{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:14:15Z","timestamp":1742912055633,"version":"3.40.3"},"publisher-location":"Cham","reference-count":61,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030561499"},{"type":"electronic","value":"9783030561505"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-56150-5_8","type":"book-chapter","created":{"date-parts":[[2020,8,17]],"date-time":"2020-08-17T15:07:40Z","timestamp":1597676860000},"page":"155-172","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Action Recognition Using Co-trained Deep Convolutional Neural Networks"],"prefix":"10.1007","author":[{"given":"Le","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jagannadan","family":"Varadarajan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Pei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,8,18]]},"reference":[{"key":"8_CR1","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1109\/34.868685","volume":"22","author":"M Brand","year":"2000","unstructured":"Brand, M., Kettnaker, V.: Discovery and segmentation of activities in video. IEEE Trans. Pattern Anal. Mach. Intell. 22, 844\u2013851 (2000)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"8_CR2","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/34.910878","volume":"23","author":"AF Bobick","year":"2001","unstructured":"Bobick, A.F., Davis, J.W.: The recognition of human movement using temporal templates. IEEE Trans. Pattern Anal. Mach. Intell. 23(3), 257\u2013267 (2001)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Efros, A.A., Berg, A.C., Mori, G., Malik, J.: Recognizing action at a distance, vol. 2003 (October 2003)","DOI":"10.1109\/ICCV.2003.1238420"},{"issue":"2\u20133","key":"8_CR4","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev, I., Lindeberg, T.: Space-time interest points. Int. J. Comput. Vis. 64(2\u20133), 107\u2013123 (2005)","journal-title":"Int. J. Comput. Vis."},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., Liu, C.-L.: Action recognition by dense trajectories. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995407"},{"issue":"3","key":"8_CR6","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/s11263-007-0122-4","volume":"79","author":"JC Niebles","year":"2008","unstructured":"Niebles, J.C., Wang, H., Fei-Fei, L.: Unsupervised learning of human action categories using spatial-temporal words. Int. J. Comput. Vis. 79(3), 299\u2013318 (2008)","journal-title":"Int. J. Comput. Vis."},{"key":"8_CR7","unstructured":"Brand, M., Oliver, N., Pentland, A.: Coupled hidden Markov models for complex action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (1997)"},{"key":"8_CR8","doi-asserted-by":"publisher","first-page":"1473","DOI":"10.1109\/TCSVT.2008.2005594","volume":"18","author":"P Turaga","year":"2008","unstructured":"Turaga, P., Chellappa, R., Subrahmanian, V.S., Udrea, O.: Machine recognition of human activities: a survey. IEEE Trans. Circuits Syst. Video Technol. 18, 1473\u20131488 (2008)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"8_CR9","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: Ucf101: a dataset of 101 human actions classes from videos in the wild. Crcv-tr-12-01, UCF (2012)"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"8_CR11","unstructured":"Sutskever, I., Krizhevsky, A., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Szegedy, C.: Going deeper with convolutions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"8_CR13","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2014)"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. arXiv preprint \narXiv:1512.03385\n\n (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, L., et al.: Nonlinear regression via deep negative correlation learning. In: IEEE TPAMI (2019)","DOI":"10.1109\/TPAMI.2019.2943860"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Shi, Z., et al.: Crowd counting with deep negative correlation learning. In: CVPR, pp. 5382\u20135390 (2018)","DOI":"10.1109\/CVPR.2018.00564"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: DEL: deep embedding learning for efficient image segmentation. In: IJCAI, vol. 864, p. 870 (2018)","DOI":"10.24963\/ijcai.2018\/120"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, L., Peng, S., Winkler, S.: Persemon: a deep network for joint analysis of apparent personality, emotion and their relationship. IEEE Trans. Affect. Comput. (2019)","DOI":"10.1109\/TAFFC.2019.2951656"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, L., Varadarajan, J., Nagaratnam Suganthan, P., Ahuja, N., Moulin, P.: Robust visual tracking using oblique random forests. In: CVPR, pp. 5589\u20135598 (2017)","DOI":"10.1109\/CVPR.2017.617"},{"key":"8_CR21","first-page":"82","volume":"69","author":"L Zhang","year":"2017","unstructured":"Zhang, L., Suganthan, P.N.: Robust visual tracking via co-trained kernelized correlation filters. PR 69, 82\u201393 (2017)","journal-title":"PR"},{"issue":"10","key":"8_CR22","doi-asserted-by":"publisher","first-page":"3243","DOI":"10.1109\/TCYB.2016.2588526","volume":"47","author":"L Zhang","year":"2016","unstructured":"Zhang, L., Suganthan, P.N.: Visual tracking with convolutional random vector functional link network. IEEE Trans. Cybern. 