{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T13:53:36Z","timestamp":1746194016770,"version":"3.37.3"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2020,1,14]],"date-time":"2020-01-14T00:00:00Z","timestamp":1578960000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,14]],"date-time":"2020-01-14T00:00:00Z","timestamp":1578960000000},"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":["Multimedia Systems"],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1007\/s00530-019-00645-5","type":"journal-article","created":{"date-parts":[[2020,1,14]],"date-time":"2020-01-14T18:02:37Z","timestamp":1579024957000},"page":"313-322","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Combining CNN streams of dynamic image and depth data for action recognition"],"prefix":"10.1007","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8527-1162","authenticated-orcid":false,"given":"Roshan","family":"Singh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajat","family":"Khurana","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alok Kumar Singh","family":"Kushwaha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajeev","family":"Srivastava","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,1,14]]},"reference":[{"key":"645_CR1","doi-asserted-by":"publisher","first-page":"976","DOI":"10.1016\/j.imavis.2009.11.014","volume":"28","author":"R Poppe","year":"2010","unstructured":"Poppe, R.: A survey on vision-based human action recognition. Image Vis. Comput. 28, 976\u2013990 (2010)","journal-title":"Image Vis. Comput."},{"key":"645_CR2","doi-asserted-by":"publisher","first-page":"809","DOI":"10.1109\/34.868683","volume":"22","author":"I Haritaoglu","year":"2000","unstructured":"Haritaoglu, I., Harwood, D., Davis, L.: W4: real-time surveillance of people and their activities. IEEE Trans. Pattern Anal. Mach. Intell. 22, 809\u2013830 (2000)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"645_CR3","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1007\/978-3-642-15567-3_11","volume":"6316","author":"G Taylor","year":"2010","unstructured":"Taylor, G., Fergus, R., LeCun, Y., Bregler, C.: Convolutional learning of spatio-temporal features. Lect. Notes Comput. Sci. 6316, 140\u2013153 (2010)","journal-title":"Lect. Notes Comput. Sci."},{"key":"645_CR4","first-page":"1097","volume":"12","author":"I Krizhevsky Sutskever","year":"2012","unstructured":"Krizhevsky Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. Adv. Neural. Inf. Process. Syst. 12, 1097\u20131105 (2012)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"645_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1922649.1922653","volume":"43","author":"J Aggarwal","year":"2011","unstructured":"Aggarwal, J., Ryoo, M.: Human activity analysis\u202f: a review. ACM Comput. Surv. 43, 1\u201343 (2011)","journal-title":"ACM Comput. Surv."},{"key":"645_CR6","doi-asserted-by":"crossref","unstructured":"Ofli, F., Chaudhry, R., Kurillo, G., Vidal, R., Bajcsy, R.: Berkeley MHAD\u202f: a comprehensive multimodal human action database, Proceedings IEEE workshop on applications of computer vision (2013)","DOI":"10.1109\/WACV.2013.6474999"},{"key":"645_CR7","doi-asserted-by":"crossref","unstructured":"Yun, K., Honorio, J., Chattopadhyay, D., Berg, T., Samaras, D.: Two-person interaction detection using body-pose features and multiple instance learning, Proceeding IEEE computer society conference on computer vision and pattern recognition workshops (2012)","DOI":"10.1109\/CVPRW.2012.6239234"},{"key":"645_CR8","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1007\/s11263-015-0876-z","volume":"118","author":"L Lin","year":"2016","unstructured":"Lin, L., Wang, K., Zuo, W., Wang, M., Luo, J., Zhang, L.: A deep structured model with radius margin bound for 3D human activity recognition. Int. J. Comput. Vision 118, 256\u2013273 (2016)","journal-title":"Int. J. Comput. Vision"},{"key":"645_CR9","unstructured":"Wang, J., Liu, Z., Wu, Y., Yuan, J.: Mining actionlet ensemble for action recognition with depth cameras, Proceedings IEEE Conference on computer vision and pattern recognition, pp. 1290\u20131297 (2012)"},{"key":"645_CR10","unstructured":"Sung, J., Ponce, C., Selman, B., Saxena, A.: Unstructured human activity detection from RGBD images, Proceedings IEEE Conference on robotics and automation (2011)"},{"key":"645_CR11","doi-asserted-by":"crossref","unstructured":"Foggia, P., Percannella, G., Saggese, A., Vento, M.: Recognizing human actions