{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T16:14:30Z","timestamp":1781799270569,"version":"3.54.5"},"publisher-location":"Cham","reference-count":70,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200670","type":"print"},{"value":"9783031200687","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20068-7_3","type":"book-chapter","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T08:06:38Z","timestamp":1668067598000},"page":"37-54","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":72,"title":["Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-person Human Pose Estimation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7187-7147","authenticated-orcid":false,"given":"William","family":"McNally","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9515-7259","authenticated-orcid":false,"given":"Kanav","family":"Vats","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5295-2797","authenticated-orcid":false,"given":"Alexander","family":"Wong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3908-9519","authenticated-orcid":false,"given":"John","family":"McPhee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,11]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Andriluka, M., et al.: Posetrack: A benchmark for human pose estimation and tracking. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00542"},{"key":"3_CR2","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Bras\u00f3, G., Kister, N., Leal-Taix\u00e9, L.: The center of attention: Center-keypoint grouping via attention for multi-person pose estimation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01164"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Cao, Z., Hidalgo, G., Simon, T., Wei, S.E., Sheikh, Y.: Openpose: realtime multi-person 2d pose estimation using part affinity fields. arXiv preprint arXiv:1812.08008 (2018)","DOI":"10.1109\/CVPR.2017.143"},{"key":"3_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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G., Sun, J.: Cascaded pyramid network for multi-person pose estimation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"3_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: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., Sun, J.: RepVGG: Making VGG-style convnets great again. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Dong, X., Yan, Y., Ouyang, W., Yang, Y.: Style aggregated network for facial landmark detection. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00047"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Fang, H.S., Xie, S., Tai, Y.W., Lu, C.: RMPE: Regional multi-person pose estimation. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.256"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Gavrilyuk, K., Sanford, R., Javan, M., Snoek, C.G.: Actor-transformers for group activity recognition. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00092"},{"key":"3_CR12","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: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01444"},{"key":"3_CR13","unstructured":"Goyal, P., et al.: Accurate, large minibatch sgd: Training imagenet in 1 hour. arXiv preprint arXiv:1706.02677 (2017)"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Huang, W., Ren, P., Wang, J., Qi, Q., Sun, H.: Awr: Adaptive weighting regression for 3d hand pose estimation. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6761"},{"key":"3_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1007\/978-3-319-46466-4_3","volume-title":"Computer Vision \u2013 ECCV 2016","author":"E Insafutdinov","year":"2016","unstructured":"Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., Schiele, B.: DeeperCut: A deeper, stronger, and faster multi-person pose estimation model. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 34\u201350. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_3"},{"key":"3_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1007\/978-3-319-48881-3_44","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"U Iqbal","year":"2016","unstructured":"Iqbal, U., Gall, J.: Multi-person pose estimation with local joint-to-person associations. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 627\u2013642. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_44"},{"key":"3_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/978-3-030-01252-6_8","volume-title":"Computer Vision \u2013 ECCV 2018","author":"U Iqbal","year":"2018","unstructured":"Iqbal, U., Molchanov, P., Breuel, T., Gall, J., Kautz, J.: Hand pose estimation via latent 2.5D heatmap regression. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 125\u2013143. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_8"},{"key":"3_CR19","unstructured":"Jakab, T., Gupta, A., Bilen, H., Vedaldi, A.: Unsupervised learning of object landmarks through conditional image generation. In: NeurIPS (2018)"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Jeon, S., Min, D., Kim, S., Sohn, K.: Joint learning of semantic alignment and object landmark detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00739"},{"key":"3_CR21","unstructured":"Jia, X., De Brabandere, B., Tuytelaars, T., Gool, L.V.: Dynamic filter networks. In: NeurIPS (2016)"},{"key":"3_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"718","DOI":"10.1007\/978-3-030-58571-6_42","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Jin","year":"2020","unstructured":"Jin, S., et al.: Differentiable hierarchical graph grouping for multi-person pose estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 718\u2013734. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_42"},{"key":"3_CR23","doi-asserted-by":"publisher","unstructured":"Jocher, G., et al.: ultralytics\/yolov5: v5.0 (Apr 2021). DOI: https:\/\/doi.org\/10.5281\/zenodo.4679653","DOI":"10.5281\/zenodo.4679653"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Khirodkar, R., Chari, V., Agrawal, A., Tyagi, A.: Multi-hypothesis pose networks: Rethinking top-down pose estimation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00311"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Kreiss, S., Bertoni, L., Alahi, A.: Pifpaf: Composite fields for human pose estimation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01225"},{"key":"3_CR26","unstructured":"LeCun, Y., Bengio, Y., et al.: Convolutional networks for images, speech, and time series. In: The Handbook of Brain Theory and Neural Networks, vol. 3361(10) (1995)"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Human pose regression with residual log-likelihood estimation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01084"},{"key":"3_CR28","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: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01112"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Li, K., Wang, S., Zhang, X., Xu, Y., Xu, W., Tu, Z.: Pose recognition with cascade transformers. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00198"},{"key":"3_CR30","unstructured":"Li, Y., et al.: Is 2d heatmap representation even necessary for human pose estimation? arXiv preprint arXiv:2107.03332 (2021)"},{"key":"3_CR31","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"3_CR33","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_CR34","unstructured":"Loshchilov, I., Hutter, F.: SGDR: Stochastic gradient descent with warm restarts. In: ICLR (2017)"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Luo, Z., Wang, Z., Huang, Y., Wang, L., Tan, T., Zhou, E.: Rethinking the heatmap regression for bottom-up human pose estimation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01306"},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Mao, W., Tian, Z., Wang, X., Shen, C.: Fcpose: Fully convolutional multi-person pose estimation with dynamic instance-aware convolutions. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00892"},{"key":"3_CR37","doi-asserted-by":"publisher","unstructured":"McNally, W., Vats, K., Wong, A., McPhee, J.: EvoPose2D: Pushing the boundaries of 2d human pose estimation using accelerated neuroevolution with weight transfer. IEEE Access (2021). https:\/\/doi.org\/10.1109\/ACCESS.2021.3118207","DOI":"10.1109\/ACCESS.2021.3118207"},{"key":"3_CR38","doi-asserted-by":"crossref","unstructured":"McNally, W., Walters, P., Vats, K., Wong, A., McPhee, J.: DeepDarts: Modeling keypoints as objects for automatic scorekeeping in darts using a single camera. In: CVPRW (2021)","DOI":"10.1109\/CVPRW53098.2021.00512"},{"issue":"1","key":"3_CR39","first-page":"3","volume":"4","author":"W McNally","year":"2018","unstructured":"McNally, W., Wong, A., McPhee, J.: Action recognition using deep convolutional neural networks and compressed spatio-temporal pose encodings. J. Comput. Vis. Imaging Syst. 4(1), 3 (2018)","journal-title":"J. Comput. Vis. Imaging Syst."},{"key":"3_CR40","doi-asserted-by":"crossref","unstructured":"McNally, W., Wong, A., McPhee, J.: STAR-Net: Action recognition using spatio-temporal activation reprojection. In: CRV (2019)","DOI":"10.1109\/CRV.2019.00015"},{"key":"3_CR41","first-page":"543","volume":"269","author":"Y Nesterov","year":"1983","unstructured":"Nesterov, Y.: A method for solving the convex programming problem with convergence rate o(1\/k2). Proc. USSR Acad. Sci. 269, 543\u2013547 (1983)","journal-title":"Proc. USSR Acad. Sci."},{"key":"3_CR42","unstructured":"Newell, A., Huang, Z., Deng, J.: Associative embedding: End-to-end learning for joint detection and grouping. In: NeurIPS (2017)"},{"key":"3_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"key":"3_CR44","doi-asserted-by":"crossref","unstructured":"Nie, X., Feng, J., Zhang, J., Yan, S.: Single-stage multi-person pose machines. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00705"},{"key":"3_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/978-3-030-01264-9_17","volume-title":"Computer Vision \u2013 ECCV 2018","author":"G Papandreou","year":"2018","unstructured":"Papandreou, G., Zhu, T., Chen, L.-C., Gidaris, S., Tompson, J., Murphy, K.: PersonLab: Person pose estimation and instance segmentation with a bottom-up, part-based, geometric embedding model. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 282\u2013299. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_17"},{"key":"3_CR46","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Zhu, T., Kanazawa, N., Toshev, A., Tompson, J., Bregler, C., Murphy, K.: Towards accurate multi-person pose estimation in the wild. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.395"},{"key":"3_CR47","doi-asserted-by":"crossref","unstructured":"Pavllo, D., Feichtenhofer, C., Grangier, D., Auli, M.: 3d human pose estimation in video with temporal convolutions and semi-supervised training. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00794"},{"key":"3_CR48","doi-asserted-by":"crossref","unstructured":"Pishchulin, L., Insafutdinov, E., Tang, S., Andres, B., Andriluka, M., Gehler, P.V., Schiele, B.: DeepCut: Joint subset partition and labeling for multi person pose estimation. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.533"},{"key":"3_CR49","doi-asserted-by":"crossref","unstructured":"Raaj, Y., Idrees, H., Hidalgo, G., Sheikh, Y.: Efficient online multi-person 2d pose tracking with recurrent spatio-temporal affinity fields. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00475"},{"key":"3_CR50","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"3_CR51","unstructured":"Redmon, J., Farhadi, A.: Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"3_CR52","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks (2015)"},{"key":"3_CR53","unstructured":"Rezende, D., Mohamed, S.: Variational inference with normalizing flows. In: ICML (2015)"},{"key":"3_CR54","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"3_CR55","unstructured":"Suwajanakorn, S., Snavely, N., Tompson, J., Norouzi, M.: Discovery of latent 3d keypoints via end-to-end geometric reasoning. In: NeurIPS (2018)"},{"key":"3_CR56","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: Fully convolutional one-stage object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"3_CR57","unstructured":"Tompson, J.J., Jain, A., LeCun, Y., Bregler, C.: Joint training of a convolutional network and a graphical model for human pose estimation. In: NeurIPS (2014)"},{"key":"3_CR58","doi-asserted-by":"crossref","unstructured":"Toshev, A., Szegedy, C.: DeepPose: Human pose estimation via deep neural networks. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.214"},{"key":"3_CR59","unstructured":"Vats, K., McNally, W., Dulhanty, C., Lin, Z.Q., Clausi, D.A., Zelek, J.: PuckNet: Estimating hockey puck location from broadcast video. In: AAAI Workshops (2019)"},{"key":"3_CR60","doi-asserted-by":"crossref","unstructured":"Voeikov, R., Falaleev, N., Baikulov, R.: Ttnet: Real-time temporal and spatial video analysis of table tennis. In: CVPRW (2020)","DOI":"10.1109\/CVPRW50498.2020.00450"},{"key":"3_CR61","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: Scaled-YOLOv4: Scaling cross stage partial network. arXiv preprint arXiv:2011.08036 (2020)","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"3_CR62","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Liao, H.Y.M., Wu, Y.H., Chen, P.Y., Hsieh, J.W., Yeh, I.H.: Cspnet: A new backbone that can enhance learning capability of cnn. In: CVPR (2020)","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"3_CR63","doi-asserted-by":"crossref","unstructured":"Wang, X., Bo, L., Fuxin, L.: Adaptive wing loss for robust face alignment via heatmap regression. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00707"},{"key":"3_CR64","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1007\/978-3-030-58607-2_31","volume-title":"Computer Vision \u2013 ECCV 2020","author":"F Wei","year":"2020","unstructured":"Wei, F., Sun, X., Li, H., Wang, J., Lin, S.: Point-set anchors for object detection, instance segmentation and pose estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 527\u2013544. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58607-2_31"},{"key":"3_CR65","doi-asserted-by":"crossref","unstructured":"Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.511"},{"key":"3_CR66","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1007\/978-3-030-01231-1_29","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Xiao","year":"2018","unstructured":"Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 472\u2013487. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_29"},{"key":"3_CR67","doi-asserted-by":"crossref","unstructured":"Xu, Z., Li, B., Yuan, Y., Geng, M.: AnchorFace: An anchor-based facial landmark detector across large poses. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i4.16418"},{"key":"3_CR68","doi-asserted-by":"crossref","unstructured":"Yang, S., Quan, Z., Nie, M., Yang, W.: Transpose: Keypoint localization via transformer. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01159"},{"key":"3_CR69","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-IoU loss: Faster and better learning for bounding box regression. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"3_CR70","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20068-7_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T08:07:32Z","timestamp":1668067652000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20068-7_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200670","9783031200687"],"references-count":70,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20068-7_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","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":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}