{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T08:40:40Z","timestamp":1742978440054,"version":"3.40.3"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031783463"},{"type":"electronic","value":"9783031783470"}],"license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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\/978-3-031-78347-0_3","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T14:53:29Z","timestamp":1733064809000},"page":"36-50","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Sketch2Seg: Sketch-Based Image Segmentation with\u00a0Pre-trained Diffusion Model"],"prefix":"10.1007","author":[{"given":"Xin","family":"Dai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoge","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonggang","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Rahman, A., Valanarasu, J.M.J., Hacihaliloglu, I., Patel, V.M.: Ambiguous medical image segmentation using diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11536\u201311546 (2023)","DOI":"10.1109\/CVPR52729.2023.01110"},{"key":"3_CR2","unstructured":"Baranchuk, D., et al.: Label-efficient semantic segmentation with diffusion models. In: International Conference on Learning Representations (2021)"},{"key":"3_CR3","unstructured":"Amit, T., Shaharbany, T., Nachmani, E., Wolf, L.: SegDiff: image segmentation with diffusion probabilistic models. arXiv preprint arXiv:2112.00390 (2021)"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Brempong, E.A., Kornblith, S., Chen, T., Parmar, N., Minderer, M., Norouzi, M.: Denoising pretraining for semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4175\u20134186 (2022)","DOI":"10.1109\/CVPRW56347.2022.00462"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Pnvr, K., Singh, B., Ghosh, P., Siddiquie, B., Jacobs, D.: LD-ZNet: a latent diffusion approach for text-based image segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4157\u20134168 (2023)","DOI":"10.1109\/ICCV51070.2023.00384"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Xu, J., Liu, S., Vahdat, A., Byeon, W., Wang, X., De Mello, S.: Open-vocabulary panoptic segmentation with text-to-image diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2955\u20132966 (2023)","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Qi, Y., Song, Y.Z., Zhang, H., Liu, J.: Sketch-based image retrieval via siamese convolutional neural network. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 2460\u20132464. IEEE (2016)","DOI":"10.1109\/ICIP.2016.7532801"},{"key":"3_CR8","doi-asserted-by":"publisher","first-page":"9470","DOI":"10.1109\/TIP.2020.3028292","volume":"29","author":"C Hu","year":"2020","unstructured":"Hu, C., Li, D., Yang, Y., Hospedales, T.M., Song, Y.Z.: Sketch-a-Segmenter: sketch-based photo segmenter generation. IEEE Trans. Image Process. 29, 9470\u20139481 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"3_CR9","unstructured":"Yang, R., Li, D., Hu, C., Hospedales, T., Zhang, H., Song, Y.Z.: Sketch-based video object segmentation: benchmark and analysis. arXiv preprint arXiv:2311.07261 (2023)"},{"issue":"7","key":"3_CR10","doi-asserted-by":"publisher","first-page":"790","DOI":"10.1016\/j.cviu.2013.02.005","volume":"117","author":"R Hu","year":"2013","unstructured":"Hu, R., Collomosse, J.: A performance evaluation of gradient field hog descriptor for sketch based image retrieval. Comput. Vis. Image Underst. 117(7), 790\u2013806 (2013)","journal-title":"Comput. Vis. Image Underst."},{"issue":"1","key":"3_CR11","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1109\/TPAMI.2022.3148853","volume":"45","author":"P Xu","year":"2022","unstructured":"Xu, P., Hospedales, T.M., Yin, Q., Song, Y.Z., Xiang, T., Wang, L.: Deep learning for free-hand sketch: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 285\u2013312 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Voynov, A., Aberman, K., Cohen-Or, D.: Sketch-guided text-to-image diffusion models. In: ACM SIGGRAPH 2023 Conference Proceedings (2023)","DOI":"10.1145\/3588432.3591560"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Chowdhury, P.N., Bhunia, A.K., Sain, A., Koley, S., Xiang, T., Song, Y.Z.: What can human sketches do for object detection?. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15083\u201315094 (2023)","DOI":"10.1109\/CVPR52729.2023.01448"},{"key":"3_CR16","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":"3_CR17","doi-asserted-by":"crossref","unstructured":"Pang, K., Yang, Y., Hospedales, T.M., Xiang, T., Song, Y.Z.: Solving mixed-modal jigsaw puzzle for fine-grained sketch-based image retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10347\u201310355 (2020)","DOI":"10.1109\/CVPR42600.2020.01036"},{"key":"3_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833\u2013851. