{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T08:20:43Z","timestamp":1782548443644,"version":"3.54.5"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031923869","type":"print"},{"value":"9783031923876","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-92387-6_3","type":"book-chapter","created":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T18:42:27Z","timestamp":1748198547000},"page":"37-53","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Towards Zero-Shot Camera Trap Image Categorization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6443-2051","authenticated-orcid":false,"given":"Ji\u0159\u00ed","family":"Vysko\u010dil","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6041-9722","authenticated-orcid":false,"given":"Lukas","family":"Picek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"issue":"1","key":"3_CR1","doi-asserted-by":"publisher","first-page":"juy002","DOI":"10.1093\/jue\/juy002","volume":"4","author":"V Anton","year":"2018","unstructured":"Anton, V., Hartley, S., Geldenhuis, A., Wittmer, H.U.: Monitoring the mammalian fauna of urban areas using remote cameras and citizen science. J. Urban Ecol. 4(1), juy002 (2018)","journal-title":"J. Urban Ecol."},{"key":"3_CR2","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: BEiT: BERT pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Beery, S., Van\u00a0Horn, G., Perona, P.: Recognition in terra incognita. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 456\u2013473 (2018)","DOI":"10.1007\/978-3-030-01270-0_28"},{"key":"3_CR4","doi-asserted-by":"publisher","first-page":"108984","DOI":"10.1016\/j.biocon.2021.108984","volume":"256","author":"JD Blount","year":"2021","unstructured":"Blount, J.D., Chynoweth, M.W., Green, A.M., \u015eekercio\u011flu, \u00c7.H.: COVID-19 highlights the importance of camera traps for wildlife conservation research and management. Biol. Cons. 256, 108984 (2021)","journal-title":"Biol. Cons."},{"key":"3_CR5","unstructured":"Cai, H., Gan, C., Han, S.: EfficientViT: enhanced linear attention for high-resolution low-computation visual recognition. arXiv preprint arXiv:2205.14756 (2022)"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: RandAugment: practical automated data augmentation with a reduced search space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 702\u2013703 (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"3_CR7","doi-asserted-by":"publisher","first-page":"102060","DOI":"10.1016\/j.ecoinf.2023.102060","volume":"76","author":"F Cunha","year":"2023","unstructured":"Cunha, F., dos Santos, E.M., Colonna, J.G.: Bag of tricks for long-tail visual recognition of animal species in camera-trap images. Eco. Inform. 76, 102060 (2023)","journal-title":"Eco. Inform."},{"key":"3_CR8","unstructured":"Darcet, T., Oquab, M., Mairal, J., Bojanowski, P.: Vision transformers need registers. arXiv preprint arXiv:2309.16588 (2023)"},{"key":"3_CR9","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"3_CR10","unstructured":"Douze, M., et al.: The Faiss library. arXiv preprint arXiv:2401.08281 (2024)"},{"issue":"6","key":"3_CR11","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1016\/j.ecoinf.2011.06.003","volume":"6","author":"EH Fegraus","year":"2011","unstructured":"Fegraus, E.H., Lin, K., Ahumada, J.A., Baru, C., Chandra, S., Youn, C.: Data acquisition and management software for camera trap data: a case study from the team network. Eco. Inform. 6(6), 345\u2013353 (2011)","journal-title":"Eco. Inform."},{"issue":"3","key":"3_CR12","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1890\/0012-9623-91.3.352","volume":"91","author":"G Harris","year":"2010","unstructured":"Harris, G., Thompson, R., Childs, J.L., Sanderson, J.G.: Automatic storage and analysis of camera trap data. Bull. Ecol. Soc. Am. 91(3), 352\u2013360 (2010)","journal-title":"Bull. Ecol. Soc. Am."},{"issue":"2","key":"3_CR13","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1002\/rse2.362","volume":"10","author":"M Henrich","year":"2024","unstructured":"Henrich, M., et al.: A semi-automated camera trap distance sampling approach for population density estimation. Remote Sens. Ecol. Conserv. 10(2), 156\u2013171 (2024)","journal-title":"Remote Sens. Ecol. Conserv."},{"issue":"3","key":"3_CR14","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","volume":"7","author":"J Johnson","year":"2019","unstructured":"Johnson, J., Douze, M., J\u00e9gou, H.: Billion-scale similarity search with GPUs. IEEE Trans. Big Data 7(3), 535\u2013547 (2019)","journal-title":"IEEE Trans. Big Data"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"3_CR16","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., et\u00a0al.: Swin transformer V2: scaling up capacity and resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12009\u201312019 (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"issue":"1","key":"3_CR20","doi-asserted-by":"publisher","first-page":"8137","DOI":"10.1038\/s41598-019-44565-w","volume":"9","author":"Z Miao","year":"2019","unstructured":"Miao, Z., et al.: Insights and approaches using deep learning to classify wildlife. Sci. Rep. 9(1), 8137 (2019)","journal-title":"Sci. Rep."},{"key":"3_CR21","unstructured":"Microsoft: PyTorch-wildlife: a collaborative deep learning framework for conservation (2023). https:\/\/github.com\/microsoft\/CameraTraps\/blob\/main\/megadetector.md"},{"issue":"1","key":"3_CR22","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1111\/2041-210X.13504","volume":"12","author":"MS Norouzzadeh","year":"2021","unstructured":"Norouzzadeh, M.S., Morris, D., Beery, S., Joshi, N., Jojic, N., Clune, J.: A deep active learning system for species identification and counting in camera trap images. Methods Ecol. Evol. 12(1), 150\u2013161 (2021)","journal-title":"Methods Ecol. Evol."