{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:24:27Z","timestamp":1740122667494,"version":"3.37.3"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2021,8,2]],"date-time":"2021-08-02T00:00:00Z","timestamp":1627862400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,8,2]],"date-time":"2021-08-02T00:00:00Z","timestamp":1627862400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2018YFC2001600, 2018YFC2001602"],"award-info":[{"award-number":["2018YFC2001600, 2018YFC2001602"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61473150"],"award-info":[{"award-number":["61473150"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1007\/s10489-021-02631-9","type":"journal-article","created":{"date-parts":[[2021,8,2]],"date-time":"2021-08-02T00:02:25Z","timestamp":1627862545000},"page":"5015-5033","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["A novel deep pixel restoration video prediction algorithm integrating attention mechanism"],"prefix":"10.1007","volume":"52","author":[{"given":"Muxuan","family":"Yuan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qun","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,8,2]]},"reference":[{"key":"2631_CR1","doi-asserted-by":"crossref","unstructured":"Doersch C, Gupta A, Efros AA (2015) \u201cUnsupervised Visual Representation Learning by Context Prediction,\u201d in 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1422\u20131430, 2015, Santiago, Chile","DOI":"10.1109\/ICCV.2015.167"},{"issue":"12","key":"2631_CR2","doi-asserted-by":"publisher","first-page":"4261","DOI":"10.1007\/s10489-020-01750-z","volume":"50","author":"PF Sun","year":"2020","unstructured":"Sun PF, Su X, Guo SQ, Chen F (2020) Cycle representation-disentangling network: learning to completely disentangle spatial-temporal features in video. Appl Intell 50(12):4261\u20134280","journal-title":"Appl Intell"},{"issue":"4","key":"2631_CR3","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y Lecun","year":"2014","unstructured":"Lecun Y, Boser B, Denker J, Henderson D, Howard R, Hubbard W, Jackel L (2014) Backpropagation applied to handwritten zip code recognition. Neural Comput 1(4):541\u2013551","journal-title":"Neural Comput"},{"issue":"8","key":"2631_CR4","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 Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"2631_CR5","unstructured":"Shi XJ, Chen ZR, Wang H, Yeung DY, Wong WK, Woo WC (2015) \u201cConvolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting,\u201d in Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS), vol. 1, pp. 802\u2013810, Montreal, Canada"},{"issue":"7","key":"2631_CR6","doi-asserted-by":"publisher","first-page":"2515","DOI":"10.1007\/s10489-018-1395-8","volume":"49","author":"M Majd","year":"2019","unstructured":"Majd M, Safabakhsh R (2019) A motion-aware ConvLSTM network for action recognition. Appl Intell 49(7):2515\u20132521","journal-title":"Appl Intell"},{"key":"2631_CR7","unstructured":"Zhang L, Zhu G, Mei L, Shen P, Shah SAA, Bennamoun M (2018) \u201cAttention in convolutional LSTM for gesture recognition,\u201d in Proceedings of the 32nd International Conference on Neural Information Processing Systems (NIPS), pp. 1957\u20131966, 2018, Montreal, Canada"},{"key":"2631_CR8","unstructured":"Lotter W, Kreiman G, Cox D (2017) \u201cDeep Predictive Coding Networks for Video Prediction and Unsupervised Learning,\u201d in the 5th International Conference on Learning Representations (ICLR), Toulon, France"},{"issue":"1\u20133","key":"2631_CR9","first-page":"185","volume":"17","author":"BKP Horn","year":"1980","unstructured":"Horn BKP, Schunck BG (1980) Determining optical flow. Artif Intell 17(1\u20133):185\u2013203","journal-title":"Artif Intell"},{"key":"2631_CR10","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, Urtasun R (2012) \u201cAre we ready for autonomous driving? The KITTI vision benchmark suite,\u201d in 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3354\u20133361, Providence, United States","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"2631_CR11","unstructured":"Soomro K, Zamir AR, Shah M (2012) \u201cUCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild,\u201d arXiv:1212.0402"},{"key":"2631_CR12","doi-asserted-by":"crossref","unstructured":"Dollar P, Wojek C, Schiele B, Perona P (2009) \u201cPedestrian Detection: A Benchmark,\u201d in 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 304\u2013311, Miami, United States","DOI":"10.1109\/CVPR.2009.5206631"},{"key":"2631_CR13","doi-asserted-by":"crossref","unstructured":"Schuldt C, Laptev I, Caputo B (2004) \u201cRecognizing human actions: A local SVM approach,\u201d in Proceedings of the 17th International Conference on Pattern Recognition (ICPR), vol. 3, pp. 32\u201336, Cambridge, United Kindom","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"2631_CR14","doi-asserted-by":"crossref","unstructured":"Liu ZW, Yeh RA, Tang XO, Liu YM, Agarwala A (2017) \u201cVideo Frame Synthesis using Deep Voxel Flow,\u201d in 2017 IEEE International Conference on Computer Vision (ICCV), pp. 4473\u20134481, Venice, Italy","DOI":"10.1109\/ICCV.2017.478"},{"key":"2631_CR15","doi-asserted-by":"crossref","unstructured":"Gao H, Xu HZ, Cai QZ, Wang R, Yu F, and Darrell T (2019) \u201cDisentangling Propagation and Generation for Video Prediction,\u201d in 2019 IEEE International Conference on Computer Vision (ICCV), pp. 9005\u20139014, Seoul, South Korea","DOI":"10.1109\/ICCV.2019.00910"},{"key":"2631_CR16","unstructured":"Yu W, Lu Y, Easterbrook S, Fidler S (2020) \u201cEfficient and Information-Preserving Future Frame Prediction and Beyond,\u201d in the 8th International Conference on Learning Representations (ICLR), Addis Ababa, Ethiopia"},{"key":"2631_CR17","doi-asserted-by":"crossref","unstructured":"Jin BB, Hu Y, Tang QK, Niu JY, Shi ZP, Han YH, Li XW (2020) \u201cExploring Spatial-Temporal Multi-Frequency Analysis for High-Fidelity and Temporal-Consistency Video Prediction,\u201d in 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4553\u20134562, Seattle, United States","DOI":"10.1109\/CVPR42600.2020.00461"},{"key":"2631_CR18","unstructured":"Straka Z, Svoboda T, and Hoffmann M (2020) \u201cPreCNet: Next Frame Video Prediction Based on Predictive Coding,\u201d arXiv:2004.14878"},{"key":"2631_CR19","unstructured":"Shi XJ, Gao ZH, Lausen L, Wang H, Yeung DY, Wong WK, Woo WC (2017) \u201cDeep Learning for Precipitation Nowcasting: A Benchmark and A New Model,\u201d in Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS), vol. 30, pp. 5622\u20135632, Long Beach, United States"},{"key":"2631_CR20","unstructured":"Villegas R, Yang J, Hong S, Lin X, and Lee H (2017) \u201cDecomposing Motion and Content for Natural Video Sequence Prediction,\u201d in the 5th International Conference on Learning Representations (ICLR), Toulon, France"},{"key":"2631_CR21","unstructured":"Wang Y, Long M, Wang J, Gao Z, Yu PS (2017) \u201cPredRNN: recurrent neural networks for predictive learning using spatiotemporal LSTMs,\u201d in Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS), pp. 879\u2013888, Long Beach, United States"},{"key":"2631_CR22","unstructured":"Wang Y, Gao Z, Long M, Wang J, Yu PS (2018) \u201cPredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning,\u201d in Proceedings of the 35th International Conference on International Conference on Machine Learning (ICML), pp. 5110\u20135119, Stockholm, Sweden"},{"key":"2631_CR23","doi-asserted-by":"crossref","unstructured":"Lin Z, Li M, Zheng Z, Cheng Y, Yuan C (2020) \u201cSelf-Attention ConvLSTM for Spatiotemporal Prediction,\u201d in Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI), vol. 34, no. 7, pp. 11531\u201311538, New York, United States","DOI":"10.1609\/aaai.v34i07.6819"},{"key":"2631_CR24","doi-asserted-by":"crossref","unstructured":"Wu Q, Chen XT, Huang ZY, Wang WM (2020) \u201cGenerating Future Frames with Mask-Guided Prediction,\u201d in 2020 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136, 2020, London, United Kindom","DOI":"10.1109\/ICME46284.2020.9102876"},{"key":"2631_CR25","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/978-3-540-24673-2_3","volume":"3024","author":"T Brox","year":"2004","unstructured":"Brox T, Bruhn