{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T09:07:10Z","timestamp":1754557630710,"version":"3.41.2"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030007751"},{"type":"electronic","value":"9783030007768"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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":[[2018]]},"DOI":"10.1007\/978-3-030-00776-8_57","type":"book-chapter","created":{"date-parts":[[2018,9,18]],"date-time":"2018-09-18T08:14:58Z","timestamp":1537258498000},"page":"622-632","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["DT-3DResNet-LSTM: An Architecture for Temporal Activity Recognition in Videos"],"prefix":"10.1007","author":[{"given":"Li","family":"Yao","sequence":"first","affiliation":[]},{"given":"Ying","family":"Qian","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,9,19]]},"reference":[{"key":"57_CR1","unstructured":"TRECVID Homepage. https:\/\/www-nlpir.nist.gov\/projects\/tv2018\/"},{"key":"57_CR2","doi-asserted-by":"crossref","unstructured":"Wang H., Schmid, C.: Action recognition with improved trajectories. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3551\u20133558. IEEE (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"57_CR3","doi-asserted-by":"crossref","unstructured":"Ng, J.Y.H., Hausknecht, M., Vijayanarasimhan, S., et al.: Beyond short snippets: deep networks for video classification. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 4694\u20134702. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"57_CR4","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz A, Zisserman A P.: Convolutional two-stream network fusion for video action recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition 2016, CVPR, pp. 1933\u20131941. IEEE (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"57_CR5","unstructured":"Wang, L., Xiong, Y., Wang, Z., et al.: Towards good practices for very deep two-stream convnets. arXiv preprint arXiv:1507.02159 (2015)"},{"key":"57_CR6","doi-asserted-by":"crossref","unstructured":"Yao, L., Torabi, A., Cho, K., et al.: Describing videos by exploiting temporal structure. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4507\u20134515. IEEE (2015)","DOI":"10.1109\/ICCV.2015.512"},{"key":"57_CR7","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and ImageNet. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2018, pp. 18\u201322. IEEE, Salt Lake City (2018)","DOI":"10.1109\/CVPR.2018.00685"},{"key":"57_CR8","unstructured":"Kay, W., Carreira, J., Simonyan, K., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"57_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 770\u2013778. IEEE (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"57_CR10","unstructured":"Dai, J., Li, Y., He, K., et al.: R-FCN: object detection via region-based fully convolutional networks. In: Advances in Neural Information Processing Systems, pp. 379\u2013387 (2016)"},{"key":"57_CR11","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision 2015, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"57_CR12","unstructured":"Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"issue":"2","key":"57_CR13","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JRR Uijlings","year":"2013","unstructured":"Uijlings, J.R.R., Van De Sande, K.E.A., Gevers, T., et al.: Selective search for object recognition. Int. J. Comput. Vis. 104(2), 154\u2013171 (2013)","journal-title":"Int. J. Comput. Vis."},{"key":"57_CR14","doi-asserted-by":"crossref","unstructured":"Niebles, J.C., Han, B., Fei-Fei, L.: Efficient extraction of human motion volumes by tracking. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 655\u2013662. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5540152"},{"issue":"3","key":"57_CR15","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1109\/TAC.2009.2012975","volume":"54","author":"S Oh","year":"2009","unstructured":"Oh, S., Russell, S., Sastry, S.: Markov chain Monte Carlo data association for multi-target tracking. IEEE Trans. Autom. Control 54(3), 481\u2013491 (2009)","journal-title":"IEEE Trans. Autom. Control"},{"key":"57_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/978-3-642-37431-9_8","volume-title":"Computer Vision \u2013 ACCV 2012","author":"Suna Kim","year":"2013","unstructured":"Kim, Suna, Kwak, Suha, Feyereisl, Jan, Han, Bohyung: Online multi-target tracking by large margin structured learning. In: Lee, Kyoung Mu, Matsushita, Yasuyuki, Rehg, James M., Hu, Zhanyi (eds.) ACCV 2012. LNCS, vol. 7726, pp. 98\u2013111. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-37431-9_8"},{"issue":"9","key":"57_CR17","doi-asserted-by":"publisher","first-page":"1820","DOI":"10.1109\/TPAMI.2010.232","volume":"33","author":"MD Breitenstein","year":"2011","unstructured":"Breitenstein, M.D., Reichlin, F., Leibe, B., et al.: Online multiperson tracking-by-detection from a single, uncalibrated camera. IEEE Trans. Pattern Anal. Mach. Intell. 33(9), 1820\u20131833 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"57_CR18","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.P.: Spatiotemporal multiplier networks for video action recognition. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition 2017, CVPR, pp. 7445\u20137454. IEEE (2017)","DOI":"10.1109\/CVPR.2017.787"},{"issue":"1","key":"57_CR19","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"Shuiwang Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., et al.: 3D convolutional neural networks for human action recognition. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 221\u2013231. IEEE (2013)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"57_CR20","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., et al.: Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497. IEEE (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"57_CR21","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty S, et al.: Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, pp. 1725\u20131732. IEEE (2014)","DOI":"10.1109\/CVPR.2014.223"},{"issue":"6","key":"57_CR22","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1109\/TPAMI.2017.2712608","volume":"40","author":"G Varol","year":"2017","unstructured":"Varol, G., Laptev, I., Schmid, C.: Long-term temporal convolutions for action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1510\u20131517 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"8","key":"57_CR23","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"57_CR24","doi-asserted-by":"crossref","unstructured":"Yoon, J.H., Yang, M.H., Lim, J., et al.: Bayesian multi-object tracking using motion context from multiple objects. In: 2015 IEEE Winter Conference on Applications of Computer Vision, WACV, pp. 33\u201340. IEEE (2015)","DOI":"10.1109\/WACV.2015.12"},{"key":"57_CR25","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"57_CR26","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Learning spatio-temporal features with 3D residual networks for action recognition. In: Proceedings of the ICCV Workshop on Action, Gesture, and Emotion Recognition. vol. 2, No. 3, p. 4 (2017)","DOI":"10.1109\/ICCVW.2017.373"},{"key":"57_CR27","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., et al.: Aggregated residual transformations for deep neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 5987\u20135995. IEEE (2017)","DOI":"10.1109\/CVPR.2017.634"},{"issue":"2\u20134","key":"57_CR28","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1007\/s11263-017-1013-y","volume":"126","author":"S Yeung","year":"2018","unstructured":"Yeung, S., Russakovsky, O., Jin, N., et al.: Every moment counts: dense detailed labeling of actions in complex videos. Int. J. Comput. Vis. 126(2\u20134), 375\u2013389 (2018)","journal-title":"Int. J. Comput. Vis."},{"key":"57_CR29","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: Activitynet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition\u00a02015, pp. 961\u2013970. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"57_CR30","doi-asserted-by":"crossref","unstructured":"Oh, S., Hoogs, A., Perera, A., et al.: A large-scale benchmark dataset for event recognition in surveillance video. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 3153\u20133160. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995586"}],"container-title":["Lecture Notes in Computer Science","Advances in Multimedia Information Processing \u2013 PCM 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-00776-8_57","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T18:31:29Z","timestamp":1751913089000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-00776-8_57"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030007751","9783030007768"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-00776-8_57","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"19 September 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PCM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim Conference on Multimedia","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hefei","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":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pcm2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/pcm2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}