{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:20:04Z","timestamp":1780053604724,"version":"3.54.0"},"reference-count":93,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T00:00:00Z","timestamp":1660435200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T00:00:00Z","timestamp":1660435200000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1007\/s11263-022-01648-y","type":"journal-article","created":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T19:02:31Z","timestamp":1660503751000},"page":"2532-2552","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Learning Sequence Representations by Non-local Recurrent Neural Memory"],"prefix":"10.1007","volume":"130","author":[{"given":"Wenjie","family":"Pei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Canmiao","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiong","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1578-2634","authenticated-orcid":false,"given":"Guangming","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Wing","family":"Tai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,8,14]]},"reference":[{"key":"1648_CR1","unstructured":"Ba, J. L., Kiros, J. R., & Hinton, G. E. (2016). Layer normalization. arXiv preprint arXiv:1607.06450"},{"key":"1648_CR2","unstructured":"Bahdanau, D., Cho, K., & Bengio Y. (2015). Neural machine translation by jointly learning to align and translate. In ICLR."},{"key":"1648_CR3","doi-asserted-by":"crossref","unstructured":"Bello, I., Zoph, B., Vaswani, A., et\u00a0al. (2019). Attention augmented convolutional networks. In ICCV.","DOI":"10.1109\/ICCV.2019.00338"},{"key":"1648_CR4","doi-asserted-by":"crossref","unstructured":"Bertolami, R., Bunke, H., Fernandez S., et\u00a0al. (2009). A novel connectionist system for improved unconstrained handwriting recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(5).","DOI":"10.1109\/TPAMI.2008.137"},{"key":"1648_CR5","unstructured":"Brock, A., Donahue, J., Simonyan K. (2019). Large scale gan training for high fidelity natural image synthesis. In ICLR."},{"key":"1648_CR6","doi-asserted-by":"crossref","unstructured":"Buades, A., Coll, B., Morel, J. M. (2005). A non-local algorithm for image denoising. In CVPR.","DOI":"10.1109\/CVPR.2005.38"},{"key":"1648_CR7","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin S., et\u00a0al. (2019). Gcnet: Non-local networks meet squeeze-excitation networks and beyond. In ICCV workshops.","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"1648_CR8","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve G., et\u00a0al. (2020). End-to-end object detection with transformers. In ECCV.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1648_CR9","doi-asserted-by":"crossref","unstructured":"Carreira, J., & Zisserman A. (2017). Quo vadis, action recognition? A new model and the kinetics dataset. In \u201cCVPR\u201d.","DOI":"10.1109\/CVPR.2017.502"},{"key":"1648_CR10","doi-asserted-by":"crossref","unstructured":"Cho, K., Van\u00a0Merri\u00ebnboer, B., Gulcehre C., et\u00a0al. (2014). Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078","DOI":"10.3115\/v1\/D14-1179"},{"key":"1648_CR11","doi-asserted-by":"crossref","unstructured":"Choutas, V., Weinzaepfel, P., Revaud, J., et\u00a0al. (2018). Potion: Pose motion representation for action recognition. In \u201cCVPR\u201d.","DOI":"10.1109\/CVPR.2018.00734"},{"key":"1648_CR12","unstructured":"Dai, A. M., & Le, Q. V. (2015). Semi-supervised sequence learning. In NeurIPS."},{"key":"1648_CR13","doi-asserted-by":"crossref","unstructured":"Dai, Z., Yang, Z., Yang, Y., et\u00a0al. (2019). Transformer-xl: Attentive language models beyond a fixed-length context. In ACL.","DOI":"10.18653\/v1\/P19-1285"},{"key":"1648_CR14","unstructured":"Devlin, J., Chang, M. W., Lee, K., et\u00a0al. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding. In NAACL."},{"key":"1648_CR15","unstructured":"Dieng, A. B., Wang, C., Gao, J., et\u00a0al. (2017). Topicrnn: A recurrent neural network with long-range semantic dependency. In ICLR."},{"key":"1648_CR16","unstructured":"Du, Y., Wang, W., & Wang, L. (2015). Hierarchical recurrent neural network for skeleton based action recognition. In CVPR."