{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T03:01:10Z","timestamp":1790910070783,"version":"4.1.0"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2021,3,2]],"date-time":"2021-03-02T00:00:00Z","timestamp":1614643200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,3,2]],"date-time":"2021-03-02T00:00:00Z","timestamp":1614643200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1007\/s11263-021-01446-y","type":"journal-article","created":{"date-parts":[[2021,3,2]],"date-time":"2021-03-02T08:02:57Z","timestamp":1614672177000},"page":"1675-1690","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":62,"title":["Mimetics: Towards Understanding Human Actions Out of Context"],"prefix":"10.1007","volume":"129","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4223-3983","authenticated-orcid":false,"given":"Philippe","family":"Weinzaepfel","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gr\u00e9gory","family":"Rogez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,3,2]]},"reference":[{"key":"1446_CR1","unstructured":"Angelini, F., Fu, Z., Long, Y., Shao, L., & Naqvi, S. M. (2018). ActionXPose: A novel 2D multi-view pose-based algorithm for real-time human action recognition. arXiv preprint arXiv:1810.12126."},{"key":"1446_CR2","unstructured":"Bahng, H., Chun, S., Yun, S., Choo, J., & Oh, S. J. (2019). Learning de-biased representations with biased representations. arXiv."},{"key":"1446_CR3","unstructured":"Cao, C., Zhang, Y., Zhang, C., & Lu, H. (2016). Action recognition with joints-pooled 3D deep convolutional descriptors. In IJCAI."},{"key":"1446_CR4","doi-asserted-by":"crossref","unstructured":"Cao, Z., Hidalgo, G., Simon, T., Wei, S. E., & Sheikh, Y. (2018). OpenPose: Realtime multi-person 2D pose estimation using Part Affinity Fields. arXiv preprint arXiv:1812.08008.","DOI":"10.1109\/CVPR.2017.143"},{"key":"1446_CR5","doi-asserted-by":"crossref","unstructured":"Carreira, J., & Zisserman, A. (2017). Quo vadis, action recognition? A new model and the kinetics dataset. In CVPR.","DOI":"10.1109\/CVPR.2017.502"},{"key":"1446_CR6","doi-asserted-by":"crossref","unstructured":"Ch\u00e9ron, G., Laptev, I., & Schmid, C. (2015). P-CNN: Pose-based CNN features for action recognition. In ICCV.","DOI":"10.1109\/ICCV.2015.368"},{"key":"1446_CR7","doi-asserted-by":"crossref","unstructured":"Choutas, V., Weinzaepfel, P., Revaud, J., & Schmid, C. (2018). Potion: Pose motion representation for action recognition. CVPR.","DOI":"10.1109\/CVPR.2018.00734"},{"key":"1446_CR8","doi-asserted-by":"crossref","unstructured":"Donahue, J., Anne\u00a0Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., & Darrell, T. (2015). Long-term recurrent convolutional networks for visual recognition and description. In CVPR.","DOI":"10.21236\/ADA623249"},{"key":"1446_CR9","doi-asserted-by":"crossref","unstructured":"Du, W., Wang, Y., Qiao, & Y. (2017). RPAN: An end-to-end recurrent pose-attention network for action recognition in videos. In ICCV.","DOI":"10.1109\/ICCV.2017.402"},{"key":"1446_CR10","doi-asserted-by":"crossref","unstructured":"Du, Y., Fu, Y., & Wang, L. (2015a). Skeleton based action recognition with convolutional neural network. In ACPR.","DOI":"10.1109\/ACPR.2015.7486569"},{"key":"1446_CR11","unstructured":"Du, Y., Wang, W., & Wang, L. (2015b). Hierarchical recurrent neural network for skeleton based action recognition. In CVPR."},{"key":"1446_CR12","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., & He, K. (2019). Slowfast networks for video recognition. In ICCV.","DOI":"10.1109\/ICCV.2019.00630"},{"key":"1446_CR13","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., & Zisserman, A. (2016). Convolutional two-stream network fusion for video action recognition. In CVPR.","DOI":"10.1109\/CVPR.2016.213"},{"key":"1446_CR14","doi-asserted-by":"crossref","unstructured":"Ghadiyaram, D., Tran, D., & Mahajan, D. (2019). Large-scale weakly-supervised pre-training for video action recognition. In CVPR.","DOI":"10.1109\/CVPR.2019.01232"},{"key":"1446_CR15","unstructured":"Girdhar, R., & Ramanan, D. (2017). Attentional pooling for action recognition. In NIPS."},{"key":"1446_CR16","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., & Malik, J. (2015). Finding action tubes. In CVPR.","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"1446_CR17","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., & Satoh, Y. (2018). Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and ImageNet. In CVPR.","DOI":"10.1109\/CVPR.2018.00685"},{"key":"1446_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In CVPR.