{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:54:31Z","timestamp":1777654471211,"version":"3.51.4"},"publisher-location":"Cham","reference-count":85,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732010","type":"print"},{"value":"9783031732027","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"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\/978-3-031-73202-7_13","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T14:17:14Z","timestamp":1732112234000},"page":"215-233","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["ConceptExpress: Harnessing Diffusion Models for\u00a0Single-Image Unsupervised Concept Extraction"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8551-3608","authenticated-orcid":false,"given":"Shaozhe","family":"Hao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7995-9999","authenticated-orcid":false,"given":"Kai","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengyao","family":"Lv","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shihao","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8560-9007","authenticated-orcid":false,"given":"Kwan-Yee K.","family":"Wong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Abdal, R., Zhu, P., Femiani, J., Mitra, N., Wonka, P.: CLIP2StyleGAN: unsupervised extraction of stylegan edit directions. In: ACM SIGGRAPH (2022)","DOI":"10.1145\/3528233.3530747"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Aberman, K., Fried, O., Cohen-Or, D., Lischinski, D.: Break-a-scene: extracting multiple concepts from a single image. In: SIGGRAPH Asia (2023)","DOI":"10.1145\/3610548.3618154"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Fried, O., Lischinski, D.: Blended latent diffusion. In: ACM SIGGRAPH (2023)","DOI":"10.1145\/3592450"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Avrahami, O., et al.: Spatext: spatio-textual representation for controllable image generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Lischinski, D., Fried, O.: Blended diffusion for text-driven editing of natural images. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"13_CR6","unstructured":"Bar-Tal, O., Yariv, L., Lipman, Y., Dekel, T.: Multidiffusion: fusing diffusion paths for controlled image generation. In: ICML (2023)"},{"key":"13_CR7","unstructured":"Baranchuk, D., Voynov, A., Rubachev, I., Khrulkov, V., Babenko, A.: Label-efficient semantic segmentation with diffusion models. In: ICLR (2022)"},{"key":"13_CR8","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: ICLR (2019)"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: learning to follow image editing instructions. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"13_CR11","unstructured":"Chefer, H., et al.: The hidden language of diffusion models. arXiv preprint arXiv:2306.00966 (2023)"},{"key":"13_CR12","unstructured":"Chen, W., et al.: Subject-driven text-to-image generation via apprenticeship learning. In: NeurIPS (2023)"},{"key":"13_CR13","unstructured":"Couairon, G., Verbeek, J., Schwenk, H., Cord, M.: Diffedit: diffusion-based semantic image editing with mask guidance. In: ICLR (2022)"},{"key":"13_CR14","doi-asserted-by":"publisher","unstructured":"Crowson, K., et al.: VQGAN-CLIP: open domain image generation and editing with natural language guidance. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13697, pp. 88\u2013105. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_6","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"13_CR15","unstructured":"Du, Y., Li, S., Mordatch, I.: Compositional visual generation with energy based models. In: NeurIPS (2020)"},{"key":"13_CR16","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. In: ICLR (2023)"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Gal, R., Arar, M., Atzmon, Y., Bermano, A.H., Chechik, G., Cohen-Or, D.: Encoder-based domain tuning for fast personalization of text-to-image models. arXiv preprint arXiv:2302.12228 (2023)","DOI":"10.1145\/3610548.3618173"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Gal, R., Patashnik, O., Maron, H., Bermano, A.H., Chechik, G., Cohen-Or, D.: Stylegan-nada: clip-guided domain adaptation of image