{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T15:49:42Z","timestamp":1778600982651,"version":"3.51.4"},"reference-count":64,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T00:00:00Z","timestamp":1698364800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T00:00:00Z","timestamp":1698364800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Ministry of Culture, Sports, and Tourism","award":["R2020070002"],"award-info":[{"award-number":["R2020070002"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1007\/s00138-023-01471-6","type":"journal-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T10:01:48Z","timestamp":1698400908000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Position Puzzle Network and Augmentation: localizing human keypoints beyond the bounding box"],"prefix":"10.1007","volume":"34","author":[{"given":"Soonchan","family":"Park","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4676-9862","authenticated-orcid":false,"given":"Jinah","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"1471_CR1","doi-asserted-by":"crossref","unstructured":"Johnson, S., Everingham, M.: Learning effective human pose estimation from inaccurate annotation. In: CVPR 2011, pp. 1465\u20131472. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995318"},{"key":"1471_CR2","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: common objects in context. In: Proceedings of the European Conference on Computer Vision, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"4","key":"1471_CR3","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1109\/TPAMI.2018.2820063","volume":"41","author":"X Liang","year":"2018","unstructured":"Liang, X., Gong, K., Shen, X., Lin, L.: Look into person: joint body parsing and pose estimation network and a new benchmark. IEEE Trans. Pattern Anal. Mach. Intell. 41(4), 871\u2013885 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1471_CR4","unstructured":"Gao, C., Zou, Y., Huang, J.-B.: ican: instance-centric attention network for human-object interaction detection. In: British Machine Vision Conference (2018)"},{"key":"1471_CR5","doi-asserted-by":"crossref","unstructured":"Wang, T., Yang, T., Danelljan, M., Khan, F.S., Zhang, X., Sun, J.: Learning human-object interaction detection using interaction points. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4116\u20134125 (2020)","DOI":"10.1109\/CVPR42600.2020.00417"},{"key":"1471_CR6","doi-asserted-by":"crossref","unstructured":"Bansal, A., Rambhatla, S.S., Shrivastava, A., Chellappa, R.: Detecting human-object interactions via functional generalization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.e\u00a034, pp. 10460\u201310469 (2020)","DOI":"10.1609\/aaai.v34i07.6616"},{"key":"1471_CR7","doi-asserted-by":"crossref","unstructured":"Zhou, T., Wang, W., Qi, S., Ling, H., Shen, J.: Cascaded human-object interaction recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4263\u20134272 (2020)","DOI":"10.1109\/CVPR42600.2020.00432"},{"key":"1471_CR8","doi-asserted-by":"crossref","unstructured":"Su, C., Li, J., Zhang, S., Xing, J., Gao, W., Tian, Q.: Pose-driven deep convolutional model for person re-identification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3960\u20133969 (2017)","DOI":"10.1109\/ICCV.2017.427"},{"key":"1471_CR9","doi-asserted-by":"crossref","unstructured":"Miao, J., Wu, Y., Liu, P., Ding, Y., Yang, Y.: Pose-guided feature alignment for occluded person re-identification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 542\u2013551 (2019)","DOI":"10.1109\/ICCV.2019.00063"},{"key":"1471_CR10","doi-asserted-by":"crossref","unstructured":"Yan, C., Pang, G., Jiao, J., Bai, X., Feng, X., Shen, C.: Occluded person re-identification with single-scale global representations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11875\u201311884 (2021)","DOI":"10.1109\/ICCV48922.2021.01166"},{"key":"1471_CR11","doi-asserted-by":"crossref","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Proceedings of the European Conference on Computer Vision, pp. 483\u2013499. Springer (2016)","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"1471_CR12","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"1471_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2980\u20132988. IEEE (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"1471_CR14","doi-asserted-by":"crossref","unstructured":"Ke, L., Chang, M.