by a bag of visual words, Proceeding IEEE International Conference on System, Man and Cybernetics, pp. 2910\u20132915 (2013)","DOI":"10.1109\/SMC.2013.496"},{"key":"645_CR12","doi-asserted-by":"crossref","unstructured":"Chen, C., Jafari, R., Kehtarnavaz, N.: UTD-MHAD\u202f: a multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor, Proceeding IEEE International Conference of Image Processing, pp. 168\u2013172 (2015)","DOI":"10.1109\/ICIP.2015.7350781"},{"key":"645_CR13","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1007\/978-3-319-91863-1_8","volume-title":"Understanding Human Activities Through 3D Sensors","author":"Jing Zhang","year":"2018","unstructured":"Zhang, J., Li W., Wang P., Ogunbona P., Liu S., Tang C. (2018) A Large Scale RGB-D Dataset for Action Recognition. Lecture Notes in Computer Science, 101\u2013114"},{"key":"645_CR14","doi-asserted-by":"crossref","unstructured":"Oreifej, O., Liu, Z.: HON4D: histogram of oriented 4D normals for activity recognition from depth sequences, Proceedings IEEE Computer Vision and Pattern Recognition, pp. 716\u2013723 (2013)","DOI":"10.1109\/CVPR.2013.98"},{"key":"645_CR15","doi-asserted-by":"crossref","unstructured":"Yang, X., Tian, Y: Super normal vector for activity recognition using depth sequences, Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 804\u2013811 (2014)","DOI":"10.1109\/CVPR.2014.108"},{"key":"645_CR16","doi-asserted-by":"crossref","unstructured":"Li, W., Zhang, Z., Liu, Z.: Action recognition based on a bag of 3D points, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp: 9\u201314 (2010)","DOI":"10.1109\/CVPRW.2010.5543273"},{"key":"645_CR17","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wang, P., Tang, C., Li, W., Gao, Z., Ogunbona, P.: ConvNets-based action recognition from depth maps through virtual cameras and pseudocoloring, Proceedings of the 23rd ACM international conference on Multimedia, pp: 1119\u20131122 (2015)","DOI":"10.1145\/2733373.2806296"},{"key":"645_CR18","unstructured":"Wang, P., Li, W., Gao, Z., Zhang, J., Tang, C., Ogunbona, P.: Deep convolutional neural networks for action recognition using depth map sequences arXiv:1501.04686 (2015)"},{"key":"645_CR19","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. Proceedings 27th International Conference on Neural Information Processing Systems, vol. 1, pp: 568\u2013576 (2014)"},{"key":"645_CR20","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition, IEEE conference on computer vision and pattern recognition (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"645_CR21","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.patrec.2017.04.004","volume":"92","author":"L Wang","year":"2017","unstructured":"Wang, L., Ge, L., Li, R., Fang, Y.: Three-stream CNNs for action recognition. Pattern Recogn. Lett. 92, 33\u201340 (2017)","journal-title":"Pattern Recogn. Lett."},{"key":"645_CR22","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.patcog.2018.01.020","volume":"79","author":"Z Tu","year":"2018","unstructured":"Tu, Z., Xie, W., Qin, Q., Poppe, R., Veltkamp, R., Li, B., Yuan, J.: Multi-stream CNN: learning representations based on human-related regions for action recognition. Pattern Recogn. 79, 32\u201343 (2018)","journal-title":"Pattern Recogn."},{"key":"645_CR23","unstructured":"Bilen, H., Fernando, B., Gavves, E., Vedaldi, A.: Action recognition with dynamic image networks. arXiv:1612.00738 (2016)"},{"key":"645_CR24","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Li, F.: Large-scale video classification with convolutional neural networks, Proceedings IEEE Confernce of Computer Vision and Pattern Recognition, pp: 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"645_CR25","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1109\/TPAMI.2016.2558148","volume":"39","author":"B Fernando","year":"2017","unstructured":"Fernando, B., Gavves, E., Oramas, M., Ghodrati, A., Tuytelaars, T.: Rank pooling for action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39, 773\u2013787 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"645_CR26","doi-asserted-by":"crossref","unstructured":"Yang, X., Zhang, C., Tian, Y.: Recognizing actions using depth motion maps-based histograms of oriented gradients. Proceedings of ACM International Conference on Multimedia, pp: 1057\u20131060 (2012)","DOI":"10.1145\/2393347.2396382"},{"key":"645_CR27","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1109\/THMS.2015.2504550","volume":"46","author":"P Wang","year":"2016","unstructured":"Wang, P., Li, W., Gao, Z., Zhang, J., Tang, C., Ogunbona, P.: Action recognition from depth maps using deep convolutional neural networks. IEEE Trans. Hum. Mach. Syst. 46, 498\u2013509 (2016)","journal-title":"IEEE Trans. Hum. Mach. Syst."