{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:18:30Z","timestamp":1742912310051,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031784552"},{"type":"electronic","value":"9783031784569"}],"license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-78456-9_5","type":"book-chapter","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T11:23:26Z","timestamp":1733138606000},"page":"62-79","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Spatio-Temporal Attentive Fusion Unit for Effective Video Prediction"],"prefix":"10.1007","author":[{"given":"Binit","family":"Singh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Divij","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohan","family":"Kaushal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sana Vishnu Karthikeya","family":"Reddy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bandam Sai","family":"Jaswanth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pratik","family":"Chattopadhyay","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Akan, A.K., Erdem, E., Erdem, A., G\u00fcney, F.: SLAMP: Stochastic Latent Appearance and Motion Prediction. In: Proc. of the IEEE\/CVF ICCV. pp. 14728\u201314737 (2021)","DOI":"10.1109\/ICCV48922.2021.01446"},{"key":"5_CR2","unstructured":"Babaeizadeh, M., Finn, C., Erhan, D., Campbell, R.H., Levine, S.: Stochastic Variational Video Prediction. arXiv preprint arXiv:1710.11252 (2017)"},{"key":"5_CR3","unstructured":"Chang, Z., Zhang, X., Wang, S., Ma, S., Gao, W.: STAU: A SpatioTemporal-Aware Unit for Video Prediction and Beyond. arXiv (2022)"},{"key":"5_CR4","unstructured":"Chang, Z., Zhang, X., Wang, S., Ma, S., Ye, Y., Xiang, X., Gao, W.: MAU: A motion-aware unit for video prediction and beyond. In: Proc. of the Advances in NIPS (34). pp. 26950\u201326962 (2021)"},{"key":"5_CR5","unstructured":"Denton, E.L., Fergus, R.: Stochastic video generation with a learned prior. In: Proc. of the ICML. pp. 1174\u20131183 (2018)"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Ess, A., Leibe, B., Van\u00a0Gool, L.: Depth and Appearance for Mobile Scene Analysis. In: Proc. of the IEEE ICCV. pp.\u00a01\u20138 (2007)","DOI":"10.1109\/CVPR.2007.383146"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Gao, Z., Tan, C., Wu, L., Li, S.Z.: SimVP: Simpler Yet Better Video Prediction. In: Proc. of the IEEE\/CVF CVPR. pp. 3170\u20133180 (2022)","DOI":"10.1109\/CVPR52688.2022.00317"},{"key":"5_CR8","unstructured":"Kim, T., Ahn, S., Bengio, Y.: Variational Temporal Abstraction. In: Proc. of the Advances in NIPS (32). pp. 11570\u201311579 (2019)"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Kwon, Y.H., Park, M.G.: Predicting Future Frames Using Retrospective Cycle GAN. In: Proc. of the IEEE\/CVF CVPR. pp. 1811\u20131820 (2019)","DOI":"10.1109\/CVPR.2019.00191"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Le\u00a0Guen, V., Thome, N.: Disentangling Physical Dynamics From Unknown Factors for Unsupervised Video Prediction. In: Proc. of the IEEE\/CVF CVPR. pp. 11471\u201311481 (2020)","DOI":"10.1109\/CVPR42600.2020.01149"},{"key":"5_CR11","unstructured":"Lee, A., Zhang, R., Ebert, F., Abbeel, P., Finn, C., Levine, S.: Stochastic Adversarial Video Prediction. arXiv preprint arXiv:1804.01523 (2018)"},{"key":"5_CR12","unstructured":"Lee, J., Lee, J., Lee, S., Yoon, S.: MSnet: Mutual Suppression Network for Disentangled Video Representations. CoRR abs\/1804.04810 (2018)"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Lee, S., Kim, H.G., Choi, D.H., il\u00a0Kim, H., Ro, Y.M.: Video Prediction Recalling Long-term Motion Context via Memory Alignment Learning. In: Proc. of the IEEE\/CVF CVPR. pp. 3053\u20133062 (2021)","DOI":"10.1109\/CVPR46437.2021.00307"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Lin, Z., Li, M., Zheng, Z., Cheng, Y., Yuan, C.: Self-Attention ConvLSTM for Spatiotemporal Prediction. In: Proc. of the AAAI Conf. on Artificial Intelligence. pp. 11531\u201311538 (2020)","DOI":"10.1609\/aaai.v34i07.6819"},{"key":"5_CR15","unstructured":"Michalski, V., Memisevic, R., Konda, K.: Modeling Deep Temporal Dependencies with Recurrent