},{"key":"1648_CR17","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., et\u00a0al. (2019). Slowfast networks for video recognition. In ICCV.","DOI":"10.1109\/ICCV.2019.00630"},{"key":"1648_CR18","doi-asserted-by":"crossref","unstructured":"Fu, C., Pei, W., Cao, Q., et\u00a0al. (2019a). Non-local recurrent neural memory for supervised sequence modeling. In ICCV.","DOI":"10.1109\/ICCV.2019.00641"},{"key":"1648_CR19","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., et\u00a0al. (2019b). Dual attention network for scene segmentation. In CVPR.","DOI":"10.1109\/CVPR.2019.00326"},{"key":"1648_CR20","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., et\u00a0al. (2019c). Dual attention network for scene segmentation. In CVPR.","DOI":"10.1109\/CVPR.2019.00326"},{"key":"1648_CR21","unstructured":"Grave, E., Joulin, A., Usunier, N. (2017). Improving neural language models with a continuous cache. In ICLR."},{"key":"1648_CR22","unstructured":"Graves, A., Wayne, G., & Danihelka, I. (2014). Neural turing machines. arXiv preprint arXiv:1410.5401"},{"key":"1648_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., et\u00a0al. (2017). Mask R-CNN. In ICCV.","DOI":"10.1109\/ICCV.2017.322"},{"issue":"8","key":"1648_CR24","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. (1997). Long short-term memory. Neural Computation, 9(8), 1735\u20131780.","journal-title":"Neural Computation"},{"key":"1648_CR25","unstructured":"Hochreiter, S., Bengio, Y., Frasconi, P., et\u00a0al. (2001). Gradient flow in recurrent nets: The difficulty of learning long-term dependencies"},{"key":"1648_CR26","doi-asserted-by":"crossref","unstructured":"Hu, H., Zhang, Z., Xie, Z., et al. (2019). Local relation networks for image recognition. In ICCV.","DOI":"10.1109\/ICCV.2019.00356"},{"key":"1648_CR27","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., et\u00a0al. (2017). Densely connected convolutional networks. In CVPR.","DOI":"10.1109\/CVPR.2017.243"},{"key":"1648_CR28","doi-asserted-by":"crossref","unstructured":"Johnson, R., & Zhang, T. (2014). Effective use of word order for text categorization with convolutional neural networks. arXiv preprint arXiv:1412.1058","DOI":"10.3115\/v1\/N15-1011"},{"key":"1648_CR29","unstructured":"Johnson, R., & Zhang, T. (2016). Supervised and semi-supervised text categorization using LSTM for region embeddings. In ICML."},{"key":"1648_CR30","unstructured":"Kay, W., Carreira, J., Simonyan, K., et\u00a0al. (2017). The kinetics human action video dataset. arXiv preprint arXiv:1705.06950"},{"key":"1648_CR31","unstructured":"Kingma, D. P., & Ba, J.(2015). Adam: A method for stochastic optimization. In ICLR."},{"key":"1648_CR32","unstructured":"Krueger, D., Maharaj, T., Kram\u00e1r, J., et\u00a0al. (2017). Zoneout: Regularizing rnns by randomly preserving hidden activations. In ICLR."},{"key":"1648_CR33","unstructured":"Kumar, A., Irsoy, O., Ondruska, P., et\u00a0al. (2016). Ask me anything: Dynamic memory networks for natural language processing. In ICML."},{"key":"1648_CR34","unstructured":"Lafferty, J. D., McCallum, A., & Pereira, F. C. (2001). Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In ICML."},{"key":"1648_CR35","doi-asserted-by":"crossref","unstructured":"Lee, I., Kim, D., Kang S., et\u00a0al. (2017). Ensemble deep learning for skeleton-based action recognition using temporal sliding LSTM networks. In ICCV.","DOI":"10.1109\/ICCV.2017.115"},{"key":"1648_CR36","unstructured":"Li, Z., & Yu, Y. (2016). Protein secondary structure prediction using cascaded convolutional and recurrent neural networks. arXiv preprint arXiv:1604.07176"},{"key":"1648_CR37","doi-asserted-by":"crossref","unstructured":"Liu, J., Shahroudy, A., Xu, D., et\u00a0al. (2016). Spatio-temporal LSTM with trust gates for 3D human action recognition. In ECCV.","DOI":"10.1007\/978-3-319-46487-9_50"},{"key":"1648_CR38","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., et\u00a0al. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1648_CR39","unstructured":"Maas, A. L., Daly, R. E., Pham, P. T., et\u00a0al. (2011). Learning word vectors for sentiment analysis. In ACL."},{"key":"1648_CR40","unstructured":"McCann, B., Bradbury, J., Xiong, C., et\u00a0al. (2017). Learned in translation: Contextualized word vectors. In NeurIPS."