{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T16:20:47Z","timestamp":1781194847347,"version":"3.54.1"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012397","type":"print"},{"value":"9783030012403","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\/978-3-030-01240-3_9","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T00:36:08Z","timestamp":1538786168000},"page":"136-152","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":82,"title":["Adding Attentiveness to the Neurons in Recurrent Neural Networks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8303-8930","authenticated-orcid":false,"given":"Pengfei","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4994-9343","authenticated-orcid":false,"given":"Jianru","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9145-9957","authenticated-orcid":false,"given":"Cuiling","family":"Lan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2531-3137","authenticated-orcid":false,"given":"Wenjun","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2031-2805","authenticated-orcid":false,"given":"Zhanning","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1608-8257","authenticated-orcid":false,"given":"Nanning","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,5]]},"reference":[{"key":"9_CR1","unstructured":"Al-Rfou, R., et al.: Theano: a python framework for fast computation of mathematical expressions. arXiv preprint arXiv:1605.02688, vol. 472, p. 473 (2016)"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: EMNLP, pp. 1724\u20131734. Association for Computational Linguistics, October 2014","DOI":"10.3115\/v1\/D14-1179"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"9_CR4","unstructured":"Chollet, F.: Keras (2015). https:\/\/github.com\/fchollet\/keras"},{"key":"9_CR5","unstructured":"Chollet, F.: Resnet50 model. https:\/\/github.com\/fchollet\/deep-learning-models\/releases\/download\/v0.2\/resnet50_weights_tf_dim_ordering_tf_kernels.h5"},{"key":"9_CR6","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Diba, A., Sharma, V., Van Gool, L.: Deep temporal linear encoding networks. In: CVPR, pp. 2329\u20132338 (2017)","DOI":"10.1109\/CVPR.2017.168"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR, pp. 2625\u20132634 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"9_CR9","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), pp. 1110\u20131118 (2015)","DOI":"10.1109\/ACPR.2015.7486569"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Evangelidis, G., Singh, G., Horaud, R.: Skeletal quads: human action recognition using joint quadruples. In: ICPR, pp. 4513\u20134518. IEEE (2014)","DOI":"10.1109\/ICPR.2014.772"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Gers, F.A., Schmidhuber, J., Cummins, F.: Learning to forget: continual prediction with LSTM (1999)","DOI":"10.1049\/cp:19991218"},{"issue":"Aug","key":"9_CR12","first-page":"115","volume":"3","author":"FA Gers","year":"2002","unstructured":"Gers, F.A., Schraudolph, N.N., Schmidhuber, J.: Learning precise timing with LSTM recurrent networks. JMLR 3(Aug), 115\u2013143 (2002)","journal-title":"JMLR"},{"key":"9_CR13","first-page":"85","volume":"158","author":"F Han","year":"2017","unstructured":"Han, F., Reily, B., Hoff, W., Zhang, H.: Space-time representation of people based on 3D skeletal data: a review. CVIU 158, 85\u2013105 (2017)","journal-title":"CVIU"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"9_CR15","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":"9_CR16","doi-asserted-by":"crossref","unstructured":"Hu, J.F., Zheng, W.S., Lai, J., Zhang, J.: Jointly learning heterogeneous features for RGB-D activity recognition. In: CVPR, pp. 5344\u20135352. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7299172"},{"key":"9_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1007\/978-3-319-46448-0_17","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J-F Hu","year":"2016","unstructured":"Hu, J.-F., Zheng, W.-S., Ma, L., Wang, G., Lai, J.: Real-time RGB-D activity prediction by soft regression. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 280\u2013296. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_17"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M.J.: Towards understanding action recognition. In: ICCV, pp. 3192\u20133199. IEEE (2013)","DOI":"10.1109\/ICCV.2013.396"},{"key":"9_CR19","unstructured":"Jozefowicz, R., Zaremba, W., Sutskever, I.: An empirical exploration of recurrent network architectures. In: ICML, pp. 2342\u20132350 (2015)"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Ke, Q., Bennamoun, M., An, S., Sohel, F., Boussaid, F.: A new representation of skeleton sequences for 3D action recognition. In: CVPR, pp. 4570\u20134579. IEEE (2017)","DOI":"10.1109\/CVPR.2017.486"},{"key":"9_CR21","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"9_CR22","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, pp. 2556\u20132563. