{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T21:46:30Z","timestamp":1743025590065,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819984688"},{"type":"electronic","value":"9789819984695"}],"license":[{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8469-5_26","type":"book-chapter","created":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T17:02:18Z","timestamp":1703437338000},"page":"327-339","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CTHPose: An Efficient and\u00a0Effective CNN-Transformer Hybrid Network for\u00a0Human Pose Estimation"],"prefix":"10.1007","author":[{"given":"Danya","family":"Chen","sequence":"first","affiliation":[]},{"given":"Lijun","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Zhicong","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Xufeng","family":"Lin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,25]]},"reference":[{"key":"26_CR1","doi-asserted-by":"publisher","unstructured":"Carion, N., Massa, F., Synnaeve, G., et\u00a0al.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H. (eds.) Computer Vision \u2013 ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Z., Peng, Y., et\u00a0al.: Cascaded pyramid network for multi-person pose estimation. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7103\u20137112 (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"26_CR3","doi-asserted-by":"crossref","unstructured":"Cheng, B., Xiao, B., Wang, J., et\u00a0al.: HigherHRNet: scale-aware representation learning for bottom-up human pose estimation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5385\u20135394 (2020)","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"26_CR4","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et\u00a0al.: An image is worth 16 $$\\times $$ 16 words: transformers for image recognition at scale. In: 9th International Conference on Learning Representations (ICLR), pp. 1\u201321 (2021)"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Duan, H., Zhao, Y., Chen, K., et\u00a0al.: Revisiting skeleton-based action recognition. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2959\u20132968 (2022)","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Fang, H.S., Xie, S., Tai, Y.W., et\u00a0al.: RMPE: regional multi-person pose estimation. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2353\u20132362 (2017)","DOI":"10.1109\/ICCV.2017.256"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Geng, Z., Sun, K., Xiao, B., et\u00a0al.: Bottom-up human pose estimation via disentangled keypoint regression. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14671\u201314681 (2021)","DOI":"10.1109\/CVPR46437.2021.01444"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et\u00a0al.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017)","DOI":"10.1145\/3065386"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Li, K., Wang, S., Zhang, X., et\u00a0al.: Pose recognition with cascade transformers. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1944\u20131953 (2021)","DOI":"10.1109\/CVPR46437.2021.00198"},{"key":"26_CR11","unstructured":"Li, Y., Xie, S., Chen, X., et\u00a0al.: Benchmarking detection transfer learning with vision transformers. CoRR (2021). https:\/\/arxiv.org\/abs\/2111.11429"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, S., Wang, Z., et\u00a0al.: TokenPose: learning keypoint tokens for human pose estimation. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11293\u201311302 (2021)","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., et\u00a0al.: Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 936\u2013944 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"26_CR14","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., Maire, M., Belongie, S., et\u00a0al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T. (eds.) Computer Vision \u2013 ECCV 2014. LNCS, vol.\u00a08693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"26_CR15","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1016\/j.neucom.2022.07.054","volume":"506","author":"H Liu","year":"2022","unstructured":"Liu, H., Liu, F., Fan, X., et al.: Polarized self-attention: towards high-quality pixel-wise mapping. Neurocomputing 506, 158\u2013167 (2022)","journal-title":"Neurocomputing"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., et\u00a0al.: Swin transformer: hierarchical vision transformer using shifted windows. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9992\u201310002 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"26_CR17","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1186\/s13640-020-0492-x","volume":"2020","author":"F Madrigal","year":"2020","unstructured":"Madrigal, F., Lerasle, F.: Robust head pose estimation based on key frames for human-machine interaction. EURASIP J. Image Video Process. 2020, 13 (2020)","journal-title":"EURASIP J. Image Video Process."},{"key":"26_CR18","doi-asserted-by":"publisher","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Ferrari, V., Hebert, M. (eds.) Computer Vision \u2013 ECCV 2016. LNCS, vol.\u00a09912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"26_CR19","unstructured":"Ramachandran, P., Parmar, N., Vaswani, A., et\u00a0al.: Stand-alone self-attention in vision models. In: Advances in Neural Information Processing Systems (2019)"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., et\u00a0al.: Deep high-resolution representation learning for human pose estimation. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5686\u20135696 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"26_CR21","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et\u00a0al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 6000\u20136010. Curran Associates Inc., Red Hook, NY, USA (2017)"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., et\u00a0al.: Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 548\u2013558 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"issue":"3","key":"26_CR23","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","volume":"8","author":"W Wang","year":"2022","unstructured":"Wang, W., Xie, E., Li, X., et al.: PVT v2: improved baselines with pyramid vision transformer. Comput. Vis. Media 8(3), 415\u2013424 (2022)","journal-title":"Comput. Vis. Media"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xu, Z., Wang, X., et\u00a0al.: End-to-end video instance segmentation with transformers. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8737\u20138746 (2021)","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Wang, Z., Cun, X., Bao, J., et\u00a0al.: Uformer: a general u-shaped transformer for image restoration. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 17662\u201317672 (2022)","DOI":"10.1109\/CVPR52688.2022.01716"},{"key":"26_CR26","doi-asserted-by":"publisher","unstructured":"Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: Ferrari, V., Hebert, M. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11210, pp. 472\u2013487. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_29","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Yang, S., Quan, Z., Nie, M., et\u00a0al.: Transpose: keypoint localization via transformer. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11782\u201311792 (2021)","DOI":"10.1109\/ICCV48922.2021.01159"},{"key":"26_CR28","unstructured":"YUAN, Y., Fu, R., Huang, L., et\u00a0al.: Hrformer: high-resolution vision transformer for dense predict. In: Advances in Neural Information Processing Systems, pp. 7281\u20137293. Curran Associates, Inc. (2021)"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, F., Zhu, X., Dai, H., et\u00a0al.: Distribution-aware coordinate representation for human pose estimation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7091\u20137100 (2020)","DOI":"10.1109\/CVPR42600.2020.00712"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8469-5_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T17:06:29Z","timestamp":1703437589000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8469-5_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,25]]},"ISBN":["9789819984688","9789819984695"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8469-5_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,25]]},"assertion":[{"value":"25 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","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":"532","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":"37% - 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":"3,78","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":"3,69","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}