{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T00:48:33Z","timestamp":1753922913879,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819985425"},{"type":"electronic","value":"9789819985432"}],"license":[{"start":{"date-parts":[[2023,12,29]],"date-time":"2023-12-29T00:00:00Z","timestamp":1703808000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,29]],"date-time":"2023-12-29T00:00:00Z","timestamp":1703808000000},"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\/978-981-99-8543-2_29","type":"book-chapter","created":{"date-parts":[[2023,12,28]],"date-time":"2023-12-28T10:03:03Z","timestamp":1703757783000},"page":"353-364","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["MixPose: 3D Human Pose Estimation with\u00a0Mixed Encoder"],"prefix":"10.1007","author":[{"given":"Jisheng","family":"Cheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengjie","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qieshi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,29]]},"reference":[{"issue":"12","key":"29_CR1","doi-asserted-by":"publisher","first-page":"1966","DOI":"10.3390\/s16121966","volume":"16","author":"W Gong","year":"2016","unstructured":"Gong, W., et al.: Human pose estimation from monocular images: a comprehensive survey. Sensors 16(12), 1966 (2016)","journal-title":"Sensors"},{"issue":"1","key":"29_CR2","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1109\/TCSVT.2021.3057267","volume":"32","author":"T Chen","year":"2022","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 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"29_CR3","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7103\u20137112 (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Zheng, C., Zhu, S., Mendieta, M., Yang, T., Chen, C., Ding, Z.: 3D human pose estimation with spatial and temporal transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11656\u201311665 (2021)","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Zhan, Y., Li, F., Weng, R., Choi, W.: Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13116\u201313125 (2022)","DOI":"10.1109\/CVPR52688.2022.01277"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Qin, H., Cheng, J., Song, C., Hao, F., Cheng, Q.: Structure-preserving view-invariant skeleton representation for action detection. In: 2022 26th International Conference on Pattern Recognition (ICPR), pp. 3190\u20133196. IEEE (2022)","DOI":"10.1109\/ICPR56361.2022.9956485"},{"issue":"3","key":"29_CR7","doi-asserted-by":"publisher","first-page":"1498","DOI":"10.1109\/TCSVT.2021.3076165","volume":"32","author":"J Cheng","year":"2022","unstructured":"Cheng, J., Ren, Z., Zhang, Q., Gao, X., Hao, F.: Cross-modality compensation convolutional neural networks for RGB-D action recognition. IEEE Trans. Circuits Syst. Video Technol. 32(3), 1498\u20131509 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"29_CR8","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.sigpro.2017.08.016","volume":"143","author":"X Ji","year":"2018","unstructured":"Ji, X., Cheng, J., Feng, W., Tao, D.: Skeleton embedded motion body partition for human action recognition using depth sequences. Sig. Process. 143, 56\u201368 (2018)","journal-title":"Sig. Process."},{"key":"29_CR9","doi-asserted-by":"publisher","first-page":"107040","DOI":"10.1016\/j.knosys.2021.107040","volume":"227","author":"X Ji","year":"2021","unstructured":"Ji, X., Zhao, Q., Cheng, J., Ma, C.: Exploiting spatio-temporal representation for 3D human action recognition from depth map sequences. Knowl.-Based Syst. 227, 107040 (2021)","journal-title":"Knowl.-Based Syst."},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Diller, C., Funkhouser, T., Dai, A.: Forecasting characteristic 3D poses of human actions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15914\u201315923 (2022)","DOI":"10.1109\/CVPR52688.2022.01545"},{"issue":"4","key":"29_CR11","doi-asserted-by":"publisher","first-page":"2460","DOI":"10.3390\/app13042460","volume":"13","author":"T Anvari","year":"2023","unstructured":"Anvari, T., Park, K., Kim, G.: Upper body pose estimation using deep learning for a virtual reality avatar. Appl. Sci. 13(4), 2460 (2023)","journal-title":"Appl. Sci."},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Martinez, J., Hossain, R., Romero, J., Little, J.J.: A simple yet effective baseline for 3D human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2640\u20132649 (2017)","DOI":"10.1109\/ICCV.2017.288"},{"key":"29_CR13","doi-asserted-by":"publisher","unstructured":"Shan, W., Liu, Z., Zhang, X., Wang, S., Ma, S., Gao, W.: P-STMO: pre-trained spatial temporal many-to-one model for 3d human pose estimation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol. 13665, pp. 461\u2013478. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20065-6_27","DOI":"10.1007\/978-3-031-20065-6_27"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, H., Tang, H., Wang, P., Van Gool, L.: MHFormer: multi-hypothesis transformer for 3D human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13147\u201313156 (2022)","DOI":"10.1109\/CVPR52688.2022.01280"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Zhao, Q., Zheng, C., Liu, M., Wang, P., Chen, C.: PoseFormerV2: exploring frequency domain for efficient and robust 3D human pose estimation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8877\u20138886 (2023)","DOI":"10.1109\/CVPR52729.2023.00857"},{"key":"29_CR16","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: Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00794"},{"key":"29_CR17","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1109\/TPAMI.2019.2929257","volume":"43","author":"Z Cao","year":"2019","unstructured":"Cao, Z., Hidalgo Martinez, G., Simon, T., Wei, S., Sheikh, Y.A.: OpenPose: realtime multi-person 2D pose estimation using part affinity fields. IEEE Trans. Pattern Anal. Mach. Intell. 