{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T15:59:30Z","timestamp":1773417570395,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":45,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819626403","type":"print"},{"value":"9789819626410","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\/978-981-96-2641-0_5","type":"book-chapter","created":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:55:40Z","timestamp":1743382540000},"page":"69-86","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Leveraging Thermal Imaging for\u00a0Robust Human Pose Estimation in\u00a0Low-Light Vision"],"prefix":"10.1007","author":[{"given":"Mickael","family":"Cormier","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Caleb Ng Zhi","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Specker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benjamin","family":"Bla\u00df","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Heizmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J\u00fcrgen","family":"Beyerer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,29]]},"reference":[{"key":"5_CR1","doi-asserted-by":"publisher","unstructured":"Alam, E., Sufian, A., Dutta, P., Leo, M.: Real-time human fall detection using a lightweight pose estimation technique. In: Dasgupta, K., Mukhopadhyay, S., Mandal, J.K., Dutta, P. (eds.) International Conference on Computational Intelligence in Communications and Business Analytics, pp. 30\u201340. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-48879-5_3","DOI":"10.1007\/978-3-031-48879-5_3"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Andriluka, M., et al.: PoseTrack: a benchmark for human pose estimation and tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00542"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2D human pose estimation: New benchmark and state of the art analysis. In: Proceedings of the IEEE Conference on computer Vision and Pattern Recognition, pp. 3686\u20133693 (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"5_CR4","doi-asserted-by":"publisher","unstructured":"Buslaev, A., Iglovikov, V.I., Khvedchenya, E., Parinov, A., Druzhinin, M., Kalinin, A.A.: Albumentations: fast and flexible image augmentations. Information 11(2) (2020). https:\/\/doi.org\/10.3390\/info11020125, https:\/\/www.mdpi.com\/2078-2489\/11\/2\/125","DOI":"10.3390\/info11020125"},{"key":"5_CR5","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":"5_CR6","unstructured":"Chen, K., et al.: MMDetection: Open MMLAB detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"key":"5_CR7","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"},{"issue":"3","key":"5_CR8","doi-asserted-by":"crossref","first-page":"934","DOI":"10.1109\/TITS.2018.2791533","volume":"19","author":"Y Choi","year":"2018","unstructured":"Choi, Y., et al.: KAIST multi-spectral day\/night data set for autonomous and assisted driving. IEEE Trans. Intell. Transp. Syst. 19(3), 934\u2013948 (2018)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Cormier, M., Clepe, A., Specker, A., Beyerer, J.: Where are we with human pose estimation in real-world surveillance? In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, pp. 591\u2013601 (2022)","DOI":"10.1109\/WACVW54805.2022.00065"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Cormier, M., R\u00f6pke, F., Golda, T., Beyerer, J.: Interactive labeling for human pose estimation in surveillance videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) Workshops, pp. 1649\u20131658 (2021)","DOI":"10.1109\/ICCVW54120.2021.00190"},{"key":"5_CR11","unstructured":"Dendorfer, P., et al.: Mot20: a benchmark for multi object tracking in crowded scenes. arXiv: 2003.09003 (2020)"},{"key":"5_CR12","unstructured":"Drillis, R., Contini, R.: Body segment parameters, New York University. Tech. rep, NY, Technical Report (1966)"},{"key":"5_CR13","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: YOLOX: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Gebhardt, E., Wolf, M.: Camel dataset for visual and thermal infrared multiple object detection and tracking. In: 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp.\u00a01\u20136. IEEE (2018)","DOI":"10.1109\/AVSS.2018.8639094"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Geng, Z., Sun, K., Xiao, B., Zhang, Z., Wang, J.: Bottom-up human pose estimation via disentangled keypoint regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14676\u201314686 (2021)","DOI":"10.1109\/CVPR46437.2021.01444"},{"key":"5_CR16","unstructured":"Heindl, C., Ikeda, M., St\u00fcbl, G., Pichler, A., Scharinger, J.: Metric pose estimation for human-machine interaction using monocular vision. arXiv preprint arXiv:1910.03239 (2019)"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Hwang, S., Park, J., Kim, N., Choi, Y., Kweon, I.S.: Multispectral pedestrian detection: Benchmark dataset and baselines. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"5_CR18","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3496\u20133504 (2021)","DOI":"10.1109\/ICCVW54120.2021.00389"},{"key":"5_CR19","doi-asserted-by":"publisher","unstructured":"Kuzdeuov, A., Taratynova, D., Tleuliyev, A., Varol, H.A.: OpenThermalPose: an open-source annotated thermal human pose dataset and initial yolov8-pose baselines. In: 2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG), pp.\u00a01\u20138 (2024). https:\/\/doi.org\/10.1109\/FG59268.2024.10581992","DOI":"10.1109\/FG59268.2024.10581992"},{"key":"5_CR20","unstructured":"Leal-Taix\u00e9, L., Milan, A., Reid, I., Roth, S., Schindler, K.: MOTChallenge 2015: towards a benchmark for multi-target tracking. arXiv:1504.01942 (2015)"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, C., Zhu, H., Mao, Y., Fang, H.S., Lu, C.: CrowdPose: efficient crowded scenes pose estimation and a new benchmark. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01112"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Li, K., Wang, S., Zhang, X., Xu, Y., Xu, W., Tu, Z.: Pose recognition with cascade transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1944\u20131953 (2021)","DOI":"10.1109\/CVPR46437.2021.00198"},{"key":"5_CR23","doi-asserted-by":"publisher","unstructured":"Li, Y., et al.: SIMCC: a simple coordinate classification perspective for human pose estimation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, pp. 89\u2013106. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20068-7_6","DOI":"10.1007\/978-3-031-20068-7_6"},{"key":"5_CR24","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":"5_CR25","doi-asserted-by":"crossref","unstructured":"Lu, P., Jiang, T., Li, Y., Li, X., Chen, K., Yang, W.: RTMO: towards high-performance one-stage real-time multi-person pose estimation. arXiv preprint arXiv:2312.07526 (2023)","DOI":"10.1109\/CVPR52733.2024.00148"},{"key":"5_CR26","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2637\u20132646 (2022)","DOI":"10.1109\/CVPRW56347.2022.00297"},{"key":"5_CR27","doi-asserted-by":"publisher","unstructured":"Mao, W., et al.: Poseur: direct human pose regression with transformers. In: In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European conference on computer vision, pp. 72\u201388. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20068-7_5","DOI":"10.1007\/978-3-031-20068-7_5"},{"key":"5_CR28","doi-asserted-by":"publisher","unstructured":"Martin, M., Popp, J., Anneken, M., Voit, M., Stiefelhagen, R.: Body pose and context information for driver secondary task detection. In: 2018 IEEE Intelligent Vehicles Symposium (IV), pp. 2015\u20132021 (2018).https:\/\/doi.org\/10.1109\/IVS.2018.8500523","DOI":"10.1109\/IVS.2018.8500523"},{"key":"5_CR29","unstructured":"Milan, A., Leal-Taix\u00e9, L., Reid, I., Roth, S., Schindler, K.: MOT16: a benchmark for multi-object tracking. arXiv:1603.00831 (2016)"},{"key":"5_CR30","unstructured":"MMPose-Contributors: Openmmlab pose estimation toolbox and benchmark. https:\/\/github.com\/open-mmlab\/mmpose (2020)"},{"key":"5_CR31","unstructured":"Newell, A., Huang, Z., Deng, J.: Associative embedding: end-to-end learning for joint detection and grouping. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Tang, Z., Ye, W., Ma, W.C., Zhao, H.: What happened 3 seconds ago? Inferring the past with thermal imaging. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01641"},{"key":"5_CR33","doi-asserted-by":"crossref","unstructured":"Toshev, A., Szegedy, C.: DeepPose: human pose estimation via deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1653\u20131660 (2014)","DOI":"10.1109\/CVPR.2014.214"},{"key":"5_CR34","doi-asserted-by":"crossref","unstructured":"Vendrow, E., Le, D.T., Cai, J., Rezatofighi, H.: JRDB-pose: a large-scale dataset for multi-person pose estimation and tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4811\u20134820 (2023)","DOI":"10.1109\/CVPR52729.2023.00466"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Deep high-resolution representation learning for visual recognition. TPAMI 43, 3349\u20133364 (2019)","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"5_CR36","doi-asserted-by":"publisher","unstructured":"Wang, S., et al.: Skeleton-based traffic command recognition at road intersections for intelligent vehicles. Neurocomputing 501, 123\u2013134 (2022). https:\/\/doi.org\/10.1016\/j.neucom.2022.05.107, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0925231222006944","DOI":"10.1016\/j.neucom.2022.05.107"},{"key":"5_CR37","doi-asserted-by":"publisher","unstructured":"Wang, X., et al.: PANDA: a gigapixel-level human-centric video dataset. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3265\u20133275 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00333","DOI":"10.1109\/CVPR42600.2020.00333"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.511"},{"key":"5_CR39","doi-asserted-by":"crossref","unstructured":"Winter, D.A.: Biomechanics and Motor Control of Human Movement. Wiley (2009)","DOI":"10.1002\/9780470549148"},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 466\u2013481 (2018)","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"5_CR41","first-page":"38571","volume":"35","author":"Y Xu","year":"2022","unstructured":"Xu, Y., Zhang, J., Zhang, Q., Tao, D.: ViTPose: simple vision transformer baselines for human pose estimation. Adv. Neural. Inf. Process. Syst. 35, 38571\u201338584 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR42","unstructured":"Yang, J., Zeng, A., Liu, S., Li, F., Zhang, R., Zhang, L.: Explicit box detection unifies end-to-end multi-person pose estimation. arXiv preprint arXiv:2302.01593 (2023)"},{"key":"5_CR43","doi-asserted-by":"crossref","unstructured":"Yang, S., Quan, Z., Nie, M., Yang, W.: Transpose: Keypoint localization via transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11802\u201311812 (2021)","DOI":"10.1109\/ICCV48922.2021.01159"},{"key":"5_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, S.H., et al.: Pose2Seg: detection free human instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00098"},{"key":"5_CR45","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Welschehold, T., Dornhege, C., Burgard, W., Brox, T.: 3D human pose estimation in RGBD images for robotic task learning. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 1986\u20131992. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8462833"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2641-0_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:56:03Z","timestamp":1743382563000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2641-0_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819626403","9789819626410"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2641-0_5","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":"29 March 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}