{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:38:49Z","timestamp":1778258329115,"version":"3.51.4"},"publisher-location":"Cham","reference-count":64,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012632","type":"print"},{"value":"9783030012649","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01264-9_11","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T08:20:53Z","timestamp":1538986853000},"page":"174-192","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":84,"title":["Graph Distillation for Action Detection with Privileged Modalities"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3597-5046","authenticated-orcid":false,"given":"Zelun","family":"Luo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun-Ting","family":"Hsieh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan Carlos","family":"Niebles","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Fei-Fei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,9]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: International Conference on Machine Learning (ICML) (2009)","DOI":"10.1145\/1553374.1553380"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Buch, S., Escorcia, V., Shen, C., Ghanem, B., Niebles, J.C.: SST: single-stream temporal action proposals. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.675"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"11_CR4","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/978-1-4615-5529-2_5","volume-title":"Learning to learn","author":"R Caruana","year":"1998","unstructured":"Caruana, R.: Multitask learning. In: Thrun, S., Pratt, L. (eds.) Learning to learn, pp. 95\u2013133. Springer, Boston (1998). https:\/\/doi.org\/10.1007\/978-1-4615-5529-2_5"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., Gupta, A.: Webly supervised learning of convolutional networks. In: International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.168"},{"key":"11_CR6","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling (2014)"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Computer Vision and Pattern Recognition (CVPR) (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"11","key":"11_CR8","doi-asserted-by":"publisher","first-page":"4322","DOI":"10.1109\/TIP.2015.2462023","volume":"24","author":"Z Ding","year":"2015","unstructured":"Ding, Z., Shao, M., Fu, Y.: Missing modality transfer learning via latent low-rank constraint. IEEE Trans. Image Process. 24(11), 4322\u20134334 (2015). https:\/\/doi.org\/10.1109\/TIP.2015.2462023","journal-title":"IEEE Trans. Image Process."},{"key":"11_CR9","unstructured":"Ding, Z., Wang, P., Ogunbona, P.O., Li, W.: Investigation of different skeleton features for CNN-based 3D action recognition. arXiv preprint arXiv:1705.00835 (2017)"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. In: Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/ACPR.2015.7486569"},{"key":"11_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1007\/978-3-319-46487-9_47","volume-title":"Computer Vision \u2013 ECCV 2016","author":"V Escorcia","year":"2016","unstructured":"Escorcia, V., Caba Heilbron, F., Niebles, J.C., Ghanem, B.: DAPs: deep action proposals for action understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 768\u2013784. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_47"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Fernando, B., Habrard, A., Sebban, M., Tuytelaars, T.: Unsupervised visual domain adaptation using subspace alignment. In: International Conference on Computer Vision (ICCV), pp. 2960\u20132967 (2013)","DOI":"10.1109\/ICCV.2013.368"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"11_CR14","unstructured":"Gorban, A., et al.: Thumos challenge: action recognition with a large number of classes. In: Computer Vision and Pattern Recognition (CVPR) Workshop (2015)"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Gupta, S., Hoffman, J., Malik, J.: Cross modal distillation for supervision transfer. In: Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.309"},{"key":"11_CR16","unstructured":"Haque, A., et al.: Towards vision-based smart hospitals: a system for tracking and monitoring hand hygiene compliance. In: Proceedings of Machine Learning for Healthcare 2017 (2017)"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"11_CR18","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS Workshop (2015)"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Hoffman, J., Gupta, S., Darrell, T.: Learning with side information through modality hallucination. In: Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.96"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Jiang, L., Meng, D., Mitamura, T., Hauptmann, A.G.: Easy samples first: self-paced reranking for zero-example multimedia search. In: MM (2014)","DOI":"10.1145\/2647868.2654918"},{"key":"11_CR21","unstructured":"Kingma, P.K., Ba, J.: Adam: a method for stochastic optimization (2015)"},{"issue":"8","key":"11_CR22","doi-asserted-by":"publisher","first-page":"951","DOI":"10.1177\/0278364913478446","volume":"32","author":"HS Koppula","year":"2013","unstructured":"Koppula, H.S., Gupta, R., Saxena, A.: Learning human activities and object affordances from RGB-D videos. Int. J. Robot. Res. 32(8), 951\u2013970 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"11_CR23","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (NIPS) (2012)"},{"key":"11_CR24","unstructured":"Li, C., Zhong, Q., Xie, D., Pu, S.: Skeleton-based action recognition with convolutional neural networks. arXiv preprint arXiv:1704.07595 (2017)"},{"issue":"8","key":"11_CR25","doi-asserted-by":"publisher","first-page":"2030","DOI":"10.1109\/TPAMI.2017.2734890","volume":"40","author":"W Li","year":"2018","unstructured":"Li, W., Chen, L., Xu, D., Gool, L.V.: Visual recognition in RGB images and videos by learning from RGB-D data. IEEE Trans. Pattern Anal. Mach. Intell. 