{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:01:34Z","timestamp":1786978894232,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":63,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031731945","type":"print"},{"value":"9783031731952","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"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\/978-3-031-73195-2_25","type":"book-chapter","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T04:38:32Z","timestamp":1732595912000},"page":"430-448","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["When Pedestrian Detection Meets Multi-modal Learning: Generalist Model and\u00a0Benchmark Dataset"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7303-7594","authenticated-orcid":false,"given":"Yi","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1562-6332","authenticated-orcid":false,"given":"Wang","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5736-7434","authenticated-orcid":false,"given":"Sheng","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8761-5563","authenticated-orcid":false,"given":"Chen","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6685-7950","authenticated-orcid":false,"given":"Ping","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6587-9878","authenticated-orcid":false,"given":"Wentao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Boretti, C., Bich, P., Pareschi, F., Prono, L., Rovatti, R., Setti, G.: Pedro: an event-based dataset for person detection in robotics. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop (2023)","DOI":"10.1109\/CVPRW59228.2023.00426"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Broedermann, T., Sakaridis, C., Dai, D., Van Gool, L.: Hrfuser: a multi-resolution sensor fusion architecture for 2d object detection. In: IEEE Conference on Intelligent Transportation System (2023)","DOI":"10.1109\/ITSC57777.2023.10422432"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Cao, Y., Bin, J., Hamari, J., Blasch, E., Liu, Z.: Multimodal object detection by channel switching and spatial attention. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop, pp. 403\u2013411 (2023)","DOI":"10.1109\/CVPRW59228.2023.00046"},{"key":"25_CR4","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":"25_CR5","unstructured":"Chen, K., et\u00a0al.: Mmdetection: open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"key":"25_CR6","doi-asserted-by":"publisher","unstructured":"Chen, Y.T., Shi, J., Ye, Z., Mertz, C., Ramanan, D., Kong, S.: Multimodal object detection via probabilistic ensembling. In: European Conference on Computer Vision, pp. 139\u2013158. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_9","DOI":"10.1007\/978-3-031-20077-9_9"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Chu, X., Zheng, A., Zhang, X., Sun, J.: Detection in crowded scenes: one proposal, multiple predictions. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop, pp. 12214\u201312223 (2020)","DOI":"10.1109\/CVPR42600.2020.01223"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Ci, Y., et al.: Unihcp: a unified model for human-centric perceptions. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop, pp. 17840\u201317852 (2023)","DOI":"10.1109\/CVPR52729.2023.01711"},{"key":"25_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.margen.2019.100723","volume":"51","author":"MC Cieslak","year":"2020","unstructured":"Cieslak, M.C., Castelfranco, A.M., Roncalli, V., Lenz, P.H., Hartline, D.K.: t-distributed stochastic neighbor embedding (t-sne): a tool for eco-physiological transcriptomic analysis. Mar. Genomics 51, 100723 (2020)","journal-title":"Mar. Genomics"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Cong, P., et al.: Stcrowd: a multimodal dataset for pedestrian perception in crowded scenes. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop, pp. 19608\u201319617 (2022)","DOI":"10.1109\/CVPR52688.2022.01899"},{"key":"25_CR11","unstructured":"De\u00a0Tournemire, P., Nitti, D., Perot, E., Migliore, D., Sironi, A.: A large scale event-based detection dataset for automotive. arXiv preprint arXiv:2001.08499 (2020)"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: a benchmark. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 304\u2013311. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206631"},{"issue":"4","key":"25_CR13","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1109\/TPAMI.2011.155","volume":"34","author":"P Dollar","year":"2011","unstructured":"Dollar, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: an evaluation of the state of the art. IEEE Trans. Pattern Anal. Mach. Intell. 34(4), 743\u2013761 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR14","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representation (2021)"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Finateu, T., et\u00a0al.: 5.10 a 1280x720 back-illuminated stacked temporal contrast event-based vision sensor with 4.86 um pixels, 1.066 geps readout, programmable event-rate controller and compressive data-formatting pipeline. In: IEEE International Solid-State Circuits Conference, pp. 112\u2013114 (2020)","DOI":"10.1109\/ISSCC19947.2020.9063149"},{"key":"25_CR16","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"issue":"3","key":"25_CR17","doi-asserted-by":"publisher","first-page":"4947","DOI":"10.1109\/LRA.2021.3068942","volume":"6","author":"M Gehrig","year":"2021","unstructured":"Gehrig, M., Aarents, W., Gehrig, D., Scaramuzza, D.: Dsec: a stereo event camera dataset for driving scenarios. IEEE Robot. Autom. Lett. 6(3), 4947\u20134954 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Girdhar, R., et al.: Imagebind: one embedding space to bind them all. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 15180\u201315190 (2023)","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"25_CR19","unstructured":"Imaging, T.: Flir data set dataset (2023). https:\/\/universe.roboflow.com\/thermal-imaging-0hwfw\/flir-data-set"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Jia, X., Zhu, C., Li, M., Tang, W., Zhou, W.: Llvip: a visible-infrared paired dataset for low-light vision. In: International Conference on Computer Vision, pp. 3496\u20133504 (2021)","DOI":"10.1109\/ICCVW54120.2021.00389"},{"key":"25_CR21","doi-asserted-by":"publisher","unstructured":"Jin, S., et al.: You only learn one query: learning unified human query for single-stage multi-person multi-task human-centric perception. In: European Conference on Computer Vision. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-72649-1_8","DOI":"10.1007\/978-3-031-72649-1_8"},{"key":"25_CR22","doi-asserted-by":"publisher","unstructured":"Jin, S., et al.: Whole-body human pose estimation in the wild. In: European Conference on Computer Vision, pp. 196\u2013214. Springer, Heidelberg (2020). https:\/\/doi.org\/10.1007\/978-3-031-72649-1_8","DOI":"10.1007\/978-3-031-72649-1_8"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Jin, S., et al.: Unifs: universal few-shot instance perception with point representations. In: European Conference on Computer Vision (2024)","DOI":"10.1007\/978-3-031-73397-0_27"},{"key":"25_CR24","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: Yolo by ultralytics (2023). https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"25_CR25","unstructured":"Li, C., Song, D., Tong, R., Tang, M.: Multispectral pedestrian detection via simultaneous detection and segmentation. In: British Machine on Vision Conference (2018)"},{"key":"25_CR26","first-page":"21002","volume":"33","author":"X Li","year":"2020","unstructured":"Li, X., et al.: Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection. Adv. Neural Inform. Process. Syst. 33, 21002\u201321012 (2020)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"25_CR27","doi-asserted-by":"publisher","first-page":"6893","DOI":"10.1109\/TIP.2022.3216771","volume":"31","author":"T Liang","year":"2022","unstructured":"Liang, T., et al.: Cbnet: a composite backbone network architecture for object detection. IEEE Trans. Image Process. 31, 6893\u20136906 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"25_CR28","unstructured":"Lin, M., et al.: Detr for crowd pedestrian detection. arXiv preprint arXiv:2012.06785 (2020)"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"25_CR30","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":"25_CR31","doi-asserted-by":"crossref","unstructured":"Liu, J., Zhang, S., Wang, S., Metaxas, D.N.: Multispectral deep neural networks for pedestrian detection. In: British Machine on Vision Conference (2016)","DOI":"10.5244\/C.30.73"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Target-aware dual adversarial learning and a multi-scenario multi-modality benchmark to fuse infrared and visible for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5802\u20135811 (2022)","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"25_CR34","doi-asserted-by":"crossref","unstructured":"Mees, O., Eitel, A., Burgard, W.: Choosing smartly: adaptive multimodal fusion for object detection in changing environments. In: IEEE International Conference on Intelligent Robots Systems, pp. 151\u2013156 (2016)","DOI":"10.1109\/IROS.2016.7759048"},{"key":"25_CR35","first-page":"16639","volume":"33","author":"E Perot","year":"2020","unstructured":"Perot, E., De Tournemire, P., Nitti, D., Masci, J., Sironi, A.: Learning to detect objects with a 1 megapixel event camera. Adv. Neural Inf. Process. Syst. 33, 16639\u201316652 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"25_CR36","unstructured":"Qingyun, F., Dapeng, H., Zhaokui, W.: Cross-modality fusion transformer for multispectral object detection. arXiv preprint arXiv:2111.00273 (2021)"},{"key":"25_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108786","volume":"130","author":"F Qingyun","year":"2022","unstructured":"Qingyun, F., Zhaokui, W.: Cross-modality attentive feature fusion for object detection in multispectral remote sensing imagery. Pattern Recogn. 130, 108786 (2022)","journal-title":"Pattern Recogn."},{"key":"25_CR38","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"25_CR39","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"25_CR40","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"25_CR41","doi-asserted-by":"crossref","unstructured":"Shao, S., et al.: Objects365: a large-scale, high-quality dataset for object detection. In: International Conference on Computer Vision, pp. 8430\u20138439 (2019)","DOI":"10.1109\/ICCV.2019.00852"},{"key":"25_CR42","unstructured":"Shao, S., et al.: Crowdhuman: a benchmark for detecting human in a crowd. arXiv preprint arXiv:1805.00123 (2018)"},{"key":"25_CR43","unstructured":"Sun, P., et\u00a0al.: Scalability in perception for autonomous driving: waymo open dataset. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2446\u20132454 (2020)"},{"key":"25_CR44","doi-asserted-by":"crossref","unstructured":"Sun, P., et\u00a0al.: Sparse r-cnn: end-to-end object detection with learnable proposals. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 14454\u201314463 (2021)","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"25_CR45","doi-asserted-by":"crossref","unstructured":"Takumi, K., Watanabe, K., Ha, Q., Tejero-De-Pablos, A., Ushiku, Y., Harada, T.: Multispectral object detection for autonomous vehicles. In: Proceedings of the Thematic Workshops of ACM Multimedia, pp. 35\u201343 (2017)","DOI":"10.1145\/3126686.3126727"},{"key":"25_CR46","doi-asserted-by":"crossref","unstructured":"Tang, S., et\u00a0al.: Humanbench: towards general human-centric perception with projector assisted pretraining. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 21970\u201321982 (2023)","DOI":"10.1109\/CVPR52729.2023.02104"},{"key":"25_CR47","doi-asserted-by":"crossref","unstructured":"Tomy, A., Paigwar, A., Mann, K.S., Renzaglia, A., Laugier, C.: Fusing event-based and rgb camera for robust object detection in adverse conditions. In: IEEE International Conference on Robotics Automation, pp. 933\u2013939. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9812059"},{"key":"25_CR48","doi-asserted-by":"crossref","unstructured":"Vasquez, A., Kollmitz, M., Eitel, A., Burgard, W.: Deep detection of people and their mobility aids for a hospital robot. In: European Conference on Mobile Robots (ECMR), pp.\u00a01\u20137. IEEE (2017)","DOI":"10.1109\/ECMR.2017.8098665"},{"key":"25_CR49","doi-asserted-by":"crossref","unstructured":"Wang, W., et\u00a0al.: Internimage: exploring large-scale vision foundation models with deformable convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 14408\u201314419 (2023)","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"25_CR50","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"25_CR51","doi-asserted-by":"crossref","unstructured":"Yao, T., Li, Y., Pan, Y., Wang, Y., Zhang, X.P., Mei, T.: Dual vision transformer. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3268446"},{"key":"25_CR52","doi-asserted-by":"crossref","unstructured":"Zeng, W., et al.: Not all tokens are equal: human-centric visual analysis via token clustering transformer. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 11101\u201311111 (2022)","DOI":"10.1109\/CVPR52688.2022.01082"},{"key":"25_CR53","unstructured":"Zhang, H., et al.: Dino: detr with improved denoising anchor boxes for end-to-end object detection. In: International Conference on Learning Representation (2023)"},{"key":"25_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, H., Fromont, E., Lefevre, S., Avignon, B.: Multispectral fusion for object detection with cyclic fuse-and-refine blocks. In: IEEE International Conference on Image Processing, pp. 276\u2013280. IEEE (2020)","DOI":"10.1109\/ICIP40778.2020.9191080"},{"key":"25_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, H., Fromont, E., Lef\u00e8vre, S., Avignon, B.: Guided attentive feature fusion for multispectral pedestrian detection. In: IEEE Winter Conference on Application of Computer Vision, pp. 72\u201380 (2021)","DOI":"10.1109\/WACV48630.2021.00012"},{"key":"25_CR56","volume-title":"Cmx: Cross-modal fusion for rgb-x semantic segmentation with transformers","author":"J Zhang","year":"2023","unstructured":"Zhang, J., Liu, H., Yang, K., Hu, X., Liu, R., Stiefelhagen, R.: Cmx: Cross-modal fusion for rgb-x semantic segmentation with transformers. IEEE Trans. Intell. Transp, Syst (2023)"},{"key":"25_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Delivering arbitrary-modal semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1136\u20131147 (2023)","DOI":"10.1109\/CVPR52729.2023.00116"},{"key":"25_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, S., Benenson, R., Schiele, B.: Citypersons: a diverse dataset for pedestrian detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133221 (2017)","DOI":"10.1109\/CVPR.2017.474"},{"key":"25_CR59","unstructured":"Zhang, Y., et al.: Meta-transformer: a unified framework for multimodal learning. arXiv preprint arXiv:2307.10802 (2023)"},{"key":"25_CR60","doi-asserted-by":"crossref","unstructured":"Zheng, A., Zhang, Y., Zhang, X., Qi, X., Sun, J.: Progressive end-to-end object detection in crowded scenes. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 857\u2013866 (2022)","DOI":"10.1109\/CVPR52688.2022.00093"},{"key":"25_CR61","unstructured":"Zhu, B., et al.: Languagebind: extending video-language pretraining to n-modality by language-based semantic alignment. In: International Conference on Learning Representation (2024)"},{"key":"25_CR62","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. In: International Conference on Learning Representation (2020)"},{"key":"25_CR63","doi-asserted-by":"crossref","unstructured":"Zong, Z., Song, G., Liu, Y.: Detrs with collaborative hybrid assignments training. In: International Conference on Computer Vision, pp. 6748\u20136758 (2023)","DOI":"10.1109\/ICCV51070.2023.00621"}],"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\/978-3-031-73195-2_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T05:14:38Z","timestamp":1732598078000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73195-2_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,27]]},"ISBN":["9783031731945","9783031731952"],"references-count":63,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73195-2_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,27]]},"assertion":[{"value":"27 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"}}]}}