{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T02:45:24Z","timestamp":1761965124257,"version":"3.37.3"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030349943"},{"type":"electronic","value":"9783030349950"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","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":[[2019]]},"DOI":"10.1007\/978-3-030-34995-0_56","type":"book-chapter","created":{"date-parts":[[2019,11,22]],"date-time":"2019-11-22T19:02:40Z","timestamp":1574449360000},"page":"612-626","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Leveraging Pre-trained CNN Models for\u00a0Skeleton-Based Action Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7937-4149","authenticated-orcid":false,"given":"Sohaib","family":"Laraba","sequence":"first","affiliation":[]},{"given":"Jo\u00eblle","family":"Tilmanne","sequence":"additional","affiliation":[]},{"given":"Thierry","family":"Dutoit","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,11,23]]},"reference":[{"key":"56_CR1","doi-asserted-by":"crossref","unstructured":"Adel, H., Sch\u00fctze, H.: Exploring different dimensions of attention for uncertainty detection. arXiv preprint arXiv:1612.06549 (2016)","DOI":"10.18653\/v1\/E17-1003"},{"key":"56_CR2","unstructured":"Bai, S., Kolter, J.Z., Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 (2018)"},{"key":"56_CR3","unstructured":"Bengio, Y., Goodfellow, I., Courville, A.: Deep learning, vol. 1. Citeseer (2017)"},{"issue":"2","key":"56_CR4","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/72.279181","volume":"5","author":"Y Bengio","year":"1994","unstructured":"Bengio, Y., Simard, P., Frasconi, P., et al.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5(2), 157\u2013166 (1994)","journal-title":"IEEE Trans. Neural Netw."},{"key":"56_CR5","unstructured":"Broadwater, D.R., Smith, N.E.: A fine-tuned inception v3 constitutional neural network (CNN) architecture accurately distinguishes between benign and malignant breast histology. Technical report, 59 MDW San Antonio United States (2018)"},{"key":"56_CR6","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"56_CR7","doi-asserted-by":"crossref","unstructured":"Du, Y., Fu, Y., Wang, L.: Skeleton based action recognition with convolutional neural network. In: 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), pp. 579\u2013583. IEEE (2015)","DOI":"10.1109\/ACPR.2015.7486569"},{"issue":"7","key":"56_CR8","doi-asserted-by":"publisher","first-page":"3010","DOI":"10.1109\/TIP.2016.2552404","volume":"25","author":"Y Du","year":"2016","unstructured":"Du, Y., Fu, Y., Wang, L.: Representation learning of temporal dynamics for skeleton-based action recognition. IEEE Trans. Image Process. 25(7), 3010\u20133022 (2016)","journal-title":"IEEE Trans. Image Process."},{"key":"56_CR9","unstructured":"Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1110\u20131118 (2015)"},{"key":"56_CR10","doi-asserted-by":"crossref","unstructured":"Efros, A.A., Berg, A.C., Mori, G., Malik, J.: Recognizing action at a distance. In: Null, p. 726. IEEE (2003)","DOI":"10.1109\/ICCV.2003.1238420"},{"issue":"4","key":"56_CR11","first-page":"83","volume":"14","author":"H Fan","year":"2018","unstructured":"Fan, H., Zheng, L., Yan, C., Yang, Y.: Unsupervised person re-identification: clustering and fine-tuning. ACM Trans. Multimedia Comput. Commun. Appl. (TOMM) 14(4), 83 (2018)","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl. (TOMM)"},{"key":"56_CR12","doi-asserted-by":"crossref","unstructured":"Gehring, J., Auli, M., Grangier, D., Dauphin, Y.N.: A convolutional encoder model for neural machine translation. arXiv preprint arXiv:1611.02344 (2016)","DOI":"10.18653\/v1\/P17-1012"},{"key":"56_CR13","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.eswa.2017.11.028","volume":"95","author":"D Han","year":"2018","unstructured":"Han, D., Liu, Q., Fan, W.: A new image classification method using CNN transfer learning and web data augmentation. Expert Syst. Appl. 95, 43\u201356 (2018)","journal-title":"Expert Syst. Appl."},{"key":"56_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"56_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":"56_CR16","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"56_CR17","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wan, C., Probst, T., Van Gool, L.: Deep learning on lie groups for skeleton-based action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6099\u20136108 (2017)","DOI":"10.1109\/CVPR.2017.137"},{"key":"56_CR18","unstructured":"Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and $$<$$0.5 MB model size. arXiv preprint arXiv:1602.07360 (2016)"},{"issue":"10","key":"56_CR19","doi-asserted-by":"publisher","first-page":"2896","DOI":"10.1109\/TCSVT.2017.2736553","volume":"28","author":"K Kang","year":"2017","unstructured":"Kang, K., et al.: T-CNN: tubelets with convolutional neural networks for object detection from videos. IEEE Trans. Circ. Syst. Video Technol. 