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"issue":"5","key":"9_CR23","first-page":"944","volume":"19","author":"J Li","year":"2017","unstructured":"Li, J., et al.: Attentive contexts for object detection. TMM 19(5), 944\u2013954 (2017)","journal-title":"TMM"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Li, W., Wen, L., Chang, M.C., Lim, S.N., Lyu, S.: Adaptive RNN tree for large-scale human action recognition. In: Computer Vision and Pattern Recognition (CVPR), pp. 1444\u20131452 (2017)","DOI":"10.1109\/ICCV.2017.161"},{"key":"9_CR25","unstructured":"Lipton, Z.C., Berkowitz, J., Elkan, C.: A critical review of recurrent neural networks for sequence learning. arXiv preprint arXiv:1506.00019 (2015)"},{"key":"9_CR26","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":"9_CR27","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.391"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025 (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"9_CR29","unstructured":"Olah, C.: LSTM (2015). http:\/\/colah.github.io\/posts\/2015-08-Understanding-LSTMs\/"},{"key":"9_CR30","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: CVPR, June 2016","DOI":"10.1109\/CVPR.2016.115"},{"key":"9_CR31","unstructured":"Sharma, S., Kiros, R., Salakhutdinov, R.: Action recognition using visual attention. arXiv preprint arXiv:1511.04119 (2015)"},{"key":"9_CR32","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS, pp. 568\u2013576 (2014)"},{"key":"9_CR33","doi-asserted-by":"crossref","unstructured":"Song, S., Lan, C., Xing, J., Zeng, W., Liu, J.: An end-to-end spatio-temporal attention model for human action recognition from skeleton data. In: AAAI, vol. 1, p. 7 (2017)","DOI":"10.1609\/aaai.v31i1.11212"},{"issue":"1","key":"9_CR34","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. JMLR 15(1), 1929\u20131958 (2014)","journal-title":"JMLR"},{"key":"9_CR35","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: NIPS, pp. 3104\u20133112 (2014)"},{"key":"9_CR36","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS, pp. 6000\u20136010 (2017)"},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"Veeriah, V., Zhuang, N., Qi, G.J.: Differential recurrent neural networks for action recognition. In: ICCV, pp. 4041\u20134049. IEEE (2015)","DOI":"10.1109\/ICCV.2015.460"},{"key":"9_CR38","doi-asserted-by":"crossref","unstructured":"Vemulapalli, R., Arrate, F., Chellappa, R.: Human action recognition by representing 3D skeletons as points in a lie group. In: CVPR, pp. 588\u2013595 (2014)","DOI":"10.1109\/CVPR.2014.82"},{"key":"9_CR39","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: CVPR, pp. 3156\u20133164. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"9_CR40","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: ICCV, pp. 3551\u20133558 (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"9_CR41","series-title":"SpringerBriefs in Computer Science","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/978-3-319-04561-0_2","volume-title":"Human Action Recognition with Depth Cameras","author":"J Wang","year":"2014","unstructured":"Wang, J., Liu, Z., Wu, Y.: Learning actionlet ensemble for 3D human action recognition. Human Action Recognition with Depth Cameras. SCS, pp. 11\u201340. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-04561-0_2"},{"key":"9_CR42","doi-asserted-by":"crossref","unstructured":"Wang, J., Liu, Z., Wu, Y., Yuan, J.: Mining actionlet ensemble for action recognition with depth cameras. In: CVPR, pp. 1290\u20131297. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247813"},{"key":"9_CR43","doi-asserted-by":"crossref","unstructured":"Wang, J., Nie, X., Xia, Y., Wu, Y., Zhu, S.C.: Cross-view action modeling, learning and recognition. In: CVPR, pp. 2649\u20132656 (2014)","DOI":"10.1109\/CVPR.2014.339"},{"key":"9_CR44","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). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"key":"9_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1007\/978-3-319-46478-7_23","volume-title":"Computer Vision \u2013 ECCV 2016","author":"P Wang","year":"2016","unstructured":"Wang, P., Yuan, C., Hu, W., Li, B., Zhang, Y.: Graph based skeleton motion representation and similarity measurement for action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 370\u2013385. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_23"},{"key":"9_CR46","unstructured":"Wang, Y., Wang, S., Tang, J., O\u2019Hare, N., Chang, Y., Li, B.: Hierarchical attention network for action recognition in videos. arXiv preprint arXiv:1607.06416 (2016)"},{"key":"9_CR47","doi-asserted-by":"crossref","unstructured":"Xia, L., Chen, C.C., Aggarwal, J.: View invariant human action recognition using histograms of 3D joints. In: Computer Vision and Pattern Recognition Workshop (CVPRW), pp. 20\u201327. IEEE (2012)","DOI":"10.1109\/CVPRW.2012.6239233"},{"key":"9_CR48","unstructured":"Xiong, Y.: TSN model (2016). https:\/\/github.com\/yjxiong\/temporal-segment-networks"},{"key":"9_CR49","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML, pp. 2048\u20132057 (2015)"},{"key":"9_CR50","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: CVPR, pp. 4694\u20134702 (2015)","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"9_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, P., Lan, C., Xing, J., Zeng, W., Xue, J., Zheng, N.: View adaptive recurrent neural networks for high performance human action recognition from skeleton data. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.233"},{"key":"9_CR52","doi-asserted-by":"crossref","unstructured":"Zhu, W., et al.: Co-occurrence feature learning for skeleton based action recognition using regularized deep LSTM networks. In: AAAI, vol. 2, p. 8 (2016)","DOI":"10.1609\/aaai.v30i1.10451"}],"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\/978-3-030-01240-3_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:42:48Z","timestamp":1775241768000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01240-3_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012397","9783030012403"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01240-3_9","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":"5 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}