{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:58:03Z","timestamp":1780588683444,"version":"3.54.1"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,11,6]],"date-time":"2021-11-06T00:00:00Z","timestamp":1636156800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,11,6]],"date-time":"2021-11-06T00:00:00Z","timestamp":1636156800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100004410","name":"T\u00fcrkiye Bilimsel ve Teknolojik Arastirma Kurumu","doi-asserted-by":"publisher","award":["116E102"],"award-info":[{"award-number":["116E102"]}],"id":[{"id":"10.13039\/501100004410","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1007\/s11760-021-02028-8","type":"journal-article","created":{"date-parts":[[2021,11,6]],"date-time":"2021-11-06T14:02:37Z","timestamp":1636207357000},"page":"865-872","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Comparison of 2D and 3D attention mechanisms for human (collective) activity recognition"],"prefix":"10.1007","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8716-6297","authenticated-orcid":false,"given":"Cemil","family":"Zalluhoglu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nazli","family":"Ikizler-Cinbis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,11,6]]},"reference":[{"key":"2028_CR1","doi-asserted-by":"crossref","unstructured":"Addabbo, P., Bernardi, M.L., Biondi, F., Cimitile, M., Clemente, C., Orlando, D.: Gait recognition using fmcw radar and temporal convolutional deep neural networks. In: 2020 IEEE 7th International Workshop on Metrology for AeroSpace (MetroAeroSpace), pp. 171\u2013175 (2020)","DOI":"10.1109\/MetroAeroSpace48742.2020.9160199"},{"key":"2028_CR2","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"2028_CR3","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":"2028_CR4","doi-asserted-by":"publisher","first-page":"117365","DOI":"10.1109\/ACCESS.2020.3004284","volume":"8","author":"Q Chen","year":"2020","unstructured":"Chen, Q., Zhang, W., Lou, Y.: Forecasting stock prices using a hybrid deep learning model integrating attention mechanism, multi-layer perceptron, and bidirectional long-short term memory neural network. IEEE Access 8, 117365\u2013117376 (2020)","journal-title":"IEEE Access"},{"key":"2028_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, L.C., Huang, Y.H., Wu, M.E.: Applied attention-based lstm neural networks in stock prediction. In: 2018 IEEE International Conference on Big Data (Big Data), pp. 4716\u20134718. IEEE (2018)","DOI":"10.1109\/BigData.2018.8622541"},{"key":"2028_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, Y.: Semi-supervised learning for neural machine translation. In: Joint Training for Neural Machine Translation, pp. 25\u201340. Springer (2019)","DOI":"10.1007\/978-981-32-9748-7_3"},{"key":"2028_CR7","unstructured":"Choi, W., Shahid, K., Savarese, S.: What are they doing?: Collective activity classification using spatio-temporal relationship among people. In: EEE International Conference on Computer Vision Workshops (ICCV Workshops), pp. 1282\u20131289. IEEE (2009)"},{"key":"2028_CR8","doi-asserted-by":"crossref","unstructured":"Fukui, H., Hirakawa, T., Yamashita, T., Fujiyoshi, H.: Attention branch network: Learning of attention mechanism for visual explanation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10705\u201310714 (2019)","DOI":"10.1109\/CVPR.2019.01096"},{"key":"2028_CR9","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 (CVPR), pp. 6546\u20136555 (2018)","DOI":"10.1109\/CVPR.2018.00685"},{"key":"2028_CR10","unstructured":"He, D., Li, F., Zhao, Q., Long, X., Fu, Y., Wen, S.: Exploiting spatial-temporal modelling and multi-modal fusion for human action recognition. arXiv preprint arXiv:1806.10319 (2018)"},{"key":"2028_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"1","key":"2028_CR12","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3d convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2028_CR13","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1097\u20131105 (2012)"},{"key":"2028_CR14","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: Proceedings of the International Conference on Computer Vision (ICCV) (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"2028_CR15","doi-asserted-by":"crossref","unstructured":"Lei, J., Jia, Y., Peng, B., Huang, Q.: Channel-wise temporal attention network for video action recognition. In: 2019 IEEE International Conference on Multimedia and Expo (ICME), pp. 562\u2013567. IEEE (2019)","DOI":"10.1109\/ICME.2019.00103"},{"key":"2028_CR16","unstructured":"Li, H., Shen, Y., Zhu, Y.: Stock price prediction using attention-based multi-input lstm. In: Asian conference on machine learning, pp. 454\u2013469. PMLR (2018)"},{"key":"2028_CR17","doi-asserted-by":"crossref","unstructured":"Li, L., Gan, Z., Cheng, Y., Liu, J.: Relation-aware graph attention network for visual question answering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.01041"},{"key":"2028_CR18","doi-asserted-by":"crossref","unstructured":"Lin, W., Mi, Y., Wu, J., Lu, K., Xiong, H.: Action recognition with coarse-to-fine deep feature integration and asynchronous fusion. arXiv preprint arXiv:1711.07430 (2017)","DOI":"10.1609\/aaai.v32i1.12232"},{"key":"2028_CR19","doi-asserted-by":"crossref","unstructured":"Liu, J., Rojas, J., Liang, Z., Li, Y., Guan, Y.: A graph attention spatio-temporal convolutional network for 3d human pose estimation in video. arXiv preprint arXiv:2003.14179 (2020)","DOI":"10.1109\/ICRA48506.2021.9561605"},{"issue":"2","key":"2028_CR20","doi-asserted-by":"publisher","first-page":"102178","DOI":"10.1016\/j.ipm.2019.102178","volume":"57","author":"M Liu","year":"2020","unstructured":"Liu, M., Li, L., Hu, H., Guan, W., Tian, J.: Image caption generation with dual attention mechanism. Inf. Process. Manage. 