Grammar Cells. In: Proc. of the Advances in NIPS (27). pp. 1925\u20131933 (2014)"},{"key":"5_CR16","doi-asserted-by":"publisher","unstructured":"Schuldt, C., Laptev, I., Caputo, B.: Recognizing Human Actions: A Local SVM Approach. In: Proc. of the ICPR. pp. 32\u201336 Vol.3 (2004). https:\/\/doi.org\/10.1109\/ICPR.2004.1334462","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"5_CR17","unstructured":"Shi, X., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., WOO, W.C.: Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting. In: Proc. of the Advances in NIPS (28). pp. 802\u2013810 (2015)"},{"key":"5_CR18","unstructured":"Shi, X., Gao, Z., Lausen, L., Wang, H., Yeung, D.Y., Wong, W.k., Woo, W.c.: Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model. In: Proc. of the Advances in NIPS (30). pp. 5617\u20135627 (2017)"},{"key":"5_CR19","unstructured":"Shrivastava, G., Shrivastava, A.: Diverse Video Generation using a Gaussian Process Trigger. In: Proc. of the ICLR (2021), https:\/\/openreview.net\/forum?id=Qm7R_SdqTpT"},{"key":"5_CR20","unstructured":"Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised Learning of Video Representations using LSTMs. In: Proc. of the ICML. pp. 843\u2013852 (2015)"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Sun, M., Wang, W., Zhu, X., Liu, J.: MOSO: Decomposing MOtion, Scene and Object for Video Prediction. In: Proc. of the IEEE\/CVF CVPR. pp. 18727\u201318737 (2023)","DOI":"10.1109\/CVPR52729.2023.01796"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Tang, S., Li, C., Zhang, P., Tang, R.: SwinLSTM: Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTM. In: Proc. of the IEEE\/CVF ICCV. pp. 13470\u201313479 (2023)","DOI":"10.1109\/ICCV51070.2023.01239"},{"key":"5_CR23","unstructured":"Villar-Corrales, A., Karapetyan, A., Boltres, A., Behnke, S.: MSPred: Video Prediction at Multiple Spatio-Temporal Scales with Hierarchical Recurrent Networks. arXiv preprint arXiv:2203.09303 (2022)"},{"key":"5_CR24","unstructured":"Villegas, R., Pathak, A., Kannan, H., Erhan, D., Le, Q.V., Lee, H.: High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networks. In: Proc. of the Advances in NIPS (32). pp. 81\u201391 (2019)"},{"key":"5_CR25","unstructured":"Wang, Y., Gao, Z., Long, M., Wang, J., Yu, P.S.: PredRNN++: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning. In: Proc. of the $$35^{th}$$ ICML. pp. 5123\u20135132 (2018)"},{"key":"5_CR26","unstructured":"Wang, Y., Jiang, L., Yang, M.H., Li, L.J., Long, M., Fei-Fei, L.: Eidetic 3d LSTM: A model for video prediction and beyond. In: Proc. of the ICLR (2019)"},{"key":"5_CR27","unstructured":"Wang, Y., Long, M., Wang, J., Gao, Z., Yu, P.S.: PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs. In: Proc. of the Advances in NIPS (30). pp. 879\u2013888 (2017)"},{"issue":"2","key":"5_CR28","doi-asserted-by":"publisher","first-page":"2208","DOI":"10.1109\/TPAMI.2022.3165153","volume":"45","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Wu, H., Zhang, J., Gao, Z., Wang, J., Philip, S.Y., Long, M.: PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning. IEEE Trans. on PAMI 45(2), 2208\u20132225 (2022)","journal-title":"IEEE Trans. on PAMI"},{"key":"5_CR29","unstructured":"Yu, W., Lu, Y., Easterbrook, S., Fidler, S.: Efficient and Information-Preserving Future Frame Prediction and Beyond. In: Proc. of the Intl. Conf. on Learning Representations (2020)"},{"key":"5_CR30","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Liang, L., Zharkov, I., Neumann, U.: MMVP: Motion-Matrix-Based Video Prediction. In: Proc. of the IEEE\/CVF ICCV. pp. 4273\u20134283 (2023)","DOI":"10.1109\/ICCV51070.2023.00394"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78456-9_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T12:09:49Z","timestamp":1733141389000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78456-9_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"ISBN":["9783031784552","9783031784569"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78456-9_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"3 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}