40(8), 2030\u20132036 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2017.2734890","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Li, Y., Yang, J., Song, Y., Cao, L., Luo, J., Li, J.: Learning from noisy labels with distillation. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.211"},{"key":"11_CR27","unstructured":"Liang, J., Jiang, L., Meng, D., Hauptmann, A.G.: Learning to detect concepts from webly-labeled video data. In: IJCAI (2016)"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Liu, C., Hu, Y., Li, Y., Song, S., Liu, J.: PKU-MMD: a large scale benchmark for continuous multi-modal human action understanding. arXiv preprint arXiv:1703.07475 (2017)","DOI":"10.1145\/3132734.3132739"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Liu, J., Akhtar, N., Mian, A.: Viewpoint invariant action recognition using RGB-D videos. arXiv preprint arXiv:1709.05087 (2017)","DOI":"10.1109\/DICTA.2017.8227505"},{"key":"11_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1007\/978-3-319-46487-9_50","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Liu","year":"2016","unstructured":"Liu, J., Shahroudy, A., Xu, D., Wang, G.: Spatio-temporal LSTM with trust gates for 3D human action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 816\u2013833. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_50"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Liu, J., Wang, G., Hu, P., Duan, L.Y., Kot, A.C.: Global context-aware attention LSTM networks for 3D action recognition. In: Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.391"},{"key":"11_CR32","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.patcog.2017.02.030","volume":"68","author":"M Liu","year":"2017","unstructured":"Liu, M., Liu, H., Chen, C.: Enhanced skeleton visualization for view invariant human action recognition. Pattern Recognit. 68, 346\u2013362 (2017)","journal-title":"Pattern Recognit."},{"key":"11_CR33","unstructured":"Lopez-Paz, D., Bottou, L., Sch\u00f6lkopf, B., Vapnik, V.: Unifying distillation and privileged information. In: International Conference on Learning Representations (ICLR) (2016)"},{"key":"11_CR34","unstructured":"Luo, Z., et al.: Computer vision-based descriptive analytics of seniors\u2019 daily activities for long-term health monitoring. In: Machine Learning for Healthcare (MLHC) (2018)"},{"key":"11_CR35","doi-asserted-by":"crossref","unstructured":"Luo, Z., Peng, B., Huang, D.A., Alahi, A., Fei-Fei, L.: Unsupervised learning of long-term motion dynamics for videos. In: Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.751"},{"key":"11_CR36","unstructured":"Luo, Z., Zou, Y., Hoffman, J., Fei-Fei, L.: Label efficient learning of transferable representations across domains and tasks. In: Advances in Neural Information Processing Systems (NIPS) (2017)"},{"key":"11_CR37","unstructured":"Montes, A., Salvador, A., Giro-i Nieto, X.: Temporal activity detection in untrimmed videos with recurrent neural networks. arXiv preprint arXiv:1608.08128 (2016)"},{"key":"11_CR38","doi-asserted-by":"crossref","unstructured":"Motiian, S., Piccirilli, M., Adjeroh, D.A., Doretto, G.: Information bottleneck learning using privileged information for visual recognition. In: Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.166"},{"key":"11_CR39","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/978-1-4471-4640-7_10","volume-title":"Consumer Depth Cameras for Computer Vision","author":"Bingbing Ni","year":"2013","unstructured":"Ni, B., Wang, G., Moulin, P.: RGBD-HUDaACT: a color-depth video database for human daily activity recognition. In: Consumer Depth Cameras for Computer Vision (2013)"},{"key":"11_CR40","doi-asserted-by":"crossref","unstructured":"Noury, N., et al.: Fall detection-principles and methods. In: Engineering in Medicine and Biology Society (2007)","DOI":"10.1109\/IEMBS.2007.4352627"},{"issue":"10","key":"11_CR41","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2010","unstructured":"Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345\u20131359 (2010). https:\/\/doi.org\/10.1109\/TKDE.2009.191","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"12","key":"11_CR42","doi-asserted-by":"publisher","first-page":"5680","DOI":"10.1109\/TIP.2017.2745209","volume":"26","author":"Z Qin","year":"2017","unstructured":"Qin, Z., Shelton, C.R.: Event detection in continuous video: an inference in point process approach. IEEE Trans. Image Process. 