A, Papenberg N, Weickert J (2004) High accuracy optical flow estimation based on a theory for warping. Lect Notes Comput Sci 3024:25\u201336","journal-title":"Lect Notes Comput Sci"},{"key":"2631_CR26","doi-asserted-by":"crossref","unstructured":"Weinzaepfel P, Revaud J, Harchaoui Z, Schmid C (2013) \"DeepFlow: Large displacement optical flow with deep matching,\" in 2013 IEEE International Conference on Computer Vision (ICCV), pp. 1385\u20131392, Sydeny, Australia","DOI":"10.1109\/ICCV.2013.175"},{"issue":"8","key":"2631_CR27","doi-asserted-by":"publisher","first-page":"779","DOI":"10.1109\/34.400567","volume":"17","author":"A Shashua","year":"1995","unstructured":"Shashua A (1995) Algebraic functions for recognition. IEEE Transactions on Pattern Analysis & Machine Intelligence 17(8):779\u2013789","journal-title":"IEEE Transactions on Pattern Analysis & Machine Intelligence"},{"key":"2631_CR28","doi-asserted-by":"crossref","unstructured":"Donahue J, Hendricks LA, Guadarrama S, Rohrbach M, Venugopalan S, Saenko K, and Darrell T (2015) \u201cLong-term Recurrent Convolutional Networks for Visual Recognition and Description,\u201d in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2625\u20132634, Boston, United States","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"2631_CR29","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) \"deep residual learning for image recognition,\" in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770-778, Las Vegas, United States","DOI":"10.1109\/CVPR.2016.90"},{"key":"2631_CR30","unstructured":"Simonyan K, Zisserman A (2015) \u201cVery Deep Convolutional Networks for Large-Scale Image Recognition,\u201d in the 3rd International Conference on Learning Representations (ICLR), San Diego, United States"},{"key":"2631_CR31","unstructured":"Srivastava N, Mansimov E, Salakhutdinov R (2015) \u201cUnsupervised Learning of Video Representations using LSTMs,\u201d in Proceedings of the 32nd International Conference on International Conference on Machine Learning (ICML), vol. 37, pp. 843\u2013852, Lile, France"},{"key":"2631_CR32","doi-asserted-by":"crossref","unstructured":"Wang YB, Zhang JJ, Zhu HY, Long MS, Wang JM, Yu PS (2019) \u201cMemory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics,\u201d in 2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9146\u20139154, 2019, Long Beach, United States","DOI":"10.1109\/CVPR.2019.00937"},{"key":"2631_CR33","doi-asserted-by":"crossref","unstructured":"Ye YF, Singh M, Gupta A, Tulsiani S (2019) \u201cCompositional Video Prediction,\u201d in 2019 IEEE International Conference on Computer Vision (ICCV), pp. 10352\u201310361, Seoul, South Korea","DOI":"10.1109\/ICCV.2019.01045"},{"key":"2631_CR34","doi-asserted-by":"crossref","unstructured":"Elharrouss O, Almaadeed N, Al-Maadeed S, Bouridane A, Beghdadi A (2020) A combined multiple action recognition and summarization for surveillance video sequences. Appl Intell:1\u201323","DOI":"10.29117\/quarfe.2020.0235"},{"key":"2631_CR35","unstructured":"Lee AX, Zhang R, Ebert F, Abbeel P, Finn C, Levine S (2018) \u201cStochastic Adversarial Video Prediction,\u201d arXiv:1804.01523"},{"key":"2631_CR36","unstructured":"Lotter W, Kreiman G, Cox D (2015) \u201cUnsupervised Learning of Visual Structure Using Predictive Generative Networks,\u201d arXiv:1511.06380"},{"key":"2631_CR37","unstructured":"Mathieu M, Couprie C, Lecun Y (2016) \u201cDeep multi-scale video prediction beyond mean square error,\u201d in the 4th International Conference on Learning Representations (ICLR), 2016, San Juan, United States"},{"key":"2631_CR38","doi-asserted-by":"crossref","unstructured":"Liang X, Lee L, Dai W, Xing EP (2017) \"Dual Motion GAN for Future-Flow Embedded Video Prediction.