generators. ACM Trans. Graph. (TOG) (2022)","DOI":"10.1145\/3528223.3530164"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Gandikota, R., Materzynska, J., Fiotto-Kaufman, J., Bau, D.: Erasing concepts from diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00230"},{"key":"13_CR20","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS (2014)"},{"key":"13_CR21","unstructured":"Hao, S., Han, K., Zhao, S., Wong, K.Y.K.: ViCo: detail-preserving visual condition for personalized text-to-image generation. arXiv preprint arXiv:2306.00971 (2023)"},{"key":"13_CR22","unstructured":"Hedlin, E., Sharma, G., Mahajan, S., Isack, H., Kar, A., Tagliasacchi, A., Yi, K.M.: Unsupervised semantic correspondence using stable diffusion. arXiv preprint arXiv:2305.15581 (2023)"},{"key":"13_CR23","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"13_CR24","unstructured":"Ho, J., Salimans, T., Gritsenko, A.A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. In: NeurIPS (2022)"},{"key":"13_CR25","unstructured":"Jia, X., et al.: Taming encoder for zero fine-tuning image customization with text-to-image diffusion models. arXiv preprint arXiv:2304.02642 (2023)"},{"key":"13_CR26","unstructured":"Jin, C., Tanno, R., Saseendran, A., Diethe, T., Teare, P.: An image is worth multiple words: learning object level concepts using multi-concept prompt learning. arXiv preprint arXiv:2310.12274 (2023)"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., Van Der\u00a0Maaten, L., Fei-Fei, L., Lawrence\u00a0Zitnick, C., Girshick, R.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Karazija, L., Laina, I., Vedaldi, A., Rupprecht, C.: Diffusion models for zero-shot open-vocabulary segmentation. arXiv preprint arXiv:2306.09316 (2023)","DOI":"10.1007\/978-3-031-72652-1_18"},{"key":"13_CR29","unstructured":"Karras, T., et al.: Alias-free generative adversarial networks. In: NeurIPS (2021)"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"13_CR33","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"13_CR34","unstructured":"Kuhn, H.W.: The hungarian method for the assignment problem. Nav. Res. Logist. Q. (1955)"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Wang, S.Y., Shechtman, E., Zhang, R., Zhu, J.Y.: Ablating concepts in text-to-image diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.02074"},{"key":"13_CR36","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Zhang, R., Shechtman, E., Zhu, J.Y.: Multi-concept customization of text-to-image diffusion. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"13_CR37","doi-asserted-by":"crossref","unstructured":"Li, A.C., Prabhudesai, M., Duggal, S., Brown, E., Pathak, D.: Your diffusion model is secretly a zero-shot classifier. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00210"},{"key":"13_CR38","unstructured":"Li, D., Li, J., Hoi, S.C.: Blip-diffusion: pre-trained subject representation for controllable text-to-image generation and editing. In: NeurIPS (2023)"},{"key":"13_CR39","doi-asserted-by":"crossref","unstructured":"Li, X., Lu, J., Han, K., Prisacariu, V.: Sd4match: learning to prompt stable diffusion model for semantic matching. arXiv preprint arXiv:2310.17569 (2023)","DOI":"10.1109\/CVPR52733.2024.02602"},{"key":"13_CR40","doi-asserted-by":"crossref","unstructured":"Liu, N., Du, Y., Li, S., Tenenbaum, J.B., Torralba, A.: Unsupervised compositional concepts discovery with text-to-image generative models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00199"},{"key":"13_CR41","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van\u00a0Gool, L.: Repaint: inpainting using denoising diffusion probabilistic models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"13_CR42","unstructured":"Ma, Y., Yang, H., Wang, W., Fu, J., Liu, J.: Unified multi-modal latent diffusion for joint subject and text conditional image generation. arXiv preprint arXiv:2303.09319 (2023)"},{"key":"13_CR43","unstructured":"Molad, E., et al.: Dreamix: video diffusion models are general video editors. arXiv preprint arXiv:2302.01329 (2023)"},{"key":"13_CR44","unstructured":"Ni, M., Zhang, Y., Feng, K., Li, X., Guo, Y., Zuo, W.: Ref-diff: zero-shot