{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T14:12:09Z","timestamp":1765807929913,"version":"3.37.3"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2021,6,11]],"date-time":"2021-06-11T00:00:00Z","timestamp":1623369600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,6,11]],"date-time":"2021-06-11T00:00:00Z","timestamp":1623369600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100012165","name":"Key Technologies Research and Development Program","doi-asserted-by":"publisher","award":["2018AAA0102001"],"award-info":[{"award-number":["2018AAA0102001"]}],"id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072245","62002160"],"award-info":[{"award-number":["62072245","62002160"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702265","61672285"],"award-info":[{"award-number":["61702265","61672285"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61932020"],"award-info":[{"award-number":["61932020"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1007\/s00530-021-00807-4","type":"journal-article","created":{"date-parts":[[2021,6,11]],"date-time":"2021-06-11T03:34:14Z","timestamp":1623382454000},"page":"413-422","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Skip-attention encoder\u2013decoder framework for human motion prediction"],"prefix":"10.1007","volume":"28","author":[{"given":"Ruipeng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4902-4663","authenticated-orcid":false,"given":"Xiangbo","family":"Shu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiachao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,6,11]]},"reference":[{"key":"807_CR1","doi-asserted-by":"crossref","unstructured":"Aksan, E., Kaufmann, M., Hilliges, O.: Structured prediction helps 3d human motion modelling. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00724"},{"key":"807_CR2","unstructured":"Ballas, N., Yao, L., Pal, C., Courville, A.: Delving deeper into convolutional networks for learning video representations (2015). arXiv:1511.06432"},{"key":"807_CR3","doi-asserted-by":"crossref","unstructured":"Bappy, J.H., Roy-Chowdhury, A.K.: CNN based region proposals for efficient object detection. In: ICIP (2016)","DOI":"10.1109\/ICIP.2016.7533042"},{"key":"807_CR4","doi-asserted-by":"crossref","unstructured":"Blot, M., Cord, M., Thome, N.: Max-min convolutional neural networks for image classification. In: ICIP (2016)","DOI":"10.1109\/ICIP.2016.7533046"},{"key":"807_CR5","doi-asserted-by":"crossref","unstructured":"Brand, M., Hertzmann, A.: Style machines. In: SIGGRAPH, pp. 183\u2013192 (2000)","DOI":"10.1145\/344779.344865"},{"key":"807_CR6","doi-asserted-by":"crossref","unstructured":"Chiu, H.k., Adeli, E., Wang, B., Huang, D.A., Niebles, J.C.: Action-agnostic human pose forecasting. In: WACV (2019)","DOI":"10.1109\/WACV.2019.00156"},{"key":"807_CR7","doi-asserted-by":"crossref","unstructured":"Cho, K., Van\u00a0Merri\u00ebnboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation (2014). arXiv:1406.1078","DOI":"10.3115\/v1\/D14-1179"},{"key":"807_CR8","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: Deep learning with depthwise separable convolutions. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"807_CR9","doi-asserted-by":"crossref","unstructured":"Corona, E., Pumarola, A., Alenya, G., Moreno-Noguer, F.: Context-aware human motion prediction. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00702"},{"key":"807_CR10","doi-asserted-by":"crossref","unstructured":"Dong, M., Xu, C.: On retrospecting human dynamics with attention. In: IJCAI (2019)","DOI":"10.24963\/ijcai.2019\/100"},{"key":"807_CR11","doi-asserted-by":"crossref","unstructured":"Fragkiadaki, K., Levine, S., Felsen, P., Malik, J.: Recurrent network models for human dynamics. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.494"},{"key":"807_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"807_CR13","doi-asserted-by":"crossref","unstructured":"Hernandez, A., Gall, J., Moreno-Noguer, F.: Human motion prediction via spatio-temporal inpainting. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00723"},{"key":"807_CR14","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. IEEE Trans. Pattern Anal. Mach. Intell. (2013)","DOI":"10.1109\/TPAMI.2013.248"},{"key":"807_CR15","doi-asserted-by":"crossref","unstructured":"Jain, A., Zamir, A.R., Savarese, S., Saxena, A.: Structural-RNN: Deep learning on spatio-temporal graphs. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.573"},{"key":"807_CR16","doi-asserted-by":"crossref","unstructured":"Lea, C., Flynn, M.D., Vidal, R., Reiter, A., Hager, G.D.: Temporal convolutional networks for action segmentation and detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.113"},{"key":"807_CR17","doi-asserted-by":"crossref","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., et al.: Gradient-based learning applied to document recognition. Proc. IEEE (1998)","DOI":"10.1109\/5.726791"},{"key":"807_CR18","doi-asserted-by":"crossref","unstructured":"Li, C., Zhang, Z., Sun\u00a0Lee, W., Hee\u00a0Lee, G.: Convolutional sequence to sequence model for human dynamics. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00548"},{"key":"807_CR19","doi-asserted-by":"crossref","unstructured":"Li, M., Chen, S., Zhao, Y., Zhang, Y., Wang, Y., Tian, Q.: Dynamic multiscale graph neural networks for 3d skeleton based human motion prediction. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00029"},{"key":"807_CR20","doi-asserted-by":"crossref","unstructured":"Mao, W., Liu, M., Salzmann, M., Li, H.: Learning trajectory dependencies for human motion prediction. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00958"},{"key":"807_CR21","doi-asserted-by":"crossref","unstructured":"Martinez, J., Black, M.J., Romero, J.: On human motion prediction using recurrent neural networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.497"},{"key":"807_CR22","unstructured":"Pavllo, D., Grangier, D., Auli, M.: Quaternet: A quaternion-based recurrent model for human motion (2018). arXiv:1805.06485"},{"key":"807_CR23","unstructured":"Pavlovic, V., Rehg, J.M., MacCormick, J.: Learning switching linear models of human motion. In: NeurIPS (2001)"},{"key":"807_CR24","unstructured":"Shi, X., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., Woo, W.c.: Convolutional LSTM network: A machine learning approach for precipitation nowcasting. In: NeurIPS (2015)"},{"key":"807_CR25","unstructured":"Shu, X., Tang, J., Qi, G., Liu, W., Yang, J.: Hierarchical long short-term concurrent memory for human interaction recognition. IEEE Trans. Pattern Anal. Mach. Intell (2019)"},{"key":"807_CR26","doi-asserted-by":"crossref","unstructured":"Shu, X., Tang, J., Qi, G.J., Song, Y., Li, Z., Zhang, L.: Concurrence-aware long short-term sub-memories for person-person action recognition. In: CVPRW (2017)","DOI":"10.1109\/CVPRW.2017.270"},{"key":"807_CR27","doi-asserted-by":"crossref","unstructured":"Shu, X., Zhang, L., Sun, Y., Tang, J.: Host-Parasite: Graph LSTM-in-LSTM for Group Activity Recognition. IEEE Trans. Neural Netw. Learn. Syst (2020)","DOI":"10.1109\/TNNLS.2020.2978942"},{"key":"807_CR28","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. Int. J. Comput. Vision (2010)","DOI":"10.1007\/s11263-009-0273-6"},{"key":"807_CR29","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: AAAI (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"807_CR30","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions (2014)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"807_CR31","doi-asserted-by":"crossref","unstructured":"Tan, W.R., Chan, C.S., Aguirre, H.E., Tanaka, K.: ArtGAN: Artwork synthesis with conditional categorical GANs. In: ICIP (2017)","DOI":"10.1109\/ICIP.2017.8296985"},{"key":"807_CR32","unstructured":"Tang, J., Shu, X., Yan, R., Zhang, L.: Coherence constrained graph LSTM for group activity recognition. IEEE Trans. Pattern Anal. Mach. Intell (2019)"},{"key":"807_CR33","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Alahari, K., Schmid, C.: Learning video object segmentation with visual memory. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.480"},{"key":"807_CR34","doi-asserted-by":"crossref","unstructured":"Wang, J.M., Fleet, D.J., Hertzmann, A.: Gaussian process dynamical models for human motion. IEEE Trans. Pattern Anal. Mach. Intell (2007)","DOI":"10.1109\/TPAMI.2007.1167"},{"key":"807_CR35","doi-asserted-by":"crossref","unstructured":"Yan, R., Tang, J., Shu, X., Li, Z., Tian, Q.: Participation-contributed temporal dynamic model for group activity recognition. In: ACM MM (2018)","DOI":"10.1145\/3240508.3240572"},{"key":"807_CR36","doi-asserted-by":"crossref","unstructured":"Yan, R., Xie, L., Tang, J., Shu, X., Tian, Q.: Social Adaptive Module for Weakly-supervised Group Activity Recognition (2020). arXiv:2007.09470","DOI":"10.1007\/978-3-030-58598-3_13"},{"key":"807_CR37","doi-asserted-by":"crossref","unstructured":"Ye, Q., Li, Z., Fu, L., Zhang, Z., Yang, W., Yang, G.: Nonpeaked discriminant analysis for data representation. IEEE Trans. Neural Netw. Learn. Syst (2019)","DOI":"10.1109\/TNNLS.2019.2944869"},{"key":"807_CR38","unstructured":"Ye, Q., Yang, J., Liu, F., Zhao, C., Ye, N., Yin, T.: L1-norm distance linear discriminant analysis based on an effective iterative algorithm. IEEE Trans. Circuits Syst. Video Technol (2016)"},{"key":"807_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, J.Y., Felsen, P., Kanazawa, A., Malik, J.: Predicting 3d human dynamics from video. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00721"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-021-00807-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-021-00807-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-021-00807-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,30]],"date-time":"2022-12-30T18:19:00Z","timestamp":1672424340000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-021-00807-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,11]]},"references-count":39,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["807"],"URL":"https:\/\/doi.org\/10.1007\/s00530-021-00807-4","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2021,6,11]]},"assertion":[{"value":"14 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 May 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 June 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}