\" in 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1762-1770, 2017, Venice, Italy","DOI":"10.1109\/ICCV.2017.194"},{"issue":"8","key":"2631_CR39","doi-asserted-by":"publisher","first-page":"2151","DOI":"10.1162\/NECO_a_00312","volume":"24","author":"M Denil","year":"2012","unstructured":"Denil M, Bazzani L, Larochelle H, de Freitas N (2012) Learning where to attend with deep architectures for image tracking. Neural Comput 24(8):2151\u20132184","journal-title":"Neural Comput"},{"key":"2631_CR40","unstructured":"Ba J, Mnih V, Kavukcuoglu K (2015) \u201cMultiple Object Recognition with Visual Attention,\u201d in the 3rd International Conference on Learning Representations (ICLR), San Diego, United States"},{"key":"2631_CR41","unstructured":"Xu K, Ba J, Kiros R, Cho K, Courville A, Salakhutdinov R, Zemel R, Bengio Y (2015) \u201cShow, Attend and Tell: Neural Image Caption Generation with Visual Attention,\u201d in Proceedings of the 32nd International Conference on International Conference on Machine Learning (ICML), vol. 37, pp. 2048-2057, 2015, Lile, France"},{"issue":"10","key":"2631_CR42","doi-asserted-by":"publisher","first-page":"3797","DOI":"10.1007\/s10489-018-1176-4","volume":"48","author":"TF Liu","year":"2018","unstructured":"Liu TF, Yu SY, Xu BM, Yin HF (2018) Recurrent networks with attention and convolutional networks for sentence representation and classification. Appl Intell 48(10):3797\u20133806","journal-title":"Appl Intell"},{"key":"2631_CR43","doi-asserted-by":"crossref","unstructured":"Dosovitskiy A, Fischer P, Ilg E, Hausser P, Hazirbas C, Golkov V, van der Smagt P, Cremers D, Brox T (2015) \u201cFlowNet: Learning Optical Flow with Convolutional Networks,\u201d in 2015 IEEE International Conference on Computer Vision (ICCV), pp. 2758\u20132766, Santiago, Chile","DOI":"10.1109\/ICCV.2015.316"},{"key":"2631_CR44","doi-asserted-by":"crossref","unstructured":"Zhu XZ, Xiong YW, Dai JF, Yuan L, Wei YC (2017) \u201cDeep Feature Flow for Video Recognition,\u201d in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4141\u20134150, Hawaii, United States","DOI":"10.1109\/CVPR.2017.441"},{"key":"2631_CR45","doi-asserted-by":"crossref","unstructured":"Ji DH, Kwon J, McFarland M, Savarese S (2017) \u201cDeep View Morphing,\u201d in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7092\u20137100, Hawaii, United States","DOI":"10.1109\/CVPR.2017.750"},{"key":"2631_CR46","doi-asserted-by":"crossref","unstructured":"Zhou TH, Tulsiani S, Sun WL, Malik J, Efros AA (2016) \u201cView Synthesis by Appearance Flow,\u201d in European Conference on Computer Vision (ECCV), vol. 9908, pp. 286\u2013301, Amsterdam, Holland","DOI":"10.1007\/978-3-319-46493-0_18"},{"key":"2631_CR47","unstructured":"Bahdanau D, Cho K, Bengio Y (2015) \"neural machine translation by jointly learning to align and translate,\" in the 3rd International Conference on Learning Representations (ICLR), San Diego, United States"},{"key":"2631_CR48","unstructured":"Sutskever I, Vinyals O, Le QV (2014) \u201cSequence to Sequence Learning with Neural Networks,\u201d in Proceedings of the 27th International Conference on Neural Information Processing Systems (NIPS), vol. 2, pp. 3104\u20133112, Montreal, Canada"},{"key":"2631_CR49","unstructured":"Kingma D, Ba J (2015) \u201cAdam: A Method for Stochastic Optimization,\u201d in the 3rd International Conference on Learning Representations (ICLR), San Diego, United States"},{"key":"2631_CR50","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929\u20131958","journal-title":"J Mach Learn Res"},{"issue":"4","key":"2631_CR51","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600\u2013612","journal-title":"IEEE Trans Image Process"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02631-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-021-02631-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02631-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,5]],"date-time":"2022-03-05T05:14:03Z","timestamp":1646457243000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-021-02631-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,2]]},"references-count":51,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["2631"],"URL":"https:\/\/doi.org\/10.1007\/s10489-021-02631-9","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2021,8,2]]},"assertion":[{"value":"17 June 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 August 2021","order":2,"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"}}]}}