},{"issue":"25","key":"3_CR23","doi-asserted-by":"publisher","first-page":"E5716","DOI":"10.1073\/pnas.1719367115","volume":"115","author":"MS Norouzzadeh","year":"2018","unstructured":"Norouzzadeh, M.S., et al.: Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning. Proc. Natl. Acad. Sci. 115(25), E5716\u2013E5725 (2018)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"O\u2019Connell, A.F., Nichols, J.D., Karanth, K.U.: Camera Traps in Animal Ecology: Methods and Analyses, vol.\u00a0271. Springer (2011)","DOI":"10.1007\/978-4-431-99495-4"},{"key":"3_CR25","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"issue":"1\u20132","key":"3_CR26","first-page":"1","volume":"117","author":"LE Pardo","year":"2021","unstructured":"Pardo, L.E., et al.: Snapshot safari: a large-scale collaborative to monitor Africa\u2019s remarkable biodiversity. S. Afr. J. Sci. 117(1\u20132), 1\u20134 (2021)","journal-title":"S. Afr. J. Sci."},{"key":"3_CR27","unstructured":"Peng, Z., Dong, L., Bao, H., Ye, Q., Wei, F.: BEiT v2: masked image modeling with vector-quantized visual tokenizers. arXiv preprint arXiv:2208.06366 (2022)"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Picek, L., et al.: Danish fungi 2020-not just another image recognition dataset. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1525\u20131535 (2022)","DOI":"10.1109\/WACV51458.2022.00334"},{"key":"3_CR29","doi-asserted-by":"publisher","first-page":"787527","DOI":"10.3389\/fpls.2022.787527","volume":"13","author":"L Picek","year":"2022","unstructured":"Picek, L., \u0160ulc, M., Patel, Y., Matas, J.: Plant recognition by AI: deep neural nets, transformers, and kNN in deep embeddings. Front. Plant Sci. 13, 787527 (2022)","journal-title":"Front. Plant Sci."},{"issue":"1","key":"3_CR30","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/S0893-6080(98)00116-6","volume":"12","author":"N Qian","year":"1999","unstructured":"Qian, N.: On the momentum term in gradient descent learning algorithms. Neural Netw. 12(1), 145\u2013151 (1999)","journal-title":"Neural Netw."},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Rowcliffe, J.M., Field, J., Turvey, S.T., Carbone, C.: Estimating animal density using camera traps without the need for individual recognition. J. Appl. Ecol., 1228\u20131236 (2008)","DOI":"10.1111\/j.1365-2664.2008.01473.x"},{"key":"3_CR32","unstructured":"Ruu3f: FreeGPT (2023). https:\/\/github.com\/Ruu3f\/freeGPT"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Schneider, D., Bellafkir, K.L.M.V.H., Farwig, M.M.N., Freisleben, B.: Recognizing European mammals and birds in camera trap images using convolutional neural networks (2023)","DOI":"10.1049\/cvi2.12294"},{"issue":"9","key":"3_CR34","doi-asserted-by":"publisher","first-page":"4494","DOI":"10.1002\/ece3.7344","volume":"11","author":"A Shepley","year":"2021","unstructured":"Shepley, A., Falzon, G., Meek, P., Kwan, P.: Automated location invariant animal detection in camera trap images using publicly available data sources. Ecol. Evol. 11(9), 4494\u20134506 (2021)","journal-title":"Ecol. Evol."},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Stevens, S., et\u00a0al.: BioCLIP: a vision foundation model for the tree of life. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19412\u201319424 (2024)","DOI":"10.1109\/CVPR52733.2024.01836"},{"issue":"1","key":"3_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2015.26","volume":"2","author":"A Swanson","year":"2015","unstructured":"Swanson, A., Kosmala, M., Lintott, C., Simpson, R., Smith, A., Packer, C.: Snapshot Serengeti, high-frequency annotated camera trap images of 40 mammalian species in an African savanna. Sci. data 2(1), 1\u201314 (2015)","journal-title":"Sci. data"},{"key":"3_CR37","unstructured":"Valan, M., Picek, L.: Mastering large scale multi-label image recognition with high efficiency overcamera trap images. arXiv preprint arXiv:2008.07828 (2020)"},{"issue":"3","key":"3_CR38","doi-asserted-by":"publisher","first-page":"900","DOI":"10.1093\/icb\/icab107","volume":"61","author":"M Vidal","year":"2021","unstructured":"Vidal, M., Wolf, N., Rosenberg, B., Harris, B.P., Mathis, A.: Perspectives on individual animal identification from biology and computer vision. Integr. Comp. Biol. 61(3), 900\u2013916 (2021)","journal-title":"Integr. Comp. Biol."},{"key":"3_CR39","doi-asserted-by":"publisher","unstructured":"Wightman, R.: PyTorch image models (2019). https:\/\/doi.org\/10.5281\/zenodo.4414861","DOI":"10.5281\/zenodo.4414861"},{"issue":"1","key":"3_CR40","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1111\/2041-210X.13099","volume":"10","author":"M Willi","year":"2019","unstructured":"Willi, M., et al.: Identifying animal species in camera trap images using deep learning and citizen science. Methods Ecol. Evol. 10(1), 80\u201391 (2019)","journal-title":"Methods Ecol. Evol."},{"key":"3_CR41","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"issue":"1","key":"3_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1687-5281-2013-52","volume":"2013","author":"X Yu","year":"2013","unstructured":"Yu, X., Wang, J., Kays, R., Jansen, P.A., Wang, T., Huang, T.: Automated identification of animal species in camera trap images. EURASIP J. Image Video Process. 2013(1), 1\u201310 (2013). https:\/\/doi.org\/10.1186\/1687-5281-2013-52","journal-title":"EURASIP J. Image Video Process."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-92387-6_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T18:42:33Z","timestamp":1748198553000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-92387-6_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031923869","9783031923876"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-92387-6_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}