-C., Qi, H., Lyu, S.: Multi-scale structure-aware network for human pose estimation. In: Proceedings of the European Conference on Computer Vision, pp. 713\u2013728 (2018)","DOI":"10.1109\/ICIP.2018.8451114"},{"key":"1471_CR15","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Karagoz, S., Akbas, E.: Multiposenet: fast multi-person pose estimation using pose residual network. In: Proceedings of the European Conference on Computer Vision, pp. 417\u2013433 (2018)","DOI":"10.1007\/978-3-030-01252-6_26"},{"key":"1471_CR16","doi-asserted-by":"crossref","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: Proceedings of the European Conference on Computer Vision, pp. 269\u2013286 (2018)","DOI":"10.1007\/978-3-030-01264-9_17"},{"key":"1471_CR17","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, pp. 466\u2013481 (2018)","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"1471_CR18","unstructured":"Wang, Z., Li, W., Yin, B., Peng, Q., Xiao, T., Du, Y., Li, Z., Zhang, X., Yu, G., Sun, J.: Mscoco keypoints challenge 2018. In: Joint Recognition Challenge Workshop at ECCV (2018)"},{"key":"1471_CR19","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation (2019). arXiv preprint arXiv:1902.09212","DOI":"10.1109\/CVPR.2019.00584"},{"key":"1471_CR20","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Yang, B., Wang, B., Yan, W., Tan, R.T.: Occlusion-aware networks for 3d human pose estimation in video. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 723\u2013732 (2019)","DOI":"10.1109\/ICCV.2019.00081"},{"key":"1471_CR21","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. In: AAAI, pp. 13001\u201313008 (2020)","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"1471_CR22","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1016\/j.patrec.2020.06.015","volume":"136","author":"S Park","year":"2020","unstructured":"Park, S., Lee, S., Park, J.: Data augmentation method for improving the accuracy of human pose estimation with cropped images. Pattern Recognit. Lett. 136, 244\u2013250 (2020)","journal-title":"Pattern Recognit. Lett."},{"key":"1471_CR23","doi-asserted-by":"publisher","first-page":"107410","DOI":"10.1016\/j.patcog.2020.107410","volume":"106","author":"Y Bin","year":"2020","unstructured":"Bin, Y., Chen, Z.-M., Wei, X.-S., Chen, X., Gao, C., Sang, N.: Structure-aware human pose estimation with graph convolutional networks. Pattern Recognit. 106, 107410 (2020)","journal-title":"Pattern Recognit."},{"key":"1471_CR24","doi-asserted-by":"crossref","unstructured":"Park, S., Park, J.: Localizing human keypoints beyond the bounding box. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1602\u20131611 (2021)","DOI":"10.1109\/ICCVW54120.2021.00185"},{"key":"1471_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107863","volume":"115","author":"L Tian","year":"2021","unstructured":"Tian, L., Wang, P., Liang, G., Shen, C.: An adversarial human pose estimation network injected with graph structure. Pattern Recognit. 115, 107863 (2021)","journal-title":"Pattern Recognit."},{"key":"1471_CR26","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, S., Wang, Z., Yang, S., Yang, W., Xia, S.-T., Zhou, E.: Tokenpose: learning keypoint tokens for human pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11313\u201311322 (2021)","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"1471_CR27","unstructured":"Chang, J.Y., Moon, G., Lee, K.M.: Poselifter: absolute 3d human pose lifting network from a single noisy 2d human pose (2019). arXiv preprint arXiv:1910.12029"},{"issue":"1","key":"1471_CR28","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1109\/TCSVT.2021.3057267","volume":"32","author":"T Chen","year":"2021","unstructured":"Chen, T., Fang, C., Shen, X., Zhu, Y., Chen, Z., Luo, J.: Anatomy-aware 3d human pose estimation with bone-based pose decomposition. IEEE Trans. Circuits Syst. Video Technol. 