{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T06:45:57Z","timestamp":1785653157688,"version":"3.56.0"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032316653","type":"print"},{"value":"9783032316660","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-31666-0_3","type":"book-chapter","created":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:47:12Z","timestamp":1785649632000},"page":"33-48","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Revisiting Human-in-the-Loop Object Retrieval with Pre-trained Vision Transformers"],"prefix":"10.1007","author":[{"given":"Kawtar","family":"Zaher","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olivier","family":"Buisson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexis","family":"Joly","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,3]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Abdali, A., Gripon, V., Drumetz, L., Boguslawski, B.: Active learning for efficient few-shot classification. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095220"},{"key":"3_CR2","unstructured":"Aggarwal, U., Popescu, A., Hudelot, C.: Optimizing active learning for low annotation budgets (2022). arXiv:2201.07200"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: NetVLAD: CNN architecture for weakly supervised place recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5297\u20135307 (2016)","DOI":"10.1109\/CVPR.2016.572"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Arandjelovi\u0107, R., Zisserman, A.: Three things everyone should know to improve object retrieval. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2911\u20132918. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248018"},{"key":"3_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1007\/978-3-030-58565-5_43","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Cao","year":"2020","unstructured":"Cao, B., Araujo, A., Sim, J.: Unifying deep local and global features for image search. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 726\u2013743. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_43"},{"issue":"6","key":"3_CR6","doi-asserted-by":"publisher","first-page":"7270","DOI":"10.1109\/TPAMI.2022.3218591","volume":"45","author":"W Chen","year":"2022","unstructured":"Chen, W., et al.: Deep learning for instance retrieval: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 45(6), 7270\u20137292 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR7","unstructured":"Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: Workshop on Statistical Learning in Computer Vision, ECCV, vol. 1, pp. 1\u20132, Prague (2004)"},{"key":"3_CR8","unstructured":"Darcet, T., Oquab, M., Mairal, J., Bojanowski, P.: Vision transformers need registers (2023). arXiv:2309.16588"},{"issue":"5","key":"3_CR9","doi-asserted-by":"publisher","first-page":"2323","DOI":"10.1109\/TGRS.2014.2358804","volume":"53","author":"B Demir","year":"2014","unstructured":"Demir, B., Bruzzone, L.: A novel active learning method in relevance feedback for content-based remote sensing image retrieval. IEEE Trans. Geosci. Remote Sens. 53(5), 2323\u20132334 (2014)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"3_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2025.110640","volume":"196","author":"S Denner","year":"2025","unstructured":"Denner, S., et al.: Leveraging foundation models for content-based image retrieval in radiology. Comput. Biol. Med. 196, 110640 (2025)","journal-title":"Comput. Biol. Med."},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Deselaers, T., et\u00a0al.: Overview of the ImageCLEF 2007 object retrieval task. In: Advances in Multilingual and Multimodal Information Retrieval: 8th Workshop of the Cross-Language Evaluation Forum, CLEF 2007, Budapest, Hungary, September 19\u201321, 2007, Revised Selected Papers 8, pp. 445\u2013471. Springer (2008)","DOI":"10.1007\/978-3-540-85760-0_58"},{"key":"3_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 $$\\times $$ 16 words: transformers for image recognition at scale (2020). arXiv:2010.11929"},{"key":"3_CR13","unstructured":"El-Nouby, A., Neverova, N., Laptev, I., J\u00e9gou, H.: Training vision transformers for image retrieval (2021). arXiv:2102.05644"},{"key":"3_CR14","unstructured":"Everingham, M., Van\u00a0Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge 2012 (VOC2012) Results. http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2012\/workshop\/index.html"},{"issue":"4","key":"3_CR15","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1109\/TGRS.2007.892007","volume":"45","author":"M Ferecatu","year":"2007","unstructured":"Ferecatu, M., Boujemaa, N.: Interactive remote-sensing image retrieval using active relevance feedback. IEEE Trans. Geosci. Remote Sens. 45(4), 818\u2013826 (2007)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"3_CR16","doi-asserted-by":"publisher","unstructured":"Garg, K., Puligilla, S.S., Kolathaya, S., Krishna, M., Garg, S.: Revisit anything: Visual place recognition via image segment retrieval. In: European Conference on Computer Vision. pp. 326\u2013343. Springer (2024). https:\/\/doi.org\/10.1007\/978-3-031-73113-6_19","DOI":"10.1007\/978-3-031-73113-6_19"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Govindarajan, H., Lindskog, P., Lundstr\u00f6m, D., Olmin, A., Roll, J., Lindsten, F.: Self-supervised representation learning for content based image retrieval of complex scenes. In: 2021 IEEE Intelligent Vehicles Symposium Workshops (IV Workshops), pp. 249\u2013256. IEEE (2021)","DOI":"10.1109\/IVWorkshops54471.2021.9669246"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Douze, M., Schmid, C., P\u00e9rez, P.: Aggregating local descriptors into a compact image representation. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3304\u20133311. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"3_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Litayem, S., Joly, A., Boujemaa, N.: Interactive objects retrieval with efficient boosting. In: Proceedings of the 17th ACM International Conference on Multimedia, pp. 545\u2013548 (2009)","DOI":"10.1145\/1631272.1631352"},{"key":"3_CR21","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60, 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vision"},{"issue":"4","key":"3_CR22","doi-asserted-by":"publisher","first-page":"3005","DOI":"10.1007\/s10462-022-10246-w","volume":"56","author":"E Mosqueira-Rey","year":"2023","unstructured":"Mosqueira-Rey, E., Hern\u00e1ndez-Pereira, E., Alonso-R\u00edos, D., Bobes-Bascar\u00e1n, J., Fern\u00e1ndez-Leal, \u00c1.: Human-in-the-loop machine learning: a state of the art. Artif. Intell. Rev. 56(4), 3005\u20133054 (2023)","journal-title":"Artif. Intell. Rev."},{"issue":"6","key":"3_CR23","first-page":"3238","volume":"6","author":"GT Ngo","year":"2016","unstructured":"Ngo, G.T., Ngo, T.Q., Nguyen, D.D.: Image retrieval with relevance feedback using SVM active learning. Int. J. Electr. Comput. Eng. 6(6), 3238 (2016)","journal-title":"Int. J. Electr. Comput. Eng."},{"key":"3_CR24","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision (2023). arXiv:2304.07193"},{"key":"3_CR25","unstructured":"O\u2019shea, K., Nash, R.: An introduction to convolutional neural networks (2015). arXiv:1511.08458"},{"key":"3_CR26","unstructured":"Patil, P.B., Kokare, M.B.: Relevance feedback in content based image retrieval: a review. J. Appl. Comput. Sci. Math. (10) (2011)"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Perronnin, F., Dance, C.: Fisher kernels on visual vocabularies for image categorization. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138. IEEE (2007)","DOI":"10.1109\/CVPR.2007.383266"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Razavian, A.S., Azizpour, H., Sullivan, J., Carlsson, S.: CNN features off-the-shelf: an astounding baseline for recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 806\u2013813 (2014)","DOI":"10.1109\/CVPRW.2014.131"},{"key":"3_CR29","unstructured":"Settles, B.: Active learning literature survey (2009)"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Shao, S., Chen, K., Karpur, A., Cui, Q., Araujo, A., Cao, B.: Global features are all you need for image retrieval and reranking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11036\u201311046 (2023)","DOI":"10.1109\/ICCV51070.2023.01013"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Song, C.H., Yoon, J., Choi, S., Avrithis, Y.: Boosting vision transformers for image retrieval. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 107\u2013117 (2023)","DOI":"10.1109\/WACV56688.2023.00019"},{"key":"3_CR32","unstructured":"Song, Y., Zhu, R., Yang, M., He, D.: DALG: deep attentive local and global modeling for image retrieval (2022). arXiv:2207.00287"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Tan, F., Yuan, J., Ordonez, V.: Instance-level image retrieval using reranking transformers. In: proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12105\u201312115 (2021)","DOI":"10.1109\/ICCV48922.2021.01189"},{"key":"3_CR34","unstructured":"Tolias, G., Sicre, R., J\u00e9gou, H.: Particular object retrieval with integral max-pooling of CNN activations (2015). arXiv:1511.05879"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Tong, S., Chang, E.: Support vector machine active learning for image retrieval. In: Proceedings of the Ninth ACM International Conference on Multimedia, pp. 107\u2013118 (2001)","DOI":"10.1145\/500141.500159"},{"issue":"3","key":"3_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3386252","volume":"53","author":"Y Wang","year":"2020","unstructured":"Wang, Y., Yao, Q., Kwok, J.T., Ni, L.M.: Generalizing from a few examples: a survey on few-shot learning. ACM Comput. Surv. (CSUR) 53(3), 1\u201334 (2020)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"Yang, M., et al.: DOLG: single-stage image retrieval with deep orthogonal fusion of local and global features. In: Proceedings of the IEEE\/CVF International conference on Computer Vision, pp. 11772\u201311781 (2021)","DOI":"10.1109\/ICCV48922.2021.01156"},{"key":"3_CR38","unstructured":"Zaher, K., Buisson, O., Joly, A.: Positive-first most ambiguous: a simple active learning criterion for interactive retrieval of rare categories. In: CVPRW 2026 - The 13th Workshop on Fine-Grained Visual Categorization (FGVC13) (2026)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31666-0_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:47:15Z","timestamp":1785649635000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31666-0_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,3]]},"ISBN":["9783032316653","9783032316660"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31666-0_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,3]]},"assertion":[{"value":"3 August 2026","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":"Lyon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}