processing Systems, vol. 35, pp. 27937\u201327952 (2022)"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Pastore, G., Cermelli, F., Xian, Y., Mancini, M., Akata, Z., Caputo, B.: A closer look at self-training for zero-label semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2693\u20132702 (2021)","DOI":"10.1109\/CVPRW53098.2021.00303"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Peyr\u00e9, G., Cuturi, M., et\u00a0al.: Computational optimal transport: with applications to data science. Found. Trends\u00ae Mach. Learn. 11(5-6), 355\u2013607 (2019)","DOI":"10.1561\/2200000073"},{"key":"12_CR25","unstructured":"Qin, J., et\u00a0al.: FreeSeg: unified, universal and open-vocabulary image segmentation. arXiv preprint arXiv:2303.17225 (2023)"},{"key":"12_CR26","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Rao, Y., et al.: DenseCLIP: language-guided dense prediction with context-aware prompting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18082\u201318091 (2022)","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"12_CR28","unstructured":"Sander, M.E., Ablin, P., Blondel, M., Peyr\u00e9, G.: SinkFormers: transformers with doubly stochastic attention. In: International Conference on Artificial Intelligence and Statistics, pp. 3515\u20133530. PMLR (2022)"},{"issue":"3","key":"12_CR29","doi-asserted-by":"publisher","first-page":"A1443","DOI":"10.1137\/16M1106018","volume":"41","author":"B Schmitzer","year":"2019","unstructured":"Schmitzer, B.: Stabilized sparse scaling algorithms for entropy regularized transport problems. SIAM J. Sci. Comput. 41(3), A1443\u2013A1481 (2019)","journal-title":"SIAM J. Sci. Comput."},{"key":"12_CR30","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"12_CR31","unstructured":"Xu, H., Luo, D., Carin, L.: Scalable Gromov-Wasserstein learning for graph partitioning and matching. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"12_CR32","unstructured":"Xu, H., Luo, D., Zha, H., Duke, L.C.: Gromov-Wasserstein learning for graph matching and node embedding. In: International Conference on Machine Learning, pp. 6932\u20136941. PMLR (2019)"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: GroupViT: semantic segmentation emerges from text supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18134\u201318144 (2022)","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Wei, F., Hu, H., Bai, X.: Side adapter network for open-vocabulary semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2945\u20132954 (2023)","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Xu, M., et al.: A simple baseline for zero-shot semantic segmentation with pre-trained vision-language model. arXiv preprint arXiv:2112.14757 (2021)","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"12_CR36","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B., et al.: Semantic understanding of scenes through the ADE20K dataset. Int. J. Comput. Vis. 127, 302\u2013321 (2019)","journal-title":"Int. J. Comput. Vis."},{"key":"12_CR37","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"696","DOI":"10.1007\/978-3-031-19815-1_40","volume-title":"ECCV 2022","author":"C Zhou","year":"2022","unstructured":"Zhou, C., Loy, C.C., Dai, B.: Extract free dense labels from CLIP. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13688, pp. 696\u2013712. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_40"},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Lei, Y., Zhang, B., Liu, L., Liu, Y.: ZegCLIP: towards adapting clip for zero-shot semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11175\u201311185 (2023)","DOI":"10.1109\/CVPR52729.2023.01075"}],"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\/978-3-031-72980-5_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:18:47Z","timestamp":1730107127000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72980-5_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031729799","9783031729805"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72980-5_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"29 October 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"}}]}}