{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:50:41Z","timestamp":1767315041938,"version":"3.48.0"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032101846","type":"print"},{"value":"9783032101853","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-10185-3_17","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:48:33Z","timestamp":1767314913000},"page":"207-219","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Depth and\u00a0Event-Based Approaches for\u00a0Human Detection and\u00a0Pose Estimation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1107-0069","authenticated-orcid":false,"given":"Hao","family":"Quan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1829-1793","authenticated-orcid":false,"given":"Milad","family":"Goudarzi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4984-7432","authenticated-orcid":false,"given":"Chiara","family":"Plizzari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7059-413X","authenticated-orcid":false,"given":"Simone","family":"Mentasti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1862-4853","authenticated-orcid":false,"given":"Francesca","family":"Palermo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8935-5593","authenticated-orcid":false,"given":"Diana","family":"Trojaniello","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8306-6739","authenticated-orcid":false,"given":"Matteo","family":"Matteucci","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"17_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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4065\u20134070 (2023)","DOI":"10.1109\/CVPRW59228.2023.00426"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, B., Xiao, B., Wang, J., Shi, H., Huang, T.S., Zhang, L.: HigherHRNet: scale-aware representation learning for bottom-up human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5386\u20135395 (2020)","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"17_CR5","first-page":"3965","volume":"34","author":"Z Dai","year":"2021","unstructured":"Dai, Z., Liu, H., Le, Q.V., Tan, M.: CoAtNet: marrying convolution and attention for all data sizes. Adv. Neural. Inf. Process. Syst. 34, 3965\u20133977 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"1","key":"17_CR6","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1109\/TPAMI.2020.3008413","volume":"44","author":"G Gallego","year":"2020","unstructured":"Gallego, G., et al.: Event-based vision: a survey. TPAMI 44(1), 154\u2013180 (2020)","journal-title":"TPAMI"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: CVPR, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Kim, J., Bae, J., Park, G., Zhang, D., Kim, Y.M.: N-ImageNet: towards robust, fine-grained object recognition with event cameras. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2146\u20132156 (2021)","DOI":"10.1109\/ICCV48922.2021.00215"},{"key":"17_CR10","unstructured":"Li, C., et\u00a0al.: YOLOv6: a single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976 (2022)"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: ECCV, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"17_CR12","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Mai, C., et al.: DBCG-Net: dual branch calibration guided deep network for UAV images semantic segmentation. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. (2024)","DOI":"10.1109\/JSTARS.2024.3378695"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Maji, D., Nagori, S., Mathew, M., Poddar, D.: YOLO-Pose: enhancing yolo for multi person pose estimation using object keypoint similarity loss. In: CVPR, pp. 2637\u20132646 (2022)","DOI":"10.1109\/CVPRW56347.2022.00297"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Maqueda, A.I., Loquercio, A., Gallego, G., Garc\u00eda, N., Scaramuzza, D.: Event-based vision meets deep learning on steering prediction for self-driving cars. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5419\u20135427 (2018)","DOI":"10.1109\/CVPR.2018.00568"},{"key":"17_CR16","unstructured":"Microsoft: COCO keypoint detection challenge. https:\/\/cocodataset.org\/#keypoints-2020 (2020). Accessed 20 Jan 2025"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Neubeck, A., Van\u00a0Gool, L.: Efficient non-maximum suppression. In: 18th International Conference on Pattern Recognition (ICPR\u201906), vol.\u00a03, pp. 850\u2013855. IEEE (2006)","DOI":"10.1109\/ICPR.2006.479"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Palermo, F., et\u00a0al.: Advancements in context recognition for edge devices and smart eyewear: sensors and applications. IEEE Access (2025)","DOI":"10.1109\/ACCESS.2025.3555426"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Pan, J., et al.: MSFA-Net: multiple spatial-channel feature aggregation network for change detection and a UAV-CD dataset. In: IGARSS, pp. 10328\u201310332. IEEE (2024)","DOI":"10.1109\/IGARSS53475.2024.10640969"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Pham, H., Dai, Z., Xie, Q., Le, Q.V.: Meta pseudo labels. In: CVPR, pp. 11557\u201311568 (2021)","DOI":"10.1109\/CVPR46437.2021.01139"},{"key":"17_CR21","unstructured":"Prophesee: https:\/\/www.prophesee.ai\/ (2024)"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Redmon, J.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.91"},{"issue":"6","key":"17_CR23","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Stat., 400\u2013407 (1951)","DOI":"10.1214\/aoms\/1177729586"},{"key":"17_CR25","unstructured":"Smith, L.N.: A disciplined approach to neural network hyper-parameters: Part 1\u2013learning rate, batch size, momentum, and weight decay. arXiv preprint arXiv:1803.09820 (2018)"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Song, Z., et al.: Robustness-aware 3D object detection in autonomous driving: a review and outlook. TPAMI (2024)","DOI":"10.1109\/TITS.2024.3439557"},{"key":"17_CR27","unstructured":"Ultralytics: YOLO. https:\/\/www.ultralytics.com\/ (2025). Accessed 12 Jan 2025"},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Verma, A.A., Chakravarthi, B., Vaghela, A., Wei, H., Yang, Y.: eTraM: event-based traffic monitoring dataset. In: CVPR, pp. 22637\u201322646 (2024)","DOI":"10.1109\/CVPR52733.2024.02136"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Xian, T., et al.: A scale-temporal interaction network for remote sensing image change detection and a UAV-CD dataset. In: IGARSS, pp. 8603\u20138607. IEEE (2024)","DOI":"10.1109\/IGARSS53475.2024.10641915"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: unleashing the power of large-scale unlabeled data. In: CVPR, pp. 10371\u201310381 (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"17_CR31","doi-asserted-by":"crossref","unstructured":"Ying, Z., et al.: Large-scale high-altitude UAV-based vehicle detection via pyramid dual pooling attention path aggregation network. IEEE Trans. Intell. Transp. Syst. (2024)","DOI":"10.1109\/TITS.2024.3396915"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"Yu, N., et al.: Adaptive vision transformer for event-based human pose estimation. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 2833\u20132841 (2024)","DOI":"10.1145\/3664647.3681401"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Zhai, X., Kolesnikov, A., Houlsby, N., Beyer, L.: Scaling vision transformers. arXiv preprint arXiv:2106.04560 (2021)","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, S., Wen, L., Bian, X., Lei, Z., Li, S.Z.: Single-shot refinement neural network for object detection. In: CVPR, pp. 4203\u20134212 (2018)","DOI":"10.1109\/CVPR.2018.00442"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zeng, W., Jin, S., Qian, C., Luo, P., Liu, W.: When pedestrian detection meets multi-modal learning: Generalist model and benchmark dataset. In: ECCV, pp. 430\u2013448. Springer (2025)","DOI":"10.1007\/978-3-031-73195-2_25"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Zou, S., et al.: EventHPE: event-based 3D human pose and shape estimation. In: CVPR, pp. 10996\u201311005 (2021)","DOI":"10.1109\/ICCV48922.2021.01081"}],"container-title":["Lecture Notes in Computer Science","Image Analysis and Processing \u2013 ICIAP 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-10185-3_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:48:37Z","timestamp":1767314917000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-10185-3_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032101846","9783032101853"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-10185-3_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image Analysis and Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rome","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iciap2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iciap.org\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}