},{"key":"1648_CR41","unstructured":"Miyato, T., Dai, A. M., Goodfellow, I. (2017). Adversarial training methods for semi-supervised text classification. In ICLR."},{"key":"1648_CR42","doi-asserted-by":"crossref","unstructured":"Morency, L. P., Quattoni, A., & Darrell, T. (2007). Latent-dynamic discriminative models for continuous gesture recognition. In CVPR.","DOI":"10.1109\/CVPR.2007.383299"},{"key":"1648_CR43","doi-asserted-by":"crossref","unstructured":"Mueller, J., & Thyagarajan, A. (2016). Siamese recurrent architectures for learning sentence similarity. In AAAI.","DOI":"10.1609\/aaai.v30i1.10350"},{"key":"1648_CR44","unstructured":"Pei, W., Tax, D. M., & van\u00a0der Maaten, L. (2016). Modeling time series similarity with siamese recurrent networks. arXiv preprint arXiv:1603.04713"},{"key":"1648_CR45","doi-asserted-by":"crossref","unstructured":"Pei, W., Baltrusaitis, T., Tax, D. M., et\u00a0al. (2017). Temporal attention-gated model for robust sequence classification. In CVPR.","DOI":"10.1109\/CVPR.2017.94"},{"issue":"4","key":"1648_CR46","doi-asserted-by":"publisher","first-page":"920","DOI":"10.1109\/TNNLS.2017.2651018","volume":"29","author":"W Pei","year":"2018","unstructured":"Pei, W., Dibeklio\u011flu, H., Tax, D. M., et al. (2018). Multivariate time-series classification using the hidden-unit logistic model. IEEE Transactions on Neural Networks and Learning Systems, 29(4), 920\u2013931.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"1648_CR47","unstructured":"Peng, J., Bo, L., & Xu J. (2009). Conditional neural fields. In NeurIPS."},{"key":"1648_CR48","doi-asserted-by":"crossref","unstructured":"Pollastri, G., Przybylski, D., Rost, B., et\u00a0al. (2002). Improving the prediction of protein secondary structure in three and eight classes using recurrent neural networks and profiles. Proteins: Structure, Function, and Bioinformatics 47(2):228\u2013235","DOI":"10.1002\/prot.10082"},{"key":"1648_CR49","doi-asserted-by":"crossref","unstructured":"Qiu, Z., et\u00a0al. (2017). Learning spatio-temporal representation with pseudo-3d residual networks. In ICCV.","DOI":"10.1109\/ICCV.2017.590"},{"issue":"2","key":"1648_CR50","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"LR Rabiner","year":"1989","unstructured":"Rabiner, L. R. (1989). A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2), 257\u2013286.","journal-title":"Proceedings of the IEEE"},{"key":"1648_CR51","unstructured":"Radford, A., Jozefowicz, R., & Sutskever, I. (2017). Learning to generate reviews and discovering sentiment. arXiv preprint arXiv:1704.01444"},{"key":"1648_CR52","unstructured":"Ramachandran, P., Parmar, N., Vaswani, A et\u00a0al. (2019) Stand-alone self-attention in vision models. In NeurIPS."},{"issue":"3","key":"1648_CR53","first-page":"1","volume":"5","author":"DE Rumelhart","year":"1988","unstructured":"Rumelhart, D. E., Hinton, G. E., Williams, R. J., et al. (1988). Learning representations by back-propagating errors. Cognitive Modeling, 5(3), 1.","journal-title":"Cognitive Modeling"},{"key":"1648_CR54","doi-asserted-by":"crossref","unstructured":"Sak, H., Senior, A., & Beaufays, F. (2014). Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In Fifteenth annual conference of the international speech communication association.","DOI":"10.21437\/Interspeech.2014-80"},{"key":"1648_CR55","unstructured":"Santoro, A., Faulkner, R., Raposo, D., et\u00a0al. (2018). Relational recurrent neural networks. In NeurIPS."},{"key":"1648_CR56","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T. T., et\u00a0al. (2016). Ntu rgb+ d: A large scale dataset for 3d human activity analysis. In CVPR.","DOI":"10.1109\/CVPR.2016.115"},{"key":"1648_CR57","doi-asserted-by":"crossref","unstructured":"Si, C., Jing, Y., Wang, W., et\u00a0al. (2018). Skeleton-based action recognition with spatial reasoning and temporal stack learning. In ECCV.","DOI":"10.1007\/978-3-030-01246-5_7"},{"key":"1648_CR58","doi-asserted-by":"crossref","unstructured":"Sigurdsson, G. A., Varol, G., Wang, X., et\u00a0al. (2016). Hollywood in homes: Crowdsourcing data collection for activity understanding. In \u201cECCV\u201d.","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"1648_CR59","unstructured":"Simonyan, K., & Zisserman, A. (2014). Two-stream convolutional networks for action recognition in videos. In \u201cNIPS\u201d."