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1446_CR19","doi-asserted-by":"crossref","unstructured":"Iqbal, U., Garbade, M., & Gall, J. (2017). Pose for action-action for pose. In International conference on automatic face & gesture recognition (FG).","DOI":"10.1109\/FG.2017.61"},{"key":"1446_CR20","doi-asserted-by":"crossref","unstructured":"Jacquot, V., Ying, Z., & Kreiman, G. (2020). Can deep learning recognize subtle human activities. In CVPR.","DOI":"10.1109\/CVPR42600.2020.01425"},{"key":"1446_CR21","doi-asserted-by":"crossref","unstructured":"Jhuang, H., Gall, J., Zuffi, S., Schmid, C., & Black, M. J. (2013). Towards understanding action recognition. In ICCV.","DOI":"10.1109\/ICCV.2013.396"},{"key":"1446_CR22","doi-asserted-by":"crossref","unstructured":"Kalogeiton, V., Weinzaepfel, P., Ferrari, V., & Schmid, C. (2017). Action tubelet detector for spatio-temporal action localization. In ICCV.","DOI":"10.1109\/ICCV.2017.472"},{"key":"1446_CR23","unstructured":"Kay, W., Carreira, J., Simonyan, K., Zhang, B., Hillier, C., Vijayanarasimhan, S., Viola, F., Green, T., Back, T., Natsev, P, et\u00a0al. (2017). The Kinetics human action video dataset. arXiv preprint arXiv:1705.06950."},{"key":"1446_CR24","doi-asserted-by":"crossref","unstructured":"Khosla, A., Zhou, T., Malisiewicz, T., Efros, A. A., & Torralba, A. (2012). Undoing the damage of dataset bias. In ECCV.","DOI":"10.1007\/978-3-642-33718-5_12"},{"key":"1446_CR25","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, & T., Serre, T. (2011). HMDB: A large video database for human motion recognition. In ICCV.","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"1446_CR26","doi-asserted-by":"crossref","unstructured":"Li, Y., Li, Y., & Vasconcelos, N. (2018). Resound: Towards action recognition without representation bias. In ECCV.","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"1446_CR27","doi-asserted-by":"crossref","unstructured":"Li, Y., & Vasconcelos, N. (2019). Repair: Removing representation bias by dataset resampling. In CVPR.","DOI":"10.1109\/CVPR.2019.00980"},{"key":"1446_CR28","doi-asserted-by":"crossref","unstructured":"Liu, J., Shahroudy, A., Xu, D., & Wang, G. (2016). Spatio-temporal LSTM with trust gates for 3D human action recognition. In ECCV.","DOI":"10.1007\/978-3-319-46487-9_50"},{"key":"1446_CR29","doi-asserted-by":"crossref","unstructured":"Liu, M., & Yuan, J. (2018). Recognizing human actions as the evolution of pose estimation maps. In CVPR.","DOI":"10.1109\/CVPR.2018.00127"},{"key":"1446_CR30","doi-asserted-by":"crossref","unstructured":"Luvizon, D. C., Picard, D., & Tabia, H. (2018). 2D\/3D pose estimation and action recognition using multitask deep learning. In CVPR.","DOI":"10.1109\/CVPR.2018.00539"},{"key":"1446_CR31","doi-asserted-by":"crossref","unstructured":"McNally, W., Wong, A., & McPhee, J. (2019). STAR-Net: Action recognition using spatio-temporal activation reprojection. In CRV.","DOI":"10.1109\/CRV.2019.00015"},{"key":"1446_CR32","doi-asserted-by":"publisher","unstructured":"Mehta, D., Sridhar, S., Sotnychenko, O., Rhodin, H., Shafiei, M., Seidel, H. P., et al. (2017). VNect: Real-time 3D human pose estimation with a single RGB camera. ACM Transactions on Graphics. https:\/\/doi.org\/10.1145\/3072959.3073596.","DOI":"10.1145\/3072959.3073596"},{"key":"1446_CR33","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. In NIPS."},{"key":"1446_CR34","doi-asserted-by":"crossref","unstructured":"Rogez, G., Weinzaepfel, P., & Schmid, C. (2020). LCR-Net++: Multi-person 2D and 3D pose detection in natural images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(5), 1146\u20131161.","DOI":"10.1109\/TPAMI.2019.2892985"},{"key":"1446_CR35","doi-asserted-by":"crossref","unstructured":"Saha, S., Singh, G., Sapienza, M., Torr, P. H., & Cuzzolin, F. (2016). Deep learning for detecting multiple space-time action tubes in videos. In BMVC.","DOI":"10.5244\/C.30.58"},{"key":"1446_CR36","doi-asserted-by":"crossref","unstructured":"Sevilla-Lara, L., Liao, Y., G\u00fcney, F., Jampani, V., Geiger, A., & Black, M. J. (2018). On the integration of optical flow and action recognition. In GCPR.","DOI":"10.1007\/978-3-030-12939-2_20"},{"key":"1446_CR37","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T. T., & Wang, G. (2016). NTU RGB+D: A large scale dataset for 3D human activity analysis. In CVPR","DOI":"10.1109\/CVPR.2016.115"},{"key":"1446_CR38","doi-asserted-by":"crossref","unstructured":"Si, C., Jing, Y., Wang, W., Wang, L., & Tan, T. (2018). Skeleton-based action recognition with spatial reasoning and temporal stack learning. In ECCV.","DOI":"10.1007\/978-3-030-01246-5_7"},{"key":"1446_CR39","unstructured":"Simonyan, K., & Zisserman, A. (2014). Two-stream convolutional networks for action recognition in videos. In NIPS."},{"key":"1446_CR40","doi-asserted-by":"crossref","unstructured":"Singh, G., Saha, S., Sapienza, M., Torr, P. H., & Cuzzolin, F. (2017). Online real-time multiple spatiotemporal action localisation and prediction. In ICCV.","DOI":"10.1109\/ICCV.2017.393"},{"key":"1446_CR41","unstructured":"Soomro, K., Zamir, A. R., & Shah, M. (2012). UCF101: A dataset of 101 human actions classes from videos in the wild. In CRCV-TR-12-01."