{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T21:56:30Z","timestamp":1783720590386,"version":"3.55.0"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2021,9,30]],"date-time":"2021-09-30T00:00:00Z","timestamp":1632960000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,9,30]],"date-time":"2021-09-30T00:00:00Z","timestamp":1632960000000},"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":["Machine Vision and Applications"],"published-print":{"date-parts":[[2021,11]]},"DOI":"10.1007\/s00138-021-01249-8","type":"journal-article","created":{"date-parts":[[2021,9,30]],"date-time":"2021-09-30T20:03:28Z","timestamp":1633032208000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":218,"title":["Early, intermediate and late fusion strategies for robust deep learning-based multimodal action recognition"],"prefix":"10.1007","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0944-2310","authenticated-orcid":false,"given":"Said Yacine","family":"Boulahia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdenour","family":"Amamra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed Ridha","family":"Madi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Said","family":"Daikh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,30]]},"reference":[{"key":"1249_CR1","doi-asserted-by":"crossref","unstructured":"Bouderbal, I., Amamra, A., Benatia, M.A.: How would image down-sampling and compression impact object detection in the context of self-driving vehicles? In: CSA, pp. 25\u201337 (2020)","DOI":"10.1007\/978-3-030-69418-0_3"},{"key":"1249_CR2","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: 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA), pp. 1\u20136. IEEE (2017)","DOI":"10.1109\/IPTA.2017.8310146"},{"key":"1249_CR3","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.cviu.2018.07.003","volume":"174","author":"SY Boulahia","year":"2018","unstructured":"Boulahia, S.Y., Anquetil, E., Multon, F., Kulpa, R.: Cudi3d: curvilinear displacement based approach for online 3d action detection. Comput. Vis. Image Understanding 174, 57\u201369 (2018)","journal-title":"Comput. Vis. Image Understanding"},{"key":"1249_CR4","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"1249_CR5","doi-asserted-by":"crossref","unstructured":"Chen, C., Jafari, R., Kehtarnavaz, N.: Fusion of depth, skeleton, and inertial data for human action recognition. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2712\u20132716. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472170"},{"key":"1249_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, K., Zhang, Y., He, X., Chen, W., Cheng, J., Lu, H.: Skeleton-based action recognition with shift graph convolutional network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 183\u2013192 (2020)","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"1249_CR7","doi-asserted-by":"crossref","unstructured":"Das, S., Sharma, S., Dai, R., Bremond, F., Thonnat, M.: Vpn: Learning video-pose embedding for activities of daily living. In: European Conference on Computer Vision, pp. 72\u201390. Springer (2020)","DOI":"10.1007\/978-3-030-58545-7_5"},{"key":"1249_CR8","doi-asserted-by":"crossref","unstructured":"Davoodikakhki, M., Yin, K.: Hierarchical action classification with network pruning. In: International Symposium on Visual Computing, pp. 291\u2013305. Springer (2020)","DOI":"10.1007\/978-3-030-64556-4_23"},{"key":"1249_CR9","doi-asserted-by":"publisher","first-page":"168297","DOI":"10.1109\/ACCESS.2020.3023599","volume":"8","author":"AM De Boissiere","year":"2020","unstructured":"De Boissiere, A.M., Noumeir, R.: Infrared and 3d skeleton feature fusion for rgb-d action recognition. IEEE Access 8, 168297\u2013168308 (2020)","journal-title":"IEEE Access"},{"issue":"2","key":"1249_CR10","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1007\/s10489-020-01823-z","volume":"51","author":"O Elharrouss","year":"2021","unstructured":"Elharrouss, O., Almaadeed, N., Al-Maadeed, S., Bouridane, A., Beghdadi, A.: A combined multiple action recognition and summarization for surveillance video sequences. Appl. Intell. 51(2), 690\u2013712 (2021)","journal-title":"Appl. Intell."},{"key":"1249_CR11","doi-asserted-by":"publisher","first-page":"15280","DOI":"10.1109\/ACCESS.2020.2968054","volume":"8","author":"Y Fan","year":"2020","unstructured":"Fan, Y., Weng, S., Zhang, Y., Shi, B., Zhang, Y.: Context-aware cross-attention for skeleton-based human action recognition. IEEE Access 8, 15280\u201315290 (2020)","journal-title":"IEEE Access"},{"key":"1249_CR12","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.patrec.2020.01.010","volume":"131","author":"A Franco","year":"2020","unstructured":"Franco, A., Magnani, A., Maio, D.: A multimodal approach for human activity recognition based on skeleton and rgb data. Pattern Recogn. Lett. 131, 293\u2013299 (2020)","journal-title":"Pattern Recogn. Lett."