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49"},{"key":"3_CR19","unstructured":"Ha, D., Dai, A., Le, Q.V.: Hypernetworks. arXiv preprint arXiv:1609.09106 (2016)"},{"key":"3_CR20","unstructured":"Riba, P., Dey, S., Biten, A.F., Llados, J.: Localizing infinity-shaped fishes: sketch-guided object localization in the wild. arXiv preprint arXiv:2109.11874 (2021)"},{"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","doi-asserted-by":"crossref","unstructured":"Dombrowski, M., Reynaud, H., Baugh, M., Kainz, B.: Foreground-background separation through concept distillation from generative image foundation models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 988\u2013998) (2023)","DOI":"10.1109\/ICCV51070.2023.00097"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Chen, T., Li, L., Saxena, S., Hinton, G., Fleet, D.J.: A generalist framework for panoptic segmentation of images and videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 909\u2013919 (2023)","DOI":"10.1109\/ICCV51070.2023.00090"},{"key":"3_CR24","unstructured":"Kim, B., Oh, Y., Ye, J.C.: Diffusion adversarial representation learning for self-supervised vessel segmentation. arXiv preprint arXiv:2209.14566 (2022)"},{"key":"3_CR25","unstructured":"Wang, J., et al.: Diffusion model is secretly a training-free open vocabulary semantic segmenter. arXiv preprint arXiv:2309.02773 (2023)"},{"key":"3_CR26","unstructured":"Nichol, A., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"3_CR27","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: Advances in Neural Information Processing Systems, vol. 34, pp. 8780\u20138794 (2021)"},{"issue":"4","key":"3_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897824.2925954","volume":"35","author":"P Sangkloy","year":"2016","unstructured":"Sangkloy, P., Burnell, N., Ham, C., Hays, J.: The sketchy database: learning to retrieve badly drawn bunnies. ACM Trans. Graph. (TOG) 35(4), 1\u201312 (2016)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Gao, C., Liu, Q., Xu, Q., Wang, L., Liu, J., Zou, C.: SketchyCOCO: image generation from freehand scene sketches. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5174\u20135183 (2020)","DOI":"10.1109\/CVPR42600.2020.00522"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Shaban, A., Bansal, S., Liu, Z., Essa, I., Boots, B.: One-shot learning for semantic segmentation. arXiv preprint arXiv:1709.03410 (2017)","DOI":"10.5244\/C.31.167"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Girshick, R.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Bilen, H., Vedaldi, A.: Weakly supervised deep detection networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2846\u20132854 (2016)","DOI":"10.1109\/CVPR.2016.311"},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Tang, P., Wang, X., Bai, X., Liu, W.: Multiple instance detection network with online instance classifier refinement. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2843\u20132851 (2017)","DOI":"10.1109\/CVPR.2017.326"},{"issue":"1","key":"3_CR35","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1109\/TPAMI.2018.2876304","volume":"42","author":"P Tang","year":"2018","unstructured":"Tang, P., et al.: PCL: proposal cluster learning for weakly supervised object detection. IEEE Trans. Pattern Anal. Mach. Intell. 42(1), 176\u2013191 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Ren, Z., et al.: Instance-aware, context-focused, and memory-efficient weakly supervised object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10598\u201310607 (2020)","DOI":"10.1109\/CVPR42600.2020.01061"},{"key":"3_CR37","unstructured":"L Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"3_CR38","unstructured":"Jongejan, J., et al.: The Quick, Draw! http:\/\/www.springer.com\/lncs (2016)"},{"issue":"4","key":"3_CR39","first-page":"1","volume":"31","author":"M Eitz","year":"2012","unstructured":"Eitz, M., Hays, J., Alexa, M.: How do humans sketch objects? ACM Trans. Graph. (TOG) 31(4), 1\u201310 (2012)","journal-title":"ACM Trans. Graph. (TOG)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78347-0_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T15:02:14Z","timestamp":1733065334000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78347-0_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"ISBN":["9783031783463","9783031783470"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78347-0_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}