26(12), 5680\u20135691 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"11_CR43","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"11_CR44","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Neural Information Processing Systems (NIPS) (2015)"},{"key":"11_CR45","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.T., Wang, G.: NTU RGB+ D: a large scale dataset for 3D human activity analysis. In: Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"11_CR46","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Ng, T.T., Gong, Y., Wang, G.: Deep multimodal feature analysis for action recognition in RGB+ D videos. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) (2017)","DOI":"10.1109\/TPAMI.2017.2691321"},{"key":"11_CR47","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1016\/j.ins.2017.01.013","volume":"385","author":"L Shao","year":"2017","unstructured":"Shao, L., Cai, Z., Liu, L., Lu, K.: Performance evaluation of deep feature learning for RGB-D image\/video classification. Inf. Sci. 385, 266\u2013283 (2017)","journal-title":"Inf. Sci."},{"key":"11_CR48","doi-asserted-by":"crossref","unstructured":"Shi, Z., Kim, T.K.: Learning and refining of privileged information-based RNNS for action recognition from depth sequences. In: Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.498"},{"key":"11_CR49","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems (NIPS) (2014)"},{"key":"11_CR50","unstructured":"Sung, J., Ponce, C., Selman, B., Saxena, A.: Human activity detection from RGBD images. In: AAAI Workshop on Pattern, Activity and Intent Recognition (2011)"},{"key":"11_CR51","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.510"},{"issue":"5","key":"11_CR52","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1016\/j.neunet.2009.06.042","volume":"22","author":"V Vapnik","year":"2009","unstructured":"Vapnik, V., Vashist, A.: A new learning paradigm: learning using privileged information. Neural Netw. 22(5), 544\u2013557 (2009)","journal-title":"Neural Netw."},{"key":"11_CR53","unstructured":"Wang, H., Wang, L.: Learning robust representations using recurrent neural networks for skeleton based action classification and detection. In: International Conference on Multimedia & Expo Workshops (ICMEW) (2017)"},{"key":"11_CR54","unstructured":"Wang, J., Liu, Z., Wu, Y., Yuan, J.: Mining actionlet ensemble for action recognition with depth cameras. In: Computer Vision and Pattern Recognition (CVPR) (2012)"},{"key":"11_CR55","doi-asserted-by":"crossref","unstructured":"Wang, Z., Ji, Q.: Classifier learning with hidden information. In: Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/ICPR.2014.50"},{"key":"11_CR56","doi-asserted-by":"crossref","unstructured":"Xu, D., Ouyang, W., Ricci, E., Wang, X., Sebe, N.: Learning cross-modal deep representations for robust pedestrian detection. In: Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.451"},{"key":"11_CR57","doi-asserted-by":"crossref","unstructured":"Yang, H., Zhou, J.T., Cai, J., Ong, Y.S.: MIML-FCN+: multi-instance multi-label learning via fully convolutional networks with privileged information. In: Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.635"},{"key":"11_CR58","doi-asserted-by":"crossref","unstructured":"Yeung, S., Ramanathan, V., Russakovsky, O., Shen, L., Mori, G., Fei-Fei, L.: Learning to learn from noisy web videos (2017)","DOI":"10.1109\/CVPR.2017.788"},{"key":"11_CR59","unstructured":"Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: Advances in Neural Information Processing Systems (NIPS) (2014)"},{"issue":"8","key":"11_CR60","doi-asserted-by":"publisher","first-page":"1651","DOI":"10.1109\/TPAMI.2015.2491925","volume":"38","author":"M Yu","year":"2016","unstructured":"Yu, M., Liu, L., Shao, L.: Structure-preserving binary representations for RGB-D action recognition. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 38(8), 1651\u20131664 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"11_CR61","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1007\/978-3-540-74936-3_22","volume-title":"Pattern Recognition","author":"C Zach","year":"2007","unstructured":"Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime TV-$${L}^{1}$$ optical flow. In: Hamprecht, F.A., Schn\u00f6rr, C., J\u00e4hne, B. (eds.) DAGM 2007. LNCS, vol. 4713, pp. 214\u2013223. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-74936-3_22"},{"key":"11_CR62","doi-asserted-by":"crossref","unstructured":"Zhang, S., Liu, X., Xiao, J.: On geometric features for skeleton-based action recognition using multilayer LSTM networks. In: IEEE Winter Conference on Applications of Computer Vision (WACV) (2017)","DOI":"10.1109\/WACV.2017.24"},{"key":"11_CR63","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Conly, C., Athitsos, V.: A survey on vision-based fall detection. In: Conference on PErvasive Technologies Related to Assistive Environments (PETRA) (2015)","DOI":"10.1145\/2769493.2769540"},{"key":"11_CR64","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., Lin, D.: Temporal action detection with structured segment networks. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.317"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01264-9_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:47:53Z","timestamp":1665190073000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01264-9_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012632","9783030012649"],"references-count":64,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01264-9_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"9 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}