},{"key":"1648_CR60","unstructured":"Soltani, R., & Jiang, H. (2016). Higher order recurrent neural networks. arXiv preprint arXiv:1605.00064"},{"issue":"7","key":"1648_CR61","doi-asserted-by":"publisher","first-page":"3459","DOI":"10.1109\/TIP.2018.2818328","volume":"27","author":"S Song","year":"2018","unstructured":"Song, S., Lan, C., Xing, J., et al. (2018). Spatio-temporal attention-based lstm networks for 3d action recognition and detection. IEEE Transactions on Image Processing, 27(7), 3459\u20133471.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1648_CR62","doi-asserted-by":"crossref","unstructured":"Srinivas, A., Lin, T. Y., Parmar, N., et\u00a0al. (2021). Bottleneck transformers for visual recognition. In CVPR.","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"1648_CR63","unstructured":"Sukhbaatar, S., Weston, J., Fergus, R., et\u00a0al. (2015). End-to-end memory networks. In NeurIPS."},{"key":"1648_CR64","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., et\u00a0al. (2015).Going deeper with convolutions. In CVPR.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1648_CR65","doi-asserted-by":"crossref","unstructured":"Tan, C., Wei, F., Wang, W., et\u00a0al. (2018).Multiway attention networks for modeling sentence pairs. In IJCAI.","DOI":"10.24963\/ijcai.2018\/613"},{"key":"1648_CR66","doi-asserted-by":"crossref","unstructured":"Tu, J., Liu, H., Meng, F., et\u00a0al. (2018). Spatial-temporal data augmentation based on LSTM autoencoder network for skeleton-based human action recognition. In ICIP.","DOI":"10.1109\/ICIP.2018.8451608"},{"key":"1648_CR67","unstructured":"Van Der\u00a0Maaten, L., Welling, M., & Saul, L. (2011). Hidden-unit conditional random fields. In Proceedings of the fourteenth international conference on artificial intelligence and statistics."},{"key":"1648_CR68","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et\u00a0al. (2017). Attention is all you need. In NeurIPS."},{"issue":"12","key":"1648_CR69","doi-asserted-by":"publisher","first-page":"1589","DOI":"10.1093\/bioinformatics\/btg224","volume":"19","author":"G Wang","year":"2003","unstructured":"Wang, G., & Dunbrack, R. L., Jr. (2003). Pisces: A protein sequence culling server. Bioinformatics, 19(12), 1589\u20131591.","journal-title":"Bioinformatics"},{"key":"1648_CR70","doi-asserted-by":"crossref","unstructured":"Wang, H., & Wang, L. (2017). Modeling temporal dynamics and spatial configurations of actions using two-stream recurrent neural networks. In CVPR.","DOI":"10.1109\/CVPR.2017.387"},{"issue":"1","key":"1648_CR71","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-016-0001-8","volume":"6","author":"S Wang","year":"2016","unstructured":"Wang, S., Peng, J., Ma, J., et al. (2016). Protein secondary structure prediction using deep convolutional neural fields. Scientific Reports, 6(1), 1\u201311.","journal-title":"Scientific Reports"},{"key":"1648_CR72","doi-asserted-by":"crossref","unstructured":"Wang, X., & Gupta, A. (2018). Videos as space-time region graphs. In \u201cECCV\u201d.","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"1648_CR73","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., et\u00a0al. (2018). Non-local neural networks. In CVPR.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"1648_CR74","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhao, F., Peng, J., et\u00a0al. (2010). Protein 8-class secondary structure prediction using conditional neural fields. In 2010 IEEE International conference on bioinformatics and biomedicine (BIBM) (pp. 109\u2013114).","DOI":"10.1109\/BIBM.2010.5706547"},{"key":"1648_CR75","unstructured":"Weston, J., Chopra, S., & Bordes, A. (2015). Memory networks. In ICLR."},{"key":"1648_CR76","doi-asserted-by":"crossref","unstructured":"Wu, C. Y., Feichtenhofer, C., Fan, H., et\u00a0al. (2019). Long-term feature banks for detailed video understanding. In CVPR.","DOI":"10.1109\/CVPR.2019.00037"},{"key":"1648_CR77","unstructured":"Xia, Y., Tan, X., Tian F., et\u00a0al. (2018). Model-level dual learning. In ICML."