{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T15:37:47Z","timestamp":1772206667396,"version":"3.50.1"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030110239","type":"print"},{"value":"9783030110246","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-11024-6_18","type":"book-chapter","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T04:29:27Z","timestamp":1548304167000},"page":"273-286","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":104,"title":["Spatial-Temporal Attention Res-TCN for Skeleton-Based Dynamic Hand Gesture Recognition"],"prefix":"10.1007","author":[{"given":"Jingxuan","family":"Hou","sequence":"first","affiliation":[]},{"given":"Guijin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xinghao","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Jing-Hao","family":"Xue","sequence":"additional","affiliation":[]},{"given":"Rui","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Huazhong","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,1,23]]},"reference":[{"key":"18_CR1","unstructured":"Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). https:\/\/www.tensorflow.org\/, software available from tensorflow.org"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Boulahia, S., Anquetil, E., Kulpa, R., Multon, F.: HIF3D: handwriting-inspired features for 3D skeleton-based action recognition. In: ICPR (2017)","DOI":"10.1109\/ICPR.2016.7899764"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Boulahia, S.Y., Anquetil, E., Multon, F., Kulpa, R.: Dynamic hand gesture recognition based on 3D pattern assembled trajectories. In: IPTA (2017)","DOI":"10.1109\/IPTA.2017.8310146"},{"key":"18_CR4","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.cag.2018.02.009","volume":"73","author":"F Caputo","year":"2018","unstructured":"Caputo, F., Prebianca, P., Carcangiu, A., Spano, L.D., Giachetti, A.: Comparing 3D trajectories for simple mid-air gesture recognition. Comput. Graph. 73, 17\u201325 (2018)","journal-title":"Comput. Graph."},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., Guo, H., Wang, G., Zhang, L.: Motion feature augmented recurrent neural network for skeleton-based dynamic hand gesture recognition. In: ICIP (2017)","DOI":"10.1109\/ICIP.2017.8296809"},{"key":"18_CR6","unstructured":"Chen, X., Wang, G., Guo, H., Zhang, C.: Pose guided structured region ensemble network for cascaded hand pose estimation. In: Neurocomputing (2018)"},{"key":"18_CR7","unstructured":"Chollet, F., et al.: Keras (2015). https:\/\/github.com\/fchollet\/keras"},{"key":"18_CR8","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1038\/nrn755","volume":"3","author":"M Corbetta","year":"2002","unstructured":"Corbetta, M., Shulman, G.L.: Control of goal-directed and stimulus-driven attention in the brain. Nat. Rev. Neurosci. 3, 201\u2013215 (2002)","journal-title":"Nat. Rev. Neurosci."},{"issue":"7","key":"18_CR9","doi-asserted-by":"publisher","first-page":"1340","DOI":"10.1109\/TCYB.2014.2350774","volume":"45","author":"M Devanne","year":"2015","unstructured":"Devanne, M., Wannous, H., Berretti, S., Pala, P., Daoudi, M., Bimbo, A.D.: 3-D human action recognition by shape analysis of motion trajectories on riemannian manifold. IEEE Trans. Cybern. 45(7), 1340\u20131352 (2015)","journal-title":"IEEE Trans. Cybern."},{"issue":"5","key":"18_CR10","doi-asserted-by":"publisher","first-page":"1318","DOI":"10.1109\/TCYB.2013.2265378","volume":"43","author":"J Han","year":"2013","unstructured":"Han, J., Shao, L., Xu, D., Shotton, J.: Enhanced computer vision with microsoft kinect sensor: a review. IEEE Trans. Cybern. 43(5), 1318\u20131334 (2013)","journal-title":"IEEE Trans. Cybern."},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"K He","year":"2016","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630\u2013645. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_38"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"18_CR14","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Keselman, L., Woodfill, J.I., Grunnet-Jepse, A., Bhowmik, A.: Intel realsense stereoscopic depth cameras. In: CVPRW (2017)","DOI":"10.1109\/CVPRW.2017.167"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Kim, T., Reiter, A.: Interpretable 3D human action analysis with temporal convolutional networks. In: CVPR BNMW Workshop (2017)","DOI":"10.1109\/CVPRW.2017.207"},{"key":"18_CR17","unstructured":"Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Lea, C., Flynn, M.D., Vidal, R., Reiter, A., Hager, G.D.: Temporal convolutional networks for action segmentation and detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.113"},{"key":"18_CR19","unstructured":"Lin, M., Chen, Q., Yan, S.: Network in network. arXiv preprint arXiv:1312.4400 (2013)"},{"key":"18_CR20","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":"18_CR21","doi-asserted-by":"crossref","unstructured":"Molchanov, P., Gupta, S., Kim, K., Kautz, J.: Hand gesture recognition with 3D convolutional neural networks. In: CVPRW (2015)","DOI":"10.1109\/CVPRW.2015.7301342"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Moon, G., Chang, J.Y., Lee, K.M.: V2V-posenet: Voxel-to-Voxel prediction network for accurate 3D hand and human pose estimation from a single depth map. arXiv preprint arXiv:1711.07399 (2018)","DOI":"10.1109\/CVPR.2018.00533"},{"key":"18_CR23","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1016\/j.patcog.2017.10.033","volume":"76","author":"JC Nunez","year":"2018","unstructured":"Nunez, J.C., Cabido, R., Pantrigo, J.J., Montemayor, A.S., Velez, J.F.: Convolutional neural networks and long short-term memory for skeleton-based human activity and hand gesture recognition. Pattern Recognit. 76, 80\u201394 (2018)","journal-title":"Pattern Recognit."},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Ohn-Bar, E., Trivedi, M.: Joint angles similarities and HOG2 for action recognition. In: CVPRW (2013)","DOI":"10.1109\/CVPRW.2013.76"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Oreifej, O., Liu, Z.: HON4D: histogram of oriented 4D normals for activity recognition from depth sequences. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.98"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.81"},{"issue":"4","key":"18_CR27","doi-asserted-by":"publisher","first-page":"1412","DOI":"10.1109\/TIP.2015.2393054","volume":"24","author":"C Shi","year":"2015","unstructured":"Shi, C., Wang, G., Yin, X., Pei, X., He, B., Lin, X.: High-accuracy stereo matching based on adaptive ground control points. IEEE Trans. Image Process. 24(4), 1412\u20131423 (2015)","journal-title":"IEEE Trans. Image Process."},{"key":"18_CR28","unstructured":"Smedt, Q.D.: Dynamic hand gesture recognition - from traditional handcrafted to recent deep learning approaches. In: Computer Vision and Pattern Recognition [cs.CV]. Universite de Lille 1, Sciences et Technologies; CRIStAL UMR 9189, English (2017)"},{"key":"18_CR29","unstructured":"Smedt, Q.D., Wannous, H., Vandeborre, J.P.: Skeleton-based dynamic hand gesture recognition. In: CVPRW (2016)"},{"key":"18_CR30","unstructured":"Smedt, Q.D., Wannous, H., Vandeborre, J.P., Guerry, J., Saux, B.L., Filliat, D.: SHREC\u201917 track: 3D hand gesture recognition using a depth and skeletal dataset. In: Eurographics Workshop on 3D Object Retrieval (2017)"},{"key":"18_CR31","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 (2017)","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"18_CR32","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. J. Mach. Learn. Res. 15, 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"18_CR33","doi-asserted-by":"publisher","first-page":"516","DOI":"10.1364\/AO.52.000516","volume":"52","author":"G Wang","year":"2013","unstructured":"Wang, G., Yin, X., Pei, X., Shi, C.: Depth estimation for speckle projection system using progressive reliable points growing matching. Appl. Opt. 52, 516\u2013524 (2013)","journal-title":"Appl. Opt."},{"key":"18_CR34","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1016\/j.jvcir.2018.04.005","volume":"55","author":"G Wang","year":"2018","unstructured":"Wang, G., Chen, X., Guo, H., Zhang, C.: Region ensemble network: towards good practices for deep 3D hand pose estimation. J. Vis. Commun. Image Represent. 55, 404\u2013414 (2018)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"18_CR35","unstructured":"Xu, K., et al.: Show, attend and tell: Neural image caption generation with visual attention. In: ICML (2015)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-11024-6_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T01:41:02Z","timestamp":1674351662000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-11024-6_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030110239","9783030110246"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-11024-6_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"23 January 2019","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"}]}}