32(1), 198\u2013209 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1471_CR29","doi-asserted-by":"crossref","unstructured":"Lutz, S., Blythman, R., Ghosal, K., Moynihan, M., Simms, C., Smolic, A.: Jointformer: single-frame lifting transformer with error prediction and refinement for 3d human pose estimation. In: Proceedings of International Conference on Pattern Recognition, pp. 1156\u20131163. IEEE (2022)","DOI":"10.1109\/ICPR56361.2022.9956366"},{"key":"1471_CR30","doi-asserted-by":"publisher","first-page":"103055","DOI":"10.1016\/j.jvcir.2021.103055","volume":"76","author":"L Song","year":"2021","unstructured":"Song, L., Gang, Yu., Yuan, J., Liu, Z.: Human pose estimation and its application to action recognition: a survey. J. Vis. Commun. Image Represent. 76, 103055 (2021)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"1471_CR31","doi-asserted-by":"crossref","unstructured":"Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1110\u20131118 (2015)","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"1471_CR32","doi-asserted-by":"crossref","unstructured":"Si, C., Chen, W., Wang, W., Wang, L., Tan, T.: An attention enhanced graph convolutional LSTM network for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1227\u20131236 (2019)","DOI":"10.1109\/CVPR.2019.00132"},{"key":"1471_CR33","doi-asserted-by":"crossref","unstructured":"Zhao, R., Wang, K., Su, H., Ji, Q.: Bayesian graph convolution LSTM for skeleton based action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6882\u20136892 (2019a)","DOI":"10.1109\/ICCV.2019.00698"},{"key":"1471_CR34","doi-asserted-by":"crossref","unstructured":"Rao, H., Wang, S., Hu, X., Tan, M., Da, H., Cheng, J., Hu, B.: Self-supervised gait encoding with locality-aware attention for person re-identification. In: Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pp. 898\u2013905 (2021)","DOI":"10.24963\/ijcai.2020\/125"},{"key":"1471_CR35","doi-asserted-by":"publisher","first-page":"2103","DOI":"10.1109\/LSP.2022.3212634","volume":"29","author":"H Rao","year":"2022","unstructured":"Rao, H., Li, Y., Miao, C.: Revisiting-reciprocal distance re-ranking for skeleton-based person re-identification. IEEE Signal Process. Lett. 29, 2103\u20132107 (2022)","journal-title":"IEEE Signal Process. Lett."},{"key":"1471_CR36","doi-asserted-by":"crossref","unstructured":"Rao, H., Miao, C.: Transg: Transformer-based skeleton graph prototype contrastive learning with structure-trajectory prompted reconstruction for person re-identification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22118\u201322128 (2023)","DOI":"10.1109\/CVPR52729.2023.02118"},{"key":"1471_CR37","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"1471_CR38","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"1471_CR39","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: SSD: single shot multibox detector. In: Proceedings of the European Conference on Computer Vision, pp. 21\u201337. Springer (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1471_CR40","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"1471_CR41","doi-asserted-by":"crossref","unstructured":"Zhao, Q., Sheng, T., Wang, Y., Tang, Z., Chen, Y., Cai, L., Ling, H.: M2det: A single-shot object detector based on multi-level feature pyramid network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 9259\u20139266 (2019)","DOI":"10.1609\/aaai.v33i01.33019259"},{"key":"1471_CR42","unstructured":"Chen, S., Sun, P., Song, Y., Luo, P.: Diffusiondet: diffusion model for object detection (2022). arXiv preprint arXiv:2211.09788"},{"issue":"2","key":"1471_CR43","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1109\/TCSVT.2022.3202563","volume":"33","author":"B Tang","year":"2022","unstructured":"Tang, B., Liu, Z., Tan, Y., He, Q.: Hrtransnet: Hrformer-driven two-modality salient object detection. IEEE Trans. Circuits Syst. Video Technol. 33(2), 728\u2013742 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1471_CR44","doi-asserted-by":"crossref","unstructured":"Yoo, D., Park, S., Lee, J.