},{"key":"1648_CR78","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., et\u00a0al. (2018). Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification. In ECCV.","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"1648_CR79","unstructured":"Xiong, C., Merity, S., & Socher, R. (2016). Dynamic memory networks for visual and textual question answering. In ICML."},{"key":"1648_CR80","doi-asserted-by":"crossref","unstructured":"Yan, A., Wang, Y., Li, Z., et\u00a0al. (2019). Pa3d: Pose-action 3d machine for video recognition. In \u201cCVPR\u201d.","DOI":"10.1109\/CVPR.2019.00811"},{"key":"1648_CR81","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., & Lin, D. (2018). Spatial temporal graph convolutional networks for skeleton-based action recognition. In AAAI.","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"1648_CR82","doi-asserted-by":"crossref","unstructured":"Yang, R., Zhang, J., Gao, X., et\u00a0al. (2019). Simple and effective text matching with richer alignment features. In ACL (pp. 4699\u20134709).","DOI":"10.18653\/v1\/P19-1465"},{"key":"1648_CR83","unstructured":"Yang, Z., Dhingra, B., He, K., et\u00a0al. (2018). Glomo: Unsupervisedly learned relational graphs as transferable representations. In NeurIPS."},{"key":"1648_CR84","doi-asserted-by":"crossref","unstructured":"Yin, M., Yao, Z., Cao, Y., et\u00a0al. (2020). Disentangled non-local neural networks. In ECCV.","DOI":"10.1007\/978-3-030-58555-6_12"},{"key":"1648_CR85","unstructured":"Yu, F., & Koltun, V. (2015). Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122"},{"key":"1648_CR86","doi-asserted-by":"crossref","unstructured":"Zhang, C., & Woodland, P. C. (2018). High order recurrent neural networks for acoustic modelling. In ICASSP.","DOI":"10.1109\/ICASSP.2018.8461608"},{"key":"1648_CR87","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., et\u00a0al. (2019). Self-attention generative adversarial networks. In ICML."},{"key":"1648_CR88","doi-asserted-by":"crossref","unstructured":"Zhang, P., Lan, C., Xing, J., et\u00a0al. (2017). View adaptive recurrent neural networks for high performance human action recognition from skeleton data. In ICCV.","DOI":"10.1109\/ICCV.2017.233"},{"key":"1648_CR89","doi-asserted-by":"crossref","unstructured":"Zhang, P., Xue, J., Lan, C., et\u00a0al. (2018). Adding attentiveness to the neurons in recurrent neural networks. In ECCV.","DOI":"10.1007\/978-3-030-01240-3_9"},{"key":"1648_CR90","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jia, J., & Koltun, V. (2020). Exploring self-attention for image recognition. In CVPR.","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"1648_CR91","doi-asserted-by":"crossref","unstructured":"Zhou, B., Andonian, A., Oliva, A., et\u00a0al. (2018a). Temporal relational reasoning in videos. In \u201cECCV\u201d.","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"1648_CR92","unstructured":"Zhou, J., & Troyanskaya, O. (2014). Deep supervised and convolutional generative stochastic network for protein secondary structure prediction. In ICML (pp. 745\u2013753)."},{"issue":"4","key":"1648_CR93","first-page":"99","volume":"19","author":"J Zhou","year":"2018","unstructured":"Zhou, J., Wang, H., Zhao, Z., et al. (2018). Cnnh_pss: Protein 8-class secondary structure prediction by convolutional neural network with highway. BMC Bioinformatics, 19(4), 99\u2013109.","journal-title":"BMC Bioinformatics"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01648-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-022-01648-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01648-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,10]],"date-time":"2022-09-10T10:11:25Z","timestamp":1662804685000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-022-01648-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,14]]},"references-count":93,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["1648"],"URL":"https:\/\/doi.org\/10.1007\/s11263-022-01648-y","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,14]]},"assertion":[{"value":"2 September 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 July 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 August 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}