{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T11:29:56Z","timestamp":1743074996880,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":41,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819785070"},{"type":"electronic","value":"9789819785087"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-981-97-8508-7_9","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T06:08:33Z","timestamp":1730527713000},"page":"123-137","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["JPA: A Joint-Part Attention for Mitigating Overfocusing on 3D Human Pose Estimation"],"prefix":"10.1007","author":[{"given":"Dengqing","family":"Yang","sequence":"first","affiliation":[]},{"given":"Zhenhua","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Jinmeng","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Lechao","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Yanbin","family":"Hao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"9_CR1","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization (2016)"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Cai, Y., Ge, L., Liu, J., Cai, J., Cham, T.J., Yuan, J., Thalmann, N.M.: Exploiting spatial-temporal relationships for 3d pose estimation via graph convolutional networks. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00236"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Chen, T., Fang, C., Shen, X., Zhu, Y., Chen, Z., Luo, J.: Anatomy-aware 3d human pose estimation with bone-based pose decomposition. TCSVT (2021)","DOI":"10.1109\/TCSVT.2021.3057267"},{"key":"9_CR4","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":"9_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, J., Cheng, Q., Yang, M., Liu, Z., Zhang, Q., Cheng, J.: Mixpose: 3d human pose estimation with mixed encoder. In: Chinese Conference on Pattern Recognition and Computer Vision (PRCV), pp. 353\u2013364. Springer (2023)","DOI":"10.1007\/978-981-99-8543-2_29"},{"key":"9_CR6","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 16 $$\\times $$ 16 words: transformers for image recognition at scale. ArXiv (2020)"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Guo, D., Wang, S., Tian, Q., Wang, M.: Dense temporal convolution network for sign language translation. In: IJCAI, pp. 744\u2013750 (2019)","DOI":"10.24963\/ijcai.2019\/105"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Guo, Y., Stutz, D., Schiele, B.: Robustifying token attention for vision transformers. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01610"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Hao, Y., Zhang, H., Ngo, C.W., He, X.: Group contextualization for video recognition. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00100"},{"key":"9_CR10","unstructured":"He, J., Cheng, L., Fang, C., Zhang, D., Wang, Z., Chen, W.: Mitigating undisciplined over-smoothing in transformer for weakly supervised semantic segmentation. ArXiv (2023)"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Hossain, M.R.I., Little, J.J.: Exploiting temporal information for 3d human pose estimation. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01249-6_5"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3. 6m: large scale datasets and predictive methods for 3d human sensing in natural environments. TPAMI (2013)","DOI":"10.1109\/TPAMI.2013.248"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, H., Ding, R., Liu, M., Wang, P., Yang, W.: Exploiting temporal contexts with strided transformer for 3d human pose estimation. TMM (2022)","DOI":"10.1109\/TMM.2022.3141231"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, H., Tang, H., Wang, P., Van\u00a0Gool, L.: Mhformer: multi-hypothesis transformer for 3d human pose estimation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01280"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., Liu, Z.: End-to-end human pose and mesh reconstruction with transformers. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Liu, K., Ding, R., Zou, Z., Wang, L., Tang, W.: A comprehensive study of weight sharing in graph networks for 3d human pose estimation. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58607-2_19"},{"key":"9_CR17","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: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00511"},{"key":"9_CR18","unstructured":"Luo, S., Li, S., Zheng, S., Liu, T.Y., Wang, L., He, D.: Your transformer may not be as powerful as you expect. NeurlPS (2022)"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Ma, H., Lu, K., Xue, J., Niu, Z., Gao, P.: Local to global transformer for video based 3d human pose estimation. In: ICMEW (2022)","DOI":"10.1109\/ICMEW56448.2022.9859482"},{"key":"9_CR20","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: ICCV (2017)","DOI":"10.1109\/ICCV.2017.288"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Mehta, D., Rhodin, H., Casas, D., Fua, P., Sotnychenko, O., Xu, W., Theobalt, C.: Monocular 3d human pose estimation in the wild using improved CNN supervision. In: 3DV (2017)","DOI":"10.1109\/3DV.2017.00064"},{"key":"9_CR22","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":"9_CR23","doi-asserted-by":"crossref","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: ECCV (2022)","DOI":"10.1007\/978-3-031-20065-6_27"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Shan, W., Lu, H., Wang, S., Zhang, X., Gao, W.: Improving robustness and accuracy via relative information encoding in 3d human pose estimation. In: ACM MM (2021)","DOI":"10.1145\/3474085.3475504"},{"key":"9_CR25","doi-asserted-by":"crossref","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. IJCV (2010)","DOI":"10.1007\/s11263-009-0273-6"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Sun, X., Shang, J., Liang, S., Wei, Y.: Compositional human pose regression. In: ICCV, pp. 2602\u20132611 (2017)","DOI":"10.1109\/ICCV.2017.284"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Tang, Z., Hao, Y., Li, J., Hong, R.: Ftcm: frequency-temporal collaborative module for efficient 3d human pose estimation in video. TCSVT (2023)","DOI":"10.1109\/TCSVT.2023.3286402"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Tang, Z., Li, J., Hao, Y., Hong, R.: Mlp-jcg: multi-layer perceptron with joint-coordinate gating for efficient 3d human pose estimation. TMM (2023)","DOI":"10.1109\/TMM.2023.3240455"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Tang, Z., Qiu, Z., Hao, Y., Hong, R., Yao, T.: 3d human pose estimation with spatio-temporal criss-cross attention. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00464"},{"key":"9_CR30","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: NIPS (2017)"},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Wang, J., Yan, S., Xiong, Y., Lin, D.: Motion guided 3d pose estimation from videos. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58601-0_45"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Wang, S., Guo, D., Zhou, W.g., Zha, Z.j., Wang, M.: Connectionist temporal fusion for sign language translation. In: ACM MM, pp. 1483\u20131491 (2018)","DOI":"10.1145\/3240508.3240671"},{"key":"9_CR33","doi-asserted-by":"crossref","unstructured":"Xu, T., Takano, W.: Graph stacked hourglass networks for 3d human pose estimation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01584"},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Xue, Y., Chen, J., Gu, X., Ma, H., Ma, H.: Boosting monocular 3d human pose estimation with part aware attention. TIP (2022)","DOI":"10.1109\/TIP.2022.3182269"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"Yu, B.X., Zhang, Z., Liu, Y., Zhong, S.h., Liu, Y., Chen, C.W.: Gla-gcn: global-local adaptive graph convolutional network for 3d human pose estimation from monocular video. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00810"},{"key":"9_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, H., Hao, Y., Ngo, C.W.: Token shift transformer for video classification. In: ACM MM (2021)","DOI":"10.1145\/3474085.3475272"},{"key":"9_CR37","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: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01288"},{"key":"9_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, X., Tang, Z., Hou, J., Hao, Y.: 3d human pose estimation via human structure-aware fully connected network. Pattern Recogn. Lett. (2019)","DOI":"10.1016\/j.patrec.2019.05.020"},{"key":"9_CR39","doi-asserted-by":"crossref","unstructured":"Zhao, L., Peng, X., Tian, Y., Kapadia, M., Metaxas, D.N.: Semantic graph convolutional networks for 3d human pose regression. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00354"},{"key":"9_CR40","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: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"9_CR41","doi-asserted-by":"crossref","unstructured":"Zou, J., Shao, M., Xia, S.: Graphrpe: relative position encoding graph transformer for 3d human pose estimation. In: ICIP, pp. 895\u2013899 (2023)","DOI":"10.1109\/ICIP49359.2023.10222124"}],"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\/978-981-97-8508-7_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T06:14:17Z","timestamp":1730528057000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8508-7_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819785070","9789819785087"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8508-7_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","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":"Urumqi","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}