57(2), 102178 (2020)","journal-title":"Inf. Process. Manage."},{"key":"2028_CR21","doi-asserted-by":"crossref","unstructured":"Liu, R., Shen, J., Wang, H., Chen, C., Cheung, S.c., Asari, V.: Attention mechanism exploits temporal contexts: Real-time 3d human pose reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5064\u20135073 (2020)","DOI":"10.1109\/CVPR42600.2020.00511"},{"issue":"5","key":"2028_CR22","doi-asserted-by":"publisher","first-page":"1596","DOI":"10.1007\/s11263-021-01436-0","volume":"129","author":"R Liu","year":"2021","unstructured":"Liu, R., Shen, J., Wang, H., Chen, C., Cheung, S.C., Asari, V.K.: Enhanced 3d human pose estimation from videos by using attention-based neural network with dilated convolutions. Int. J. Comput. Vis. 129(5), 1596\u20131615 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"2028_CR23","doi-asserted-by":"crossref","unstructured":"Martin, P.E., Benois-Pineau, J., P\u00e9teri, R., Morlier, J.: 3d attention mechanism for fine-grained classification of table tennis strokes using a twin spatio-temporal convolutional neural networks. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 6019\u20136026. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412742"},{"key":"2028_CR24","unstructured":"Sharma, S., Kiros, R., Salakhutdinov, R.: Action recognition using visual attention. In: Neural Information Processing Systems (NIPS) Time Series Workshop (2015)"},{"key":"2028_CR25","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Adv. Neural. Inf. Process. Syst., pp. 568\u2013576 (2014)"},{"key":"2028_CR26","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)"},{"key":"2028_CR27","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"2028_CR28","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in neural information processing systems, pp. 3104\u20133112 (2014)"},{"key":"2028_CR29","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: Advances in neural information processing systems, pp. 5998\u20136008 (2017)"},{"key":"2028_CR30","doi-asserted-by":"crossref","unstructured":"Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., Wang, X., Tang, X.: Residual attention network for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2017)","DOI":"10.1109\/CVPR.2017.683"},{"issue":"3\u20134","key":"2028_CR31","first-page":"229","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3\u20134), 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"2028_CR32","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: Neural image caption generation with visual attention. In: International conference on machine learning, pp. 2048\u20132057 (2015)"},{"key":"2028_CR33","doi-asserted-by":"publisher","first-page":"107329","DOI":"10.1016\/j.sigpro.2019.107329","volume":"167","author":"S Yan","year":"2020","unstructured":"Yan, S., Xie, Y., Wu, F., Smith, J.S., Lu, W., Zhang, B.: Image captioning via hierarchical attention mechanism and policy gradient optimization. Signal Process. 167, 107329 (2020)","journal-title":"Signal Process."},{"key":"2028_CR34","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 21\u201329 (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"2028_CR35","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4651\u20134659 (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"2028_CR36","doi-asserted-by":"crossref","unstructured":"Zalluhoglu, C., Ikizler-Cinbis, N.: Collective sports: A multi-task dataset for collective activity recognition. Image and Vision Computing p. 103870 (2020)","DOI":"10.1016\/j.imavis.2020.103870"},{"key":"2028_CR37","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Mishra, S., Gligorijevic, J., Bhatia, T., Bhamidipati, N.: Understanding consumer journey using attention based recurrent neural networks. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 3102\u20133111 (2019)","DOI":"10.1145\/3292500.3330753"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-021-02028-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-021-02028-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-021-02028-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,14]],"date-time":"2023-01-14T15:58:57Z","timestamp":1673711937000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-021-02028-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,6]]},"references-count":37,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["2028"],"URL":"https:\/\/doi.org\/10.1007\/s11760-021-02028-8","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,6]]},"assertion":[{"value":"16 February 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 August 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 September 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 November 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}