{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T03:29:35Z","timestamp":1772508575473,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,1,5]],"date-time":"2022-01-05T00:00:00Z","timestamp":1641340800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,5]],"date-time":"2022-01-05T00:00:00Z","timestamp":1641340800000},"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":[[2022,2]]},"DOI":"10.1007\/s11263-021-01560-x","type":"journal-article","created":{"date-parts":[[2022,1,5]],"date-time":"2022-01-05T10:02:47Z","timestamp":1641376967000},"page":"504-516","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Instance-Aware Scene Layout Forecasting"],"prefix":"10.1007","volume":"130","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5351-8335","authenticated-orcid":false,"given":"Xiaotian","family":"Qiao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quanlong","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rynson W. H.","family":"Lau","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,5]]},"reference":[{"key":"1560_CR1","doi-asserted-by":"crossref","unstructured":"Achanta, R., Hemami, S., Estrada, F., & S\u00fcsstrunk, S. (2009). Frequency-tuned salient region detection. In CVPR.","DOI":"10.1109\/CVPR.2009.5206596"},{"key":"1560_CR2","doi-asserted-by":"crossref","unstructured":"Chao, Y. W., Yang, J., Price, B., Cohen, S., & Deng, J. (2017). Forecasting human dynamics from static images. In ICCV.","DOI":"10.1109\/CVPR.2017.388"},{"key":"1560_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Q., & Koltun, V. (2016). Full flow: Optical flow estimation by global optimization over regular grids. In CVPR.","DOI":"10.1109\/CVPR.2016.509"},{"key":"1560_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Q., & Koltun, V. (2017). Photographic image synthesis with cascaded refinement networks. In ICCV.","DOI":"10.1109\/ICCV.2017.168"},{"key":"1560_CR5","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016). The cityscapes dataset for semantic urban scene understanding. In CVPR.","DOI":"10.1109\/CVPR.2016.350"},{"key":"1560_CR6","unstructured":"Dosovitskiy, A., & Koltun, V. (2017). Learning to act by predicting the future. In ICLR."},{"key":"1560_CR7","unstructured":"Ehrig, M., & \u00e9rome Euzenat, J. (2005). Relaxed precision and recall for ontology matching. In Integrating ontologies workshop proceedings."},{"key":"1560_CR8","doi-asserted-by":"crossref","unstructured":"Gammulle, H., Denman, S., Sridharan, S., & Fookes, C.(2019). Predicting the future: A jointly learnt model for action anticipation. In ICCV.","DOI":"10.1109\/ICCV.2019.00566"},{"key":"1560_CR9","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative adversarial nets. In NeurIPS."},{"key":"1560_CR10","doi-asserted-by":"crossref","unstructured":"Graber, C., Tsai, G., Firman, M., Brostow, G., & Schwing, A. (2021). Panoptic segmentation forecasting. arXiv:2104.03962.","DOI":"10.1109\/CVPR46437.2021.01233"},{"key":"1560_CR11","doi-asserted-by":"crossref","unstructured":"Guan, J., Yuan, Y., Kitani, K.M., & Rhinehart, N. (2020). Generative hybrid representations for activity forecasting with no-regret learning. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00025"},{"key":"1560_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask r-cnn. In ICCV.","DOI":"10.1109\/ICCV.2017.322"},{"key":"1560_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In CVPR.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1560_CR14","doi-asserted-by":"crossref","unstructured":"Hoai, M., & De\u00a0la Torre, F.(2014). Max-margin early event detectors. In IJCV.","DOI":"10.1007\/s11263-013-0683-3"},{"key":"1560_CR15","doi-asserted-by":"crossref","unstructured":"Hu, A., Cotter, F., Mohan, N., Gurau, C., & Kendall, A. (2020). Probabilistic future prediction for video scene understanding. In ECCV.","DOI":"10.1007\/978-3-030-58517-4_45"},{"key":"1560_CR16","unstructured":"Jaderberg, M., Simonyan, K., & Zisserman, A., et\u00a0al. (2015). Spatial transformer networks. In NeurIPS (pp. 2017\u20132025)."},{"key":"1560_CR17","doi-asserted-by":"crossref","unstructured":"Jin, X., Li, X., Xiao, H., Shen, X., Lin, Z., Yang, J., Chen, Y., Dong, J., Liu, L., & Jie, Z., et\u00a0al. (2017). Video scene parsing with predictive feature learning. In ICCV.","DOI":"10.1109\/ICCV.2017.595"},{"key":"1560_CR18","unstructured":"Jin, X., Xiao, H., Shen, X., Yang, J., Lin, Z., Chen, Y., Jie, Z., Feng, J., & Yan, S. (2017). Predicting scene parsing and motion dynamics in the future. In NeurIPS."},{"key":"1560_CR19","doi-asserted-by":"crossref","unstructured":"Kim, W., Tanaka, M., Okutomi, M., & Sasaki, Y. (2020). Adaptive future frame prediction with ensemble network. arXiv:2011.06788.","DOI":"10.1007\/978-3-030-68787-8_1"},{"key":"1560_CR20","unstructured":"Kingma, D.P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980."