{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T18:42:01Z","timestamp":1762108921879,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031730290"},{"type":"electronic","value":"9783031730306"}],"license":[{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"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\/978-3-031-73030-6_22","type":"book-chapter","created":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T17:02:34Z","timestamp":1732554154000},"page":"393-409","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Diffusion Models as\u00a0Data Mining Tools"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2278-5825","authenticated-orcid":false,"given":"Ioannis","family":"Siglidis","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6915-0126","authenticated-orcid":false,"given":"Aleksander","family":"Holynski","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5720-8070","authenticated-orcid":false,"given":"Alexei A.","family":"Efros","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3804-0193","authenticated-orcid":false,"given":"Mathieu","family":"Aubry","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7362-1401","authenticated-orcid":false,"given":"Shiry","family":"Ginosar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,24]]},"reference":[{"key":"22_CR1","unstructured":"geodummy. https:\/\/geodummy.com\/. Accessed 14 Nov 2023"},{"key":"22_CR2","unstructured":"geoguessr. https:\/\/www.geoguessr.com\/. Accessed 14 Nov 2023"},{"key":"22_CR3","unstructured":"geohints. https:\/\/geohints.com\/. Accessed 14 Nov 2023"},{"key":"22_CR4","unstructured":"plonkit. https:\/\/www.plonkit.net\/guide. Accessed 14 Nov 2023"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Arun, N., et al.: Assessing the trustworthiness of saliency maps for localizing abnormalities in medical imaging. Radiol. Artif. Intell. (2021)","DOI":"10.1101\/2020.07.28.20163899"},{"key":"22_CR6","unstructured":"Azizi, S., Kornblith, S., Saharia, C., Norouzi, M., Fleet, D.J.: Synthetic data from diffusion models improves imagenet classification. TMLR (2023)"},{"key":"22_CR7","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":"22_CR8","doi-asserted-by":"crossref","unstructured":"Chai, L., Zhu, J.Y., Shechtman, E., Isola, P., Zhang, R.: Ensembling with deep generative views. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01475"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Chen, E.M., Sun, J., Khandelwal, A., Lischinski, D., Snavely, N., Averbuch-Elor, H.: What\u2019s in a decade? Transforming faces through time. In: Computer Graphics Forum (2023)","DOI":"10.1111\/cgf.14761"},{"key":"22_CR10","unstructured":"Dalens, T., Aubry, M., Sivic, J.: Bilinear image translation for temporal analysis of photo collections. Trans. Pattern Anal. Mach. Intell. (2019)"},{"key":"22_CR11","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: NeurIPS (2021)"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Doersch, C., Singh, S., Gupta, A., Sivic, J., Efros, A.A.: What makes Paris look like Paris? Commun. ACM (2015)","DOI":"10.1145\/2830541"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Ginosar, S., et al.: A century of portraits: a visual historical record of American high school yearbooks. IEEE Trans. Comput. Imaging (2017)","DOI":"10.1109\/TCI.2017.2699865"},{"key":"22_CR14","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)"},{"key":"22_CR15","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"22_CR16","unstructured":"Ho, J., Saharia, C., Chan, W., Fleet, D.J., Norouzi, M., Salimans, T.: Cascaded diffusion models for high fidelity image generation. JMLR (2022)"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Jae\u00a0Lee, Y., Efros, A.A., Hebert, M.: Style-aware mid-level representation for discovering visual connections in space and time. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.233"},{"key":"22_CR18","unstructured":"Jahanian, A., Puig, X., Tian, Y., Isola, P.: Generative models as a data source for multiview representation learning. In: ICLR (2022)"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Kaoua, R., Shen, X., Durr, A., Lazaris, S., Picard, D., Aubry, M.: Image collation: matching illustrations in manuscripts. In: ICDAR (2021)","DOI":"10.1007\/978-3-030-86337-1_24"},{"key":"22_CR20","unstructured":"Karras, T., Aittala, M., Aila, T., Laine, S.: Elucidating the design space of diffusion-based generative models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 26565\u201326577 (2022)"},{"key":"22_CR21","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: ICLR (2014)"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Kotchemidova, C.: Why we say \u201ccheese\u201d: producing the smile in snapshot photography. Critical Stud. Media Commun. (2005)","DOI":"10.1080\/0739318042000331853"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Lee, S., Maisonneuve, N., Crandall, D., Efros, A., Sivic, J.: Linking past to present: discovering style in two centuries of architecture. In: IEEE International Conference on Computational Photography (ICCP) (2015)","DOI":"10.1109\/ICCPHOT.2015.7168368"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Lee, Y.J., Efros, A.A., Hebert, M.: Style-aware mid-level representation for discovering visual connections in space and time. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.233"},{"key":"22_CR25","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":"22_CR26","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: GLIGEN: open-set grounded text-to-image generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Lloyd, S.: Least squares quantization in PCM. IEEE Trans. Inf. Theory (1982)","DOI":"10.1109\/TIT.1982.1056489"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Luo, G., Biamby, G., Darrell, T., Fried, D., Rohrbach, A.: $$G^3$$: Geolocation via guidebook grounding. In: Findings of EMNLP (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.430"},{"key":"22_CR29","unstructured":"Luo, G., Dunlap, L., Park, D.H., Holynski, A., Darrell, T.: Diffusion hyperfeatures: searching through time and space for semantic correspondence. In: NeurIPS (2023)"},{"key":"22_CR30","unstructured":"Matzen, K., Bala, K., Snavely, N.: StreetStyle: exploring world-wide clothing styles from millions of photos. arXiv preprint arXiv:1706.01869 (2017)"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"McInnes, L., Healy, J., Saul, N., Grossberger, L.: Umap: uniform manifold approximation and projection. J. Open Source Softw. (2018)","DOI":"10.21105\/joss.00861"},{"key":"22_CR32","unstructured":"Meng, C., et al.: Sdedit: guided image synthesis and editing with stochastic differential equations. In: ICLR (2022)"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., Cohen-Or, D.: Null-text inversion for editing real images using guided diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"22_CR34","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"22_CR35","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":"22_CR36","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":"22_CR37","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":"22_CR38","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS (2022)"},{"key":"22_CR39","doi-asserted-by":"crossref","unstructured":"Shen, X., Efros, A.A., Aubry, M.: Discovering visual patterns in art collections with spatially-consistent feature learning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00950"},{"key":"22_CR40","doi-asserted-by":"crossref","unstructured":"Shen, X., Efros, A.A., Joulin, A., Aubry, M.: Learning co-segmentation by segment swapping for retrieval and discovery. In: CVPR Image Matching Workshop and Transformer Workshop, 2022 (2021)","DOI":"10.1109\/CVPRW56347.2022.00556"},{"key":"22_CR41","doi-asserted-by":"crossref","unstructured":"Shen, X., et al.: Large-scale historical watermark recognition: dataset and a new consistency-based approach. In: ICPR (2021)","DOI":"10.1109\/ICPR48806.2021.9412762"},{"key":"22_CR42","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML (2015)"},{"key":"22_CR43","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"22_CR44","unstructured":"Tang, L., Jia, M., Wang, Q., Phoo, C.P., Hariharan, B.: Emergent correspondence from image diffusion. In: NeurIPS (2023)"},{"key":"22_CR45","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":"22_CR46","doi-asserted-by":"crossref","unstructured":"Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., Summers, R.M.: Chestx-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.369"},{"key":"22_CR47","doi-asserted-by":"crossref","unstructured":"Xu, J., Liu, S., Vahdat, A., Byeon, W., Wang, X., De\u00a0Mello, S.: Open-vocabulary panoptic segmentation with text-to-image diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"22_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"22_CR49","doi-asserted-by":"crossref","unstructured":"Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: a 10 million image database for scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2017)","DOI":"10.1167\/17.10.296"}],"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\/978-3-031-73030-6_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T17:18:55Z","timestamp":1732555135000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73030-6_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,24]]},"ISBN":["9783031730290","9783031730306"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73030-6_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,24]]},"assertion":[{"value":"24 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"}}]}}