28(10), 2896\u20132907 (2017)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"56_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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3288\u20133297 (2017)","DOI":"10.1109\/CVPR.2017.486"},{"key":"56_CR21","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"issue":"3\u20134","key":"56_CR22","doi-asserted-by":"publisher","first-page":"e1782","DOI":"10.1002\/cav.1782","volume":"28","author":"S Laraba","year":"2017","unstructured":"Laraba, S., Brahimi, M., Tilmanne, J., Dutoit, T.: 3D skeleton-based action recognition by representing motion capture sequences as 2D-RGB images. Comput. Anim. Virtual Worlds 28(3\u20134), e1782 (2017)","journal-title":"Comput. Anim. Virtual Worlds"},{"key":"56_CR23","unstructured":"Li, C., Sun, S., Min, X., Lin, W., Nie, B., Zhang, X.: End-to-end learning of deep convolutional neural network for 3D human action recognition. In: 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), pp. 609\u2013612. IEEE (2017)"},{"issue":"5","key":"56_CR24","doi-asserted-by":"publisher","first-page":"624","DOI":"10.1109\/LSP.2017.2678539","volume":"24","author":"C Li","year":"2017","unstructured":"Li, C., Hou, Y., Wang, P., Li, W.: Joint distance maps based action recognition with convolutional neural networks. IEEE Signal Process. Lett. 24(5), 624\u2013628 (2017)","journal-title":"IEEE Signal Process. Lett."},{"key":"56_CR25","doi-asserted-by":"crossref","unstructured":"Li, Q., Qiu, Z., Yao, T., Mei, T., Rui, Y., Luo, J.: Action recognition by learning deep multi-granular spatio-temporal video representation. In: Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval, pp. 159\u2013166. ACM (2016)","DOI":"10.1145\/2911996.2912001"},{"key":"56_CR26","unstructured":"Liu, H., Tu, J., Liu, M.: Two-stream 3D convolutional neural network for skeleton-based action recognition. arXiv preprint arXiv:1705.08106 (2017)"},{"key":"56_CR27","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":"56_CR28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3","volume-title":"Information Retrieval for Music and Motion","author":"M M\u00fcller","year":"2007","unstructured":"M\u00fcller, M.: Information Retrieval for Music and Motion, vol. 2. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-74048-3"},{"key":"56_CR29","doi-asserted-by":"crossref","unstructured":"Ohn-Bar, E., Trivedi, M.: Joint angles similarities and HOG2 for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 465\u2013470 (2013)","DOI":"10.1109\/CVPRW.2013.76"},{"key":"56_CR30","unstructured":"Pascanu, R., Mikolov, T., Bengio, Y.: On the difficulty of training recurrent neural networks. In: International Conference on Machine Learning, pp. 1310\u20131318 (2013)"},{"key":"56_CR31","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1010\u20131019 (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"56_CR32","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"56_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: Thirty-first AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"56_CR34","unstructured":"Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMs. In: International Conference on Machine Learning, pp. 843\u2013852 (2015)"},{"key":"56_CR35","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"56_CR36","doi-asserted-by":"crossref","unstructured":"Veeriah, V., Zhuang, N., Qi, G.J.: Differential recurrent neural networks for action recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4041\u20134049 (2015)","DOI":"10.1109\/ICCV.2015.460"},{"key":"56_CR37","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 588\u2013595 (2014)","DOI":"10.1109\/CVPR.2014.82"},{"key":"56_CR38","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"56_CR39","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.knosys.2018.05.029","volume":"158","author":"P Wang","year":"2018","unstructured":"Wang, P., Li, W., Li, C., Hou, Y.: Action recognition based on joint trajectory maps with convolutional neural networks. Knowl.-Based Syst. 158, 43\u201353 (2018)","journal-title":"Knowl.-Based Syst."},{"key":"56_CR40","doi-asserted-by":"crossref","unstructured":"Wang, P., Li, Z., Hou, Y., Li, W.: Action recognition based on joint trajectory maps using convolutional neural networks. In: Proceedings of the 24th ACM International Conference on Multimedia, pp. 102\u2013106. ACM (2016)","DOI":"10.1145\/2964284.2967191"},{"key":"56_CR41","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"56_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Pezeshki, M., Brakel, P., Zhang, S., Bengio, C.L.Y., Courville, A.: Towards end-to-end speech recognition with deep convolutional neural networks. arXiv preprint arXiv:1701.02720 (2017)","DOI":"10.21437\/Interspeech.2016-1446"}],"container-title":["Lecture Notes in Computer Science","Computer Vision Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-34995-0_56","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T19:41:40Z","timestamp":1665085300000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-34995-0_56"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030349943","9783030349950"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-34995-0_56","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"23 November 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICVS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Vision Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thessaloniki","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"23 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icvs2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icvs2019.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}