},{"key":"1560_CR21","doi-asserted-by":"crossref","unstructured":"Kwon, Y. H., & Park, M. G. (2019). Predicting future frames using retrospective cycle gan. In CVPR.","DOI":"10.1109\/CVPR.2019.00191"},{"key":"1560_CR22","doi-asserted-by":"crossref","unstructured":"Li, W. H., Hong, F. T., & Zheng, W. S. (2019). Learning to learn relation for important people detection in still images. In CVPR.","DOI":"10.1109\/CVPR.2019.00514"},{"key":"1560_CR23","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft coco: Common objects in context. In ECCV.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1560_CR24","doi-asserted-by":"crossref","unstructured":"Luc, P., Couprie, C., Lecun, Y., & Verbeek, J. (2018). Predicting future instance segmentation by forecasting convolutional features. In ECCV.","DOI":"10.1007\/978-3-030-01240-3_36"},{"key":"1560_CR25","doi-asserted-by":"crossref","unstructured":"Luc, P., Neverova, N., Couprie, C., Verbeek, J., & LeCun, Y. (2017). Predicting deeper into the future of semantic segmentation. In ICCV.","DOI":"10.1109\/ICCV.2017.77"},{"key":"1560_CR26","unstructured":"Mathieu, M., Couprie, C., & LeCun, Y. (2016). Deep multi-scale video prediction beyond mean square error. In ICLR."},{"key":"1560_CR27","doi-asserted-by":"crossref","unstructured":"Qi, X., Chen, Q., Jia, J., & Koltun, V. (2018). Semi-parametric image synthesis. In CVPR (pp. 8808\u20138816).","DOI":"10.1109\/CVPR.2018.00918"},{"key":"1560_CR28","doi-asserted-by":"crossref","unstructured":"Qi, X., Liu, Z., Chen, Q., & Jia, J. (2019). 3d motion decomposition for rgbd future dynamic scene synthesis. In CVPR.","DOI":"10.1109\/CVPR.2019.00786"},{"key":"1560_CR29","doi-asserted-by":"crossref","unstructured":"Qiao, X., Zheng, Q., Cao, Y., & Lau, R. W. (2019). Tell me where i am: Object-level scene context prediction. In CVPR (pp. 2633\u20132641).","DOI":"10.1109\/CVPR.2019.00274"},{"key":"1560_CR30","unstructured":"Ranzato, M., Szlam, A., Bruna, J., Mathieu, M., Collobert, R., & Chopra, S. (2014). Video (language) modeling: A baseline for generative models of natural videos. arXiv:1412.6604."},{"key":"1560_CR31","unstructured":"Rochan, M., et\u00a0al. (2018). Future semantic segmentation with convolutional LSTM. In BMVC."},{"key":"1560_CR32","doi-asserted-by":"crossref","unstructured":"\u0160ari\u0107, J., Or\u0161i\u0107, M., Antunovi\u0107, T., Vra\u017ei\u0107, S., & \u0160egvi\u0107, S. (2019). Single level feature-to-feature forecasting with deformable convolutions. In GCPR.","DOI":"10.1007\/978-3-030-33676-9_13"},{"key":"1560_CR33","doi-asserted-by":"crossref","unstructured":"Saric, J., Orsic, M., Antunovic, T., Vrazic, S., & Segvic, S. (2020). Warp to the future: Joint forecasting of features and feature motion. In CVPR.","DOI":"10.1109\/CVPR42600.2020.01066"},{"key":"1560_CR34","unstructured":"Shalev-Shwartz, S., Ben-Zrihem, N., Cohen, A., & Shashua, A. (2016). Long-term planning by short-term prediction. arXiv:1602.01580."},{"key":"1560_CR35","unstructured":"Vondrick, C., Pirsiavash, H., & Torralba, A. (2016). Anticipating the future by watching unlabeled video. In CVPR."},{"key":"1560_CR36","doi-asserted-by":"crossref","unstructured":"Vondrick, C., & Torralba, A. (2017). Generating the future with adversarial transformers. In CVPR.","DOI":"10.1109\/CVPR.2017.319"},{"key":"1560_CR37","doi-asserted-by":"crossref","unstructured":"Walker, J., Gupta, A., & Hebert, M. (2015). Dense optical flow prediction from a static image. In ICCV.","DOI":"10.1109\/ICCV.2015.281"},{"key":"1560_CR38","doi-asserted-by":"crossref","unstructured":"Yang, L., Fan, Y., & Xu, N. (2019). Video instance segmentation. In ICCV.","DOI":"10.1109\/ICCV.2019.00529"},{"key":"1560_CR39","doi-asserted-by":"crossref","unstructured":"Yuen, J., & Torralba, A. (2010). A data-driven approach for event prediction. In ECCV.","DOI":"10.1007\/978-3-642-15552-9_51"},{"key":"1560_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, Y., & Berg, T. L. (2016). Learning temporal transformations from time-lapse videos. In ECCV.","DOI":"10.1007\/978-3-319-46484-8_16"}],"updated-by":[{"DOI":"10.1007\/s11263-022-01577-w","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2022,2,7]],"date-time":"2022-02-07T00:00:00Z","timestamp":1644192000000}}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01560-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-021-01560-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01560-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,16]],"date-time":"2022-02-16T10:23:10Z","timestamp":1645006990000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-021-01560-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,5]]},"references-count":40,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,2]]}},"alternative-id":["1560"],"URL":"https:\/\/doi.org\/10.1007\/s11263-021-01560-x","relation":{"correction":[{"id-type":"doi","id":"10.1007\/s11263-022-01577-w","asserted-by":"object"}]},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,5]]},"assertion":[{"value":"8 May 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 November 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 February 2022","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1007\/s11263-022-01577-w","URL":"https:\/\/doi.org\/10.1007\/s11263-022-01577-w","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}}]}}