43, 172\u2013186 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR18","doi-asserted-by":"crossref","first-page":"12581","DOI":"10.1109\/TPAMI.2023.3282631","volume":"45","author":"K Li","year":"2022","unstructured":"Li, K., et al.: UniFormer: unifying convolution and self-attention for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45, 12581\u201312600 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR19","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":"29_CR20","unstructured":"Xu, Y., Zhang, J., Zhang, Q., Tao, D.: ViTPose: simple vision transformer baselines for human pose estimation. In: Advances in Neural Information Processing Systems (2022)"},{"key":"29_CR21","doi-asserted-by":"publisher","first-page":"4122","DOI":"10.1109\/TPAMI.2022.3188716","volume":"45","author":"H Shuai","year":"2022","unstructured":"Shuai, H., Wu, L., Liu, Q.: Adaptive multi-view and temporal fusing transformer for 3D human pose estimation. IEEE Trans. Pattern Anal. Mach. Intell. 45, 4122\u20134135 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, J., Tu, Z., Yang, J., Chen, Y., Yuan, J.: MixSTE: seq2seq mixed spatio-temporal encoder for 3D human pose estimation in video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13232\u201313242 (2022)","DOI":"10.1109\/CVPR52688.2022.01288"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Hossain, M.R.I., Little, J.J.: Exploiting temporal information for 3D human pose estimation. In: Proceedings of the European conference on computer vision (ECCV), pp. 68\u201384 (2018)","DOI":"10.1007\/978-3-030-01249-6_5"},{"key":"29_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al., (eds.), Advances in Neural Information Processing Systems, vol. 30. Curran Associates Inc. (2017)"},{"key":"29_CR26","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Einfalt, M., Ludwig, K., Lienhart, R.: Uplift and upsample: efficient 3D human pose estimation with uplifting transformers. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2903\u20132913 (2023)","DOI":"10.1109\/WACV56688.2023.00292"},{"issue":"7","key":"29_CR28","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2013","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3. 6m: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1\u20132","key":"29_CR29","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/s11263-009-0273-6","volume":"87","author":"L Sigal","year":"2010","unstructured":"Sigal, L., Balan, A.O., Black, M.J.: HumanEva: synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. Int. J. Comput. Vis. 87(1\u20132), 4 (2010)","journal-title":"Int. J. Comput. Vis."},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhou, X., Daniilidis, K.: Ordinal depth supervision for 3D human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7307\u20137316 (2018)","DOI":"10.1109\/CVPR.2018.00763"},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"Liu, R., Shen, J., Wang, H., Chen, C., Cheung, S.-c., Asari, V.: Attention mechanism exploits temporal contexts: real-time 3D human pose reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00511"},{"key":"29_CR32","doi-asserted-by":"crossref","unstructured":"Zeng, A., Sun, X., Yang, L., Zhao, N., Liu, M., Xu, Q.: Learning skeletal graph neural networks for hard 3D pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11436\u201311445 (2021)","DOI":"10.1109\/ICCV48922.2021.01124"},{"key":"29_CR33","doi-asserted-by":"publisher","first-page":"1282","DOI":"10.1109\/TMM.2022.3141231","volume":"25","author":"W Li","year":"2023","unstructured":"Li, W., Liu, H., Ding, R., Liu, M., Wang, P., Yang, W.: Exploiting temporal contexts with strided transformer for 3D human pose estimation. IEEE Trans. Multimedia 25, 1282\u20131293 (2023)","journal-title":"IEEE Trans. Multimedia"},{"key":"29_CR34","doi-asserted-by":"crossref","unstructured":"Kang, Y., Liu, Y., Yao, A., Wang, S., Wu, E.: 3D human pose lifting with grid convolution. In: Proceedings of the AAAI Conference on Artificial Intelligence (2023)","DOI":"10.1609\/aaai.v37i1.25192"},{"key":"29_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"764","DOI":"10.1007\/978-3-030-58601-0_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Wang","year":"2020","unstructured":"Wang, J., Yan, S., Xiong, Y., Lin, D.: Motion guided 3D pose estimation from videos. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 764\u2013780. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_45"}],"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\/978-981-99-8543-2_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T23:37:54Z","timestamp":1730936274000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8543-2_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,29]]},"ISBN":["9789819985425","9789819985432"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8543-2_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,29]]},"assertion":[{"value":"29 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)"}}]}}