47(10), 3243\u20133253 (2016)","journal-title":"IEEE Trans. Cybern."},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"8_CR24","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS (2014)"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Wang, L., Qiao, Y., Tang, X.: Action recognition with trajectory-pooled deep-convolutional descriptors. In: CVPR, pp. 4305\u20134314 (2015)","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, B., Wang, L., Wang, Z., Qiao, Y., Wang, H.: Real-time action recognition with enhanced motion vector CNNs. In: CVPR, pp. 2718\u20132726 (2016)","DOI":"10.1109\/CVPR.2016.297"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Misra, I., Shrivastava, A., Hebert, M.: Watch and learn: semi-supervised learning of object detectors from videos. CoRR \narxiv:1505.05769\n\n (2015)","DOI":"10.1109\/CVPR.2015.7298982"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Dai, D., Van Gool, L.: Ensemble projection for semi-supervised image classification (2013)","DOI":"10.1109\/ICCV.2013.259"},{"key":"8_CR29","unstructured":"Dai, D., Van Gool, L.: Unsupervised high-level feature learning by ensemble projection for semi-supervised image classification and image clustering. Technical report, ETH Zurich (2016)"},{"key":"8_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1007\/11957959_15","volume-title":"Toward Category-Level Object Recognition","author":"P Carbonetto","year":"2006","unstructured":"Carbonetto, P., Dork\u00f3, G., Schmid, C., K\u00fcck, H., de Freitas, N.: A semi-supervised learning approach to object recognition with spatial integration of local features and segmentation cues. In: Ponce, J., Hebert, M., Schmid, C., Zisserman, A. (eds.) Toward Category-Level Object Recognition. LNCS, vol. 4170, pp. 277\u2013300. Springer, Heidelberg (2006). \nhttps:\/\/doi.org\/10.1007\/11957959_15"},{"key":"8_CR31","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1007\/978-3-540-87479-9_48","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"S Gupta","year":"2008","unstructured":"Gupta, S., Kim, J., Grauman, K., Mooney, R.: Watch, listen and learn: co-training on captioned images and videos. In: Daelemans, W., Goethals, B., Morik, K. (eds.) ECML PKDD 2008. LNCS (LNAI), vol. 5211, pp. 457\u2013472. Springer, Heidelberg (2008). \nhttps:\/\/doi.org\/10.1007\/978-3-540-87479-9_48"},{"issue":"1","key":"8_CR32","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Wei, X., Yang, M., Kai, Y.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.P.: Spatiotemporal residual networks for video action recognition. In: NIPS (2016)","DOI":"10.1109\/CVPR.2017.787"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Y., Song, J., Wang, L., Van Gool, L., Hilliges, O.: Two-stream SR-CNNs for action recognition in videos. In: BMVC (2016)","DOI":"10.5244\/C.30.108"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR (2015)","DOI":"10.21236\/ADA623249"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Park, E., Han, X., Berg, T.L., Berg, A.C.: Combining multiple sources of knowledge in deep CNNs for action recognition. In: WACV (2016)","DOI":"10.1109\/WACV.2016.7477589"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: COLT, pp. 92\u2013100 (1998)","DOI":"10.1145\/279943.279962"},{"key":"8_CR41","doi-asserted-by":"crossref","unstructured":"Nigam, K., Ghani, R.: Analyzing the effectiveness and applicability of co-training. In: CIKM (2000)","DOI":"10.1145\/354756.354805"},{"key":"8_CR42","doi-asserted-by":"crossref","unstructured":"Levin, A., Viola, P.A., Freund, Y.: Unsupervised improvement of visual detectors using co-training. In: ICCV (2003)","DOI":"10.1109\/ICCV.2003.1238406"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Christoudias, C.M., Urtasun, R., Kapoorz, A., Darrell, T.: Co-training with noisy perceptual observations. In: CVPR, pp. 2844\u20132851 (2009)","DOI":"10.1109\/CVPR.2009.5206572"},{"key":"8_CR44","unstructured":"Goldman, S.A., Zhou, Y.: Enhancing supervised learning with unlabeled data. In: ICML (2000)"},{"key":"8_CR45","unstructured":"Zhou, Z.