},{"key":"645_CR28","unstructured":"Simonyan, K., Zisserman A.: Very deep convolutional networks for large-scale image recognition. CoRR. arXiv:1409.1556\u00a0(2014)"},{"key":"645_CR29","doi-asserted-by":"crossref","unstructured":"Chatfield, K., Simonyan, K., Vedaldi, A., Zisserman, A.: Return of the devil in the details: delving deep into convolutional nets. CoRR.\u00a0arXiv:1405.3531 (2014)","DOI":"10.5244\/C.28.6"},{"key":"645_CR30","doi-asserted-by":"publisher","first-page":"1800","DOI":"10.1016\/j.patcog.2013.11.032","volume":"47","author":"S Althloothi","year":"2014","unstructured":"Althloothi, S., Mahoor, M., Zhang, X., Voyles, R.: Human activity recognition using multi-features and multiple kernel learning. Pattern Recogn. 47, 1800\u20131812 (2014)","journal-title":"Pattern Recogn."},{"key":"645_CR31","doi-asserted-by":"crossref","unstructured":"Li, M., Leung, H., Shum, H.: Human action recognition via skeletal and depth based feature fusion, Proceedings 9th International Conference on Motion in Games, pp: 123\u2013132 (2016)","DOI":"10.1145\/2994258.2994268"},{"key":"645_CR32","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1109\/TPAMI.2013.198","volume":"36","author":"J Wang","year":"2014","unstructured":"Wang, J., Liu, Z., Wu, Y., Yuan, J.: Learning action let ensemble for 3D human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 36, 914\u2013927 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"645_CR33","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/j.patrec.2018.04.035","volume":"115","author":"P Khaire","year":"2018","unstructured":"Khaire, P., Kumar, P., Imran, J.: Combining CNN streams of RGB-D and skeletal data for human activity recognition. Pattern Recogn. Lett. 115, 107\u2013116 (2018)","journal-title":"Pattern Recogn. Lett."},{"key":"645_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5626\/JCSE.2018.12.1.1","volume":"12","author":"S Liu","year":"2018","unstructured":"Liu, S., Wang, H.: Human activities recognition based on skeleton information via sparse representation. J. Comput. Sci. Eng. 12, 1\u201311 (2018)","journal-title":"J. Comput. Sci. Eng."},{"issue":"5","key":"645_CR35","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., Member, S.: With convolutional neural networks. IEEE Signal Process. Lett. 24(5), 624\u2013628 (2017)","journal-title":"IEEE Signal Process. Lett."},{"key":"645_CR36","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1109\/THMS.2014.2377111","volume":"45","author":"S Gaglio","year":"2015","unstructured":"Gaglio, S., Re, G., Morana, M.: Human activity recognition process using 3-D posture data. IEEE Trans. Hum. Mach. Syst. 45, 586\u2013597 (2015)","journal-title":"IEEE Trans. Hum. Mach. Syst."},{"key":"645_CR37","doi-asserted-by":"crossref","unstructured":"Hu, J., Zheng, W., Lai, J., Zhang, J: Jointly learning heterogeneous features for RGB-D activity recognition, Proceeding IEEE Conference on Computer Vision and Pattern Recognition, pp: 5344\u20135352 (2015)","DOI":"10.1109\/CVPR.2015.7299172"},{"key":"645_CR38","first-page":"175","volume":"15","author":"E Triantaphyllou","year":"1998","unstructured":"Triantaphyllou, E., Shu, B., Sanchez, S., Ray, T.: Multi-criteria decision making: an operations research approach. Encycl. Electr. Electron. Eng. 15, 175\u2013186 (1998)","journal-title":"Encycl. Electr. Electron. Eng."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-019-00645-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00530-019-00645-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-019-00645-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,13]],"date-time":"2021-01-13T21:58:15Z","timestamp":1610575095000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00530-019-00645-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,14]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,6]]}},"alternative-id":["645"],"URL":"https:\/\/doi.org\/10.1007\/s00530-019-00645-5","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2020,1,14]]},"assertion":[{"value":"21 May 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 December 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 January 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}