},{"key":"1249_CR13","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1016\/j.inffus.2016.09.005","volume":"35","author":"R Gravina","year":"2017","unstructured":"Gravina, R., Alinia, P., Ghasemzadeh, H., Fortino, G.: Multi-sensor fusion in body sensor networks: state-of-the-art and research challenges. Inf. Fusion 35, 68\u201380 (2017)","journal-title":"Inf. Fusion"},{"key":"1249_CR14","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, pp. 6546\u20136555 (2018)","DOI":"10.1109\/CVPR.2018.00685"},{"key":"1249_CR15","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":"1249_CR16","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":"1249_CR17","doi-asserted-by":"crossref","unstructured":"Hu, J.F., Zheng, W.S., Pan, J., Lai, J., Zhang, J.: Deep bilinear learning for rgb-d action recognition. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 335\u2013351 (2018)","DOI":"10.1007\/978-3-030-01234-2_21"},{"key":"1249_CR18","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, 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":"1249_CR19","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1016\/j.patcog.2017.07.013","volume":"72","author":"EP Ijjina","year":"2017","unstructured":"Ijjina, E.P., Chalavadi, K.M.: Human action recognition in rgb-d videos using motion sequence information and deep learning. Pattern Recogn. 72, 504\u2013516 (2017)","journal-title":"Pattern Recogn."},{"key":"1249_CR20","first-page":"1","volume":"11","author":"J Imran","year":"2019","unstructured":"Imran, J., Raman, B.: Evaluating fusion of rgb-d and inertial sensors for multimodal human action recognition. J. Ambient Intell. Hum. Comput. 11, 1\u201320 (2019)","journal-title":"J. Ambient Intell. Hum. Comput."},{"key":"1249_CR21","doi-asserted-by":"crossref","unstructured":"Islam, M.M., Iqbal, T.: Hamlet: A hierarchical multimodal attention-based human activity recognition algorithm. Preprint arXiv:2008.01148 (2020)","DOI":"10.1109\/IROS45743.2020.9340987"},{"issue":"2","key":"1249_CR22","doi-asserted-by":"publisher","first-page":"1729","DOI":"10.1109\/LRA.2021.3059624","volume":"6","author":"MM Islam","year":"2021","unstructured":"Islam, M.M., Iqbal, T.: Multi-gat: a graphical attention-based hierarchical multimodal representation learning approach for human activity recognition. IEEE Robot. Autom. Lett. 6(2), 1729\u20131736 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"1249_CR23","doi-asserted-by":"publisher","first-page":"200901","DOI":"10.1016\/j.fsidi.2019.200901","volume":"32","author":"I Jegham","year":"2020","unstructured":"Jegham, I., Khalifa, A.B., Alouani, I., Mahjoub, M.A.: Vision-based human action recognition: an overview and real world challenges. For. Sci. Int. Digital Investig. 32, 200901 (2020)","journal-title":"For. Sci. Int. Digital Investig."},{"key":"1249_CR24","unstructured":"Joze, H.R.V., Shaban, A., Iuzzolino, M.L., Koishida, K.: Mmtm: Multimodal transfer module for cnn fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13289\u201313299 (2020)"},{"key":"1249_CR25","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":"1249_CR26","doi-asserted-by":"crossref","unstructured":"Lin, W., Sun, M.T., Poovandran, R., Zhang, Z.: Human activity recognition for video surveillance. In: IEEE International Symposium on Circuits and Systems, pp. 2737\u20132740 (2008)","DOI":"10.1109\/ISCAS.2008.4542023"},{"issue":"12","key":"1249_CR27","doi-asserted-by":"publisher","first-page":"3007","DOI":"10.1109\/TPAMI.2017.2771306","volume":"40","author":"J Liu","year":"2017","unstructured":"Liu, J., Shahroudy, A., Xu, D., Kot, A.C., Wang, G.: Skeleton-based action recognition using spatio-temporal lstm network with trust gates. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 3007\u20133021 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1249_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhang, H., Chen, Z., Wang, Z., Ouyang, W.: Disentangling and unifying graph convolutions for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 143\u2013152 (2020)","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"1249_CR29","doi-asserted-by":"crossref","unstructured":"Lockhart, J.W., Pulickal, T., Weiss, G.M.: Applications of mobile activity recognition. In: Proceedings of the ACM Conference on Ubiquitous Computing, pp. 1054\u20131058 (2012)","DOI":"10.1145\/2370216.2370441"},{"key":"1249_CR30","doi-asserted-by":"crossref","unstructured":"Memmesheimer, R., Theisen, N., Paulus, D.: Gimme signals: discriminative signal encoding for multimodal activity recognition. Preprint arXiv:2003.06156 (2020)","DOI":"10.1109\/IROS45743.2020.9341699"},{"key":"1249_CR31","doi-asserted-by":"crossref","unstructured":"P\u00e9rez-R\u00faa, J.M., Vielzeuf, V., Pateux, S., Baccouche, M., Jurie, F.: Mfas: Multimodal fusion architecture search. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6966\u20136975 (2019)","DOI":"10.1109\/CVPR.2019.00713"},{"key":"1249_CR32","doi-asserted-by":"crossref","unstructured":"Pham, C., Nguyen, L., Nguyen, A., Nguyen, N., Nguyen, V.T.: Combining skeleton and accelerometer data for human fine-grained activity recognition and abnormal behaviour detection with deep temporal convolutional networks. Multimedia Tools and Applications pp. 1\u201322 (2021)","DOI":"10.1007\/s11042-021-11058-w"},{"issue":"8","key":"1249_CR33","doi-asserted-by":"publisher","first-page":"2436","DOI":"10.3390\/s20082436","volume":"20","author":"I Rodr\u00edguez-Moreno","year":"2020","unstructured":"Rodr\u00edguez-Moreno, I., Mart\u00ednez-Otzeta, J.M., Goienetxea, I., Rodriguez-Rodriguez, I., Sierra, B.: Shedding light on people action recognition in social robotics by means of common spatial patterns. Sensors 20(8), 2436 (2020)","journal-title":"Sensors"},{"key":"1249_CR34","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: Conference on Computer Vision and Pattern Recognition, pp. 1010\u20131019. IEEE (2016)","DOI":"10.1109\/CVPR.2016.115"},{"issue":"5","key":"1249_CR35","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1109\/TPAMI.2017.2691321","volume":"40","author":"A Shahroudy","year":"2017","unstructured":"Shahroudy, A., Ng, T.T., Gong, Y., Wang, G.: Deep multimodal feature analysis for action recognition in rgb+ d videos. IEEE Trans. Pattern Anal. Mach. Intell. 40(5), 1045\u20131058 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1249_CR36","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Wang, G., Ng, T.T.: Multi-modal feature fusion for action recognition in rgb-d sequences. In: 6th International Symposium on Communications, Control and Signal Processing (ISCCSP), pp. 1\u20134. IEEE (2014)","DOI":"10.1109\/ISCCSP.2014.6877819"},{"key":"1249_CR37","doi-asserted-by":"crossref","unstructured":"Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipman, A., Blake, A.: Real-time human pose recognition in parts from single depth images. In: CVPR, pp. 1297\u20131304. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995316"},{"key":"1249_CR38","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Preprint arXiv:1409.1556 (2014)"},{"key":"1249_CR39","unstructured":"Su, L., Hu, C., Li, G., Cao, D.: Msaf: Multimodal split attention fusion. Preprint arXiv:2012.07175 (2020)"},{"key":"1249_CR40","unstructured":"Tan, M., Le, Q.: Efficientnet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"1249_CR41","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"1249_CR42","doi-asserted-by":"crossref","unstructured":"Yun, K., Honorio, J., Chattopadhyay, D., Berg, T.L., Samaras, D.: Two-person interaction detection using body-pose features and multiple instance learning. In: Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp. 28\u201335. IEEE (2012)","DOI":"10.1109\/CVPRW.2012.6239234"},{"key":"1249_CR43","doi-asserted-by":"crossref","unstructured":"Zhao, R., Ali, H., Van\u00a0der Smagt, P.: Two-stream rnn\/cnn for action recognition in 3d videos. In: RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4260\u20134267. IEEE (2017)","DOI":"10.1109\/IROS.2017.8206288"},{"key":"1249_CR44","unstructured":"Zhao, Y., Liu, Z., Yang, L., Cheng, H.: Combing rgb and depth map features for human activity recognition. In: Proceedings of The Asia Pacific Signal and Information Processing Association Annual Summit and Conference, pp. 1\u20134. IEEE (2012)"},{"issue":"2","key":"1249_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2629483","volume":"6","author":"Y Zhu","year":"2015","unstructured":"Zhu, Y., Chen, W., Guo, G.: Fusing multiple features for depth-based action recognition. ACM Trans. Intell. Syst. Technol. (TIST) 6(2), 1\u201320 (2015)","journal-title":"ACM Trans. Intell. Syst. Technol. (TIST)"},{"key":"1249_CR46","doi-asserted-by":"crossref","unstructured":"Zolfaghari, M., Oliveira, G.L., Sedaghat, N., Brox, T.: Chained multi-stream networks exploiting pose, motion, and appearance for action classification and detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2904\u20132913 (2017)","DOI":"10.1109\/ICCV.2017.316"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-021-01249-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-021-01249-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-021-01249-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T03:10:58Z","timestamp":1725851458000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-021-01249-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,30]]},"references-count":46,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,11]]}},"alternative-id":["1249"],"URL":"https:\/\/doi.org\/10.1007\/s00138-021-01249-8","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,30]]},"assertion":[{"value":"8 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 September 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 September 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"121"}}