-H., Li, M.: Semi-supervised regression with co-training. In: IJCAI (2005)"},{"key":"8_CR46","unstructured":"Yu, S., Krishnapuram, B., Steck, H., Rao, R.B., Rosales, R.: Bayesian co-training. In: JMLR, vol. 12 (November 2011)"},{"key":"8_CR47","unstructured":"Gorban, A., et al.: THUMOS challenge: action recognition with a large number of classes (2015). \nhttp:\/\/www.thumos.info\/"},{"key":"8_CR48","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Wang","year":"2016","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20\u201336. Springer, Cham (2016). \nhttps:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"key":"8_CR49","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint \narXiv:1502.03167\n\n (2015)"},{"key":"8_CR50","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, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"8_CR51","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y.: Towards good practices for very deep two-stream convnets. arXiv preprint \narXiv:1507.02159\n\n (2015)"},{"key":"8_CR52","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-L1 optical flow. In: Hamprecht, F.A., Schn\u00f6rr, C., J\u00e4hne, B. (eds.) DAGM 2007. LNCS, vol. 4713, pp. 214\u2013223. Springer, Heidelberg (2007). \nhttps:\/\/doi.org\/10.1007\/978-3-540-74936-3_22"},{"key":"8_CR53","doi-asserted-by":"crossref","unstructured":"Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. arXiv preprint \narXiv:1408.5093\n\n (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"8_CR54","doi-asserted-by":"crossref","unstructured":"Yue-Hei Ng, J., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4694\u20134702 (2015)","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"8_CR55","doi-asserted-by":"crossref","unstructured":"Sun, L., Jia, K., Yeung, D.-Y., Shi, B.E.: Human action recognition using factorized spatio-temporal convolutional networks. In: IEEE International Conference on Computer Vision, pp. 4597\u20134605 (2015)","DOI":"10.1109\/ICCV.2015.522"},{"key":"8_CR56","doi-asserted-by":"crossref","unstructured":"Cai, Z., Wang, L., Peng, X., Qiao, Y.: Multi-view super vector for action recognition. In: IEEE conference on Computer Vision and Pattern Recognition, pp. 596\u2013603 (2014)","DOI":"10.1109\/CVPR.2014.83"},{"key":"8_CR57","unstructured":"Wang, H., Schmid, C.: Lear-Inria submission for the thumos workshop. In: ICCV Workshop on Action Recognition with a Large Number of Classes, vol. 2, p. 8 (2013)"},{"key":"8_CR58","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.cviu.2016.03.013","volume":"150","author":"X Peng","year":"2016","unstructured":"Peng, X., Wang, L., Wang, X., Qiao, Y.: Bag of visual words and fusion methods for action recognition: comprehensive study and good practice. Comput. Vis. Image Underst. 150, 109\u2013125 (2016)","journal-title":"Comput. Vis. Image Underst."},{"issue":"3","key":"8_CR59","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1007\/s11263-015-0859-0","volume":"119","author":"L Wang","year":"2016","unstructured":"Wang, L., Qiao, Y., Tang, X.: MoFAP: a multi-level representation for action recognition. Int. J. Comput. Vis. 119(3), 254\u2013271 (2016)","journal-title":"Int. J. Comput. Vis."},{"key":"8_CR60","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2625\u20132634 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"8_CR61","doi-asserted-by":"crossref","unstructured":"Zhu, W., Hu, J., Sun, G., Cao, X., Qiao, Y.: A key volume mining deep framework for action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1991\u20131999 (2016)","DOI":"10.1109\/CVPR.2016.219"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence. IJCAI 2019 International Workshops"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-56150-5_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,17]],"date-time":"2020-08-17T15:12:12Z","timestamp":1597677132000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-56150-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030561499","9783030561505"],"references-count":61,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-56150-5_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"18 August 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IJCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Joint Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macao","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":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 August 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 August 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ijcai2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.ijcai19.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}