-Y., Paek, A.S., Kweon, I.S.: Attentionnet: aggregating weak directions for accurate object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2659\u20132667 (2015)","DOI":"10.1109\/ICCV.2015.305"},{"key":"1471_CR45","doi-asserted-by":"crossref","unstructured":"Najibi, M., Rastegari, M., Davis, L.S.: G-CNN: an iterative grid based object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2369\u20132377 (2016)","DOI":"10.1109\/CVPR.2016.260"},{"key":"1471_CR46","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"1471_CR47","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3686\u20133693 (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"1471_CR48","doi-asserted-by":"crossref","unstructured":"Yu, C., Xiao, B., Gao, C., Yuan, L., Zhang, L., Sang, N., Wang, J.: Lite-hrnet: a lightweight high-resolution network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10440\u201310450 (2021)","DOI":"10.1109\/CVPR46437.2021.01030"},{"key":"1471_CR49","unstructured":"Yuan, Y., Rao, F., Huang, L., Lin, W., Zhang, C., Chen, X., Wang, J.: Hrformer: high-resolution transformer for dense prediction. In: Proceedings of Advances in Neural Information Processing Systems vol. 34, pp. 7281\u20137293 (2021)"},{"key":"1471_CR50","unstructured":"Yufei, X., Zhang, J., Zhang, Q., Tao, D.: Vitpose: simple vision transformer baselines for human pose estimation. In: Proceedings of Advances in Neural Information Processing Systems, vol. 35, pp. 38571\u201338584 (2022)"},{"key":"1471_CR51","unstructured":"Qiu, Z., Yang, Q., Wang, J., Wang, X., Xu, C., Fu, D., Yao, K., Han, J., Ding, E., Wang, J.: Learning structure-guided diffusion model for 2d human pose estimation (2023). arXiv preprint arXiv:2306.17074"},{"key":"1471_CR52","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":"1471_CR53","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":"1471_CR54","doi-asserted-by":"crossref","unstructured":"Shi, D., Wei, X., Li, L., Ren, Y., Tan, W.: End-to-end multi-person pose estimation with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11069\u201311078 (2022)","DOI":"10.1109\/CVPR52688.2022.01079"},{"key":"1471_CR55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3282139","author":"L Jin","year":"2023","unstructured":"Jin, L., Wang, X., Nie, X., Wang, W., Guo, Y., Yan, S., Zhao, J.: Rethinking the person localization for single-stage multi-person pose estimation. IEEE Trans. Multimed. (2023). https:\/\/doi.org\/10.1109\/TMM.2023.3282139","journal-title":"IEEE Trans. Multimed."},{"key":"1471_CR56","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: Proceedings of International Conference on Learning Representations (2020)"},{"key":"1471_CR57","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Proceedings of Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"1471_CR58","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANS on image synthesis. In: Proceedings of Advances in neural information processing systems, vol. 34, pp. 8780\u20138794 (2021)"},{"key":"1471_CR59","doi-asserted-by":"crossref","unstructured":"Yu, J., Jiang, Y., Wang, Z., Cao, Z., Huang, T.: Unitbox: an advanced object detection network. In: Proceedings of the 24th ACM International Conference on Multimedia, pp. 516\u2013520 (2016)","DOI":"10.1145\/2964284.2967274"},{"key":"1471_CR60","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J.Y., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666, (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"1471_CR61","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, pp. 12993\u201313000 (2020)","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"1471_CR62","unstructured":"leoxiaobin. deep-high-resolution-net.pytorch (2019). https:\/\/github.com\/leoxiaobin\/deep-high-resolution-net.pytorch"},{"key":"1471_CR63","unstructured":"leeyegy. Tokenpose (2021). https:\/\/github.com\/leeyegy\/TokenPose"},{"key":"1471_CR64","unstructured":"Daniil-Osokin. gccpm-look-into-person-cvpr19.pytorch (2019). https:\/\/github.com\/Daniil-Osokin\/gccpm-look-into-person-cvpr19.pytorch"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-023-01471-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-023-01471-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-023-01471-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T22:47:00Z","timestamp":1730414820000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-023-01471-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,27]]},"references-count":64,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["1471"],"URL":"https:\/\/doi.org\/10.1007\/s00138-023-01471-6","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,27]]},"assertion":[{"value":"1 April 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 August 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 September 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"129"}}