referring image segmentation with generative models. arXiv preprint arXiv:2308.16777 (2023)"},{"key":"13_CR45","unstructured":"Nichol, A.Q., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. In: ICML (2022)"},{"key":"13_CR46","doi-asserted-by":"crossref","unstructured":"Patashnik, O., Garibi, D., Azuri, I., Averbuch-Elor, H., Cohen-Or, D.: Localizing object-level shape variations with text-to-image diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.02107"},{"key":"13_CR47","doi-asserted-by":"crossref","unstructured":"Patashnik, O., Wu, Z., Shechtman, E., Cohen-Or, D., Lischinski, D.: StyleCLIP: text-driven manipulation of stylegan imagery. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"13_CR48","unstructured":"Qiu, Z., et al.: Controlling text-to-image diffusion by orthogonal finetuning. In: NeurIPS (2023)"},{"key":"13_CR49","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"13_CR50","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"13_CR51","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: ICML (2021)"},{"key":"13_CR52","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: ICML (2016)"},{"key":"13_CR53","doi-asserted-by":"crossref","unstructured":"Richardson, E., Goldberg, K., Alaluf, Y., Cohen-Or, D.: Conceptlab: creative generation using diffusion prior constraints. arXiv preprint arXiv:2308.02669 (2023)","DOI":"10.1145\/3659578"},{"key":"13_CR54","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"13_CR55","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: Dreambooth: fine tuning text-to-image diffusion models for subject-driven generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"13_CR56","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS (2022)"},{"key":"13_CR57","doi-asserted-by":"crossref","unstructured":"Sarfraz, S., Sharma, V., Stiefelhagen, R.: Efficient parameter-free clustering using first neighbor relations. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00914"},{"key":"13_CR58","unstructured":"Schuhmann, C., et\u00a0al.: Laion-5b: an open large-scale dataset for training next generation image-text models. In: NeurIPS (2022)"},{"key":"13_CR59","doi-asserted-by":"crossref","unstructured":"Shi, J., Xiong, W., Lin, Z., Jung, H.J.: Instantbooth: personalized text-to-image generation without test-time finetuning. arXiv preprint arXiv:2304.03411 (2023)","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"13_CR60","unstructured":"Singer, U., et\u00a0al.: Make-a-video: text-to-video generation without text-video data. In: ICLR (2022)"},{"key":"13_CR61","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"13_CR62","doi-asserted-by":"crossref","unstructured":"Tang, R., et al.: What the daam: interpreting stable diffusion using cross attention. In: ACL (2023)","DOI":"10.18653\/v1\/2023.acl-long.310"},{"key":"13_CR63","doi-asserted-by":"crossref","unstructured":"Tao, M., Tang, H., Wu, F., Jing, X.Y., Bao, B.K., Xu, C.: DF-GAN: a simple and effective baseline for text-to-image synthesis. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"13_CR64","doi-asserted-by":"crossref","unstructured":"Tewel, Y., Gal, R., Chechik, G., Atzmon, Y.: Key-locked rank one editing for text-to-image personalization. In: ACM SIGGRAPH (2023)","DOI":"10.1145\/3588432.3591506"},{"key":"13_CR65","doi-asserted-by":"crossref","unstructured":"Tian, J., Aggarwal, L., Colaco, A., Kira, Z., Gonzalez-Franco, M.: Diffuse, attend, and segment: unsupervised zero-shot segmentation using stable diffusion. arXiv preprint arXiv:2308.12469 (2023)","DOI":"10.1109\/CVPR52733.2024.00341"},{"key":"13_CR66","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Geyer, M., Bagon, S., Dekel, T.: Plug-and-play diffusion features for text-driven image-to-image translation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"13_CR67","doi-asserted-by":"crossref","unstructured":"Vinker, Y., Voynov, A., Cohen-Or, D., Shamir, A.: Concept decomposition for visual exploration and inspiration. arXiv preprint arXiv:2305.18203 (2023)","DOI":"10.1145\/3618315"},{"key":"13_CR68","unstructured":"Wang, J., et al.: Diffusion model is secretly a training-free open vocabulary semantic segmenter. arXiv preprint arXiv:2309.02773 (2023)"},{"key":"13_CR69","doi-asserted-by":"crossref","unstructured":"Wang, S., et\u00a0al.: Imagen editor and editbench: advancing and evaluating text-guided image inpainting. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"13_CR70","doi-asserted-by":"crossref","unstructured":"Wang, X., Girdhar, R., Yu, S.X., Misra, I.: Cut and learn for unsupervised object detection and instance segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00305"},{"key":"13_CR71","unstructured":"Wang, Z., Gui, L., Negrea, J., Veitch, V.: Concept algebra for text-controlled vision models. arXiv preprint arXiv:2302.03693 (2023)"},{"key":"13_CR72","doi-asserted-by":"crossref","unstructured":"Wei, Y., Zhang, Y., Ji, Z., Bai, J., Zhang, L., Zuo, W.: Elite: encoding visual concepts into textual embeddings for customized text-to-image generation. arXiv preprint arXiv:2302.13848 (2023)","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"13_CR73","doi-asserted-by":"crossref","unstructured":"Wu, J.Z., et al.: Tune-a-video: one-shot tuning of image diffusion models for text-to-video generation. arXiv preprint arXiv:2212.11565 (2022)","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"13_CR74","doi-asserted-by":"crossref","unstructured":"Xia, W., Yang, Y., Xue, J.H., Wu, B.: Tedigan: text-guided diverse face image generation and manipulation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"13_CR75","doi-asserted-by":"crossref","unstructured":"Xiao, C., Yang, Q., Zhou, F., Zhang, C.: From text to mask: localizing entities using the attention of text-to-image diffusion models. arXiv preprint arXiv:2309.04109 (2023)","DOI":"10.1016\/j.neucom.2024.128437"},{"key":"13_CR76","doi-asserted-by":"crossref","unstructured":"Xu, T., et al.: AttnGAN: fine-grained text to image generation with attentional generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"13_CR77","unstructured":"Ye, H., Yang, X., Takac, M., Sunderraman, R., Ji, S.: Improving text-to-image synthesis using contrastive learning. arXiv preprint arXiv:2107.02423 (2021)"},{"key":"13_CR78","unstructured":"Yu, J., et\u00a0al.: Scaling autoregressive models for content-rich text-to-image generation. Trans. Mach. Learn. Res. (2022)"},{"key":"13_CR79","doi-asserted-by":"crossref","unstructured":"Zhang, H., Koh, J.Y., Baldridge, J., Lee, H., Yang, Y.: Cross-modal contrastive learning for text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"13_CR80","unstructured":"Zhang, J., et al.: A tale of two features: stable diffusion complements dino for zero-shot semantic correspondence. In: NeurIPS (2023)"},{"key":"13_CR81","doi-asserted-by":"crossref","unstructured":"Zhang, L., Agrawala, M.: Adding conditional control to text-to-image diffusion models. arXiv preprint arXiv:2302.05543 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"13_CR82","unstructured":"Zhang, Y., Wei, Y., Jiang, D., Zhang, X., Zuo, W., Tian, Q.: Controlvideo: training-free controllable text-to-video generation. In: ICLR (2024)"},{"key":"13_CR83","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Yang, M., Zhou, Q., Wang, Z.: Attention calibration for disentangled text-to-image personalization. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00456"},{"key":"13_CR84","unstructured":"Zhao, S., et al.: Uni-ControlNet: all-in-one control to text-to-image diffusion models. In: NeurIPS (2023)"},{"key":"13_CR85","doi-asserted-by":"crossref","unstructured":"Zhu, M., Pan, P., Chen, W., Yang, Y.: DM-GAN: dynamic memory generative adversarial networks for text-to-image synthesis. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00595"}],"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\/978-3-031-73202-7_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T15:07:44Z","timestamp":1732115264000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73202-7_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031732010","9783031732027"],"references-count":85,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73202-7_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 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"}}]}}