},{"key":"1446_CR42","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015). Going deeper with convolutions. In CVPR.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1446_CR43","doi-asserted-by":"crossref","unstructured":"Torralba, A., & Efros, A. A., et\u00a0al. (2011). Unbiased look at dataset bias. In CVPR.","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"1446_CR44","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015). Learning spatiotemporal features with 3D convolutional networks. In ICCV.","DOI":"10.1109\/ICCV.2015.510"},{"key":"1446_CR45","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., & Paluri, M. (2018). A closer look at spatiotemporal convolutions for action recognition. In CVPR.","DOI":"10.1109\/CVPR.2018.00675"},{"key":"1446_CR46","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., & Van Gool, L. (2016). Temporal segment networks: Towards good practices for deep action recognition. In ECCV.","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"1446_CR47","unstructured":"Wang, W., Zhang, J., Si, C., & Wang, L. (2018). Pose-based two-stream relational networks for action recognition in videos. arXiv preprint arXiv:1805.08484."},{"key":"1446_CR48","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., Harchaoui, Z., & Schmid, C. (2015). Learning to track for spatio-temporal action localization. In ICCV.","DOI":"10.1109\/ICCV.2015.362"},{"key":"1446_CR49","doi-asserted-by":"crossref","unstructured":"Weng, J., Liu, M., Jiang, X., & Yuan, J. (2018). Deformable pose traversal convolution for 3d action and gesture recognition. In ECCV.","DOI":"10.1007\/978-3-030-01234-2_9"},{"key":"1446_CR50","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., & He, K. (2017). Aggregated residual transformations for deep neural networks. In CVPR.","DOI":"10.1109\/CVPR.2017.634"},{"key":"1446_CR51","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., & Murphy, K. (2018). Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification. In ECCV.","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"1446_CR52","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., & Lin, D. (2018). Spatial temporal graph convolutional networks for skeleton-based action recognition. In AAAI.","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"1446_CR53","doi-asserted-by":"crossref","unstructured":"Yao, A., Gall, J., & van Gool, L. (2012). Coupled action recognition and pose estimation from multiple views. In IJCV.","DOI":"10.1007\/s11263-012-0532-9"},{"key":"1446_CR54","unstructured":"Zach, C., Pock, T., & Bischof, H. (2007). A duality based approach for realtime TV-L1 optical flow. In: Joint pattern recognition symposium."},{"key":"1446_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, W., Zhu, M., & Derpanis, K. G. (2013). From actemes to action: A strongly-supervised representation for detailed action understanding. In ICCV.","DOI":"10.1109\/ICCV.2013.280"},{"key":"1446_CR56","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). Learning deep features for discriminative localization. In CVPR.","DOI":"10.1109\/CVPR.2016.319"},{"key":"1446_CR57","unstructured":"Zhu, J., Zou, W., Xu, L., Hu, Y., Zhu, Z., Chang, M., Huang, J., Huang, G., & Du, D. (2018). Action machine: Rethinking action recognition in trimmed videos. arXiv preprint arXiv:1812.05770."},{"key":"1446_CR58","doi-asserted-by":"crossref","unstructured":"Zhu, W., Lan, C., Xing, J., Li, Y., Shen, L., Zeng, W., & Xie, X. (2016). Co-occurrence feature learning for skeleton based action recognition using regularized deep LSTM networks. In AAAI.","DOI":"10.1609\/aaai.v30i1.10451"},{"key":"1446_CR59","doi-asserted-by":"crossref","unstructured":"Zolfaghari, M., Oliveira, G. L., Sedaghat, N., Brox, T. (2017). Chained multi-stream networks exploiting pose, motion, and appearance for action classification and detection. In ICCV.","DOI":"10.1109\/ICCV.2017.316"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01446-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-021-01446-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01446-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T16:37:41Z","timestamp":1671467861000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-021-01446-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,2]]},"references-count":59,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2021,5]]}},"alternative-id":["1446"],"URL":"https:\/\/doi.org\/10.1007\/s11263-021-01446-y","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,2]]},"assertion":[{"value":"9 April 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 February 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 March 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}