{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:55:33Z","timestamp":1777568133223,"version":"3.51.4"},"publisher-location":"Cham","reference-count":82,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197864","type":"print"},{"value":"9783031197871","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19787-1_29","type":"book-chapter","created":{"date-parts":[[2022,10,20]],"date-time":"2022-10-20T22:16:11Z","timestamp":1666304171000},"page":"510-528","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Hallucinating Pose-Compatible Scenes"],"prefix":"10.1007","author":[{"given":"Tim","family":"Brooks","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexei A.","family":"Efros","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,21]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Aberman, K., Shi, M., Liao, J., Lischinski, D., Chen, B., Cohen-Or, D.: Deep video-based performance cloning. In: Computer Graphics Forum. vol. 38, pp. 219\u2013233. Wiley Online Library (2019)","DOI":"10.1111\/cgf.13632"},{"issue":"1","key":"29_CR2","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1207\/s15516709cog0901_7","volume":"9","author":"DH Ackley","year":"1985","unstructured":"Ackley, D.H., Hinton, G.E., Sejnowski, T.J.: A learning algorithm for boltzmann machines. Cogn. Sci. 9(1), 147\u2013169 (1985)","journal-title":"Cogn. Sci."},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2d human pose estimation: new benchmark and state of the art analysis. In: Proceedings of the IEEE Conference on computer Vision and Pattern Recognition, pp. 3686\u20133693 (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Balakrishnan, G., Zhao, A., Dalca, A.V., Durand, F., Guttag, J.: Synthesizing images of humans in unseen poses. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8340\u20138348 (2018)","DOI":"10.1109\/CVPR.2018.00870"},{"key":"29_CR5","unstructured":"Bau, D., et al.: Gan dissection: visualizing and understanding generative adversarial networks. In: Proceedings of the International Conference on Learning Representations (ICLR) (2019)"},{"key":"29_CR6","unstructured":"Biederman, I.: On the semantics of a glance at a scene. In: Perceptual Organization (1981)"},{"key":"29_CR7","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=B1xsqj09Fm"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Cao, Z., Gao, H., Mangalam, K., Cai, Q., Vo, M., Malik, J.: Long-term human motion prediction with scene context. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58452-8_23"},{"issue":"1","key":"29_CR9","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1109\/TPAMI.2019.2929257","volume":"43","author":"Z Cao","year":"2019","unstructured":"Cao, Z., Hidalgo, G., Simon, T., Wei, S.E., Sheikh, Y.: Openpose: realtime multi-person 2d pose estimation using part affinity fields. IEEE Trans. Pattern Anal. Mach. Intell. 43(1), 172\u2013186 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Cao, Z., Radosavovic, I., Kanazawa, A., Malik, J.: Reconstructing hand-object interactions in the wild. arXiv e-prints pp. arXiv-2012 (2020)","DOI":"10.1109\/ICCV48922.2021.01219"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"29_CR12","unstructured":"Chai, L., Wulff, J., Isola, P.: Using latent space regression to analyze and leverage compositionality in GANs. In: International Conference on Learning Representations (2021)"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Chan, C., Ginosar, S., Zhou, T., Efros, A.A.: Everybody dance now. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5933\u20135942 (2019)","DOI":"10.1109\/ICCV.2019.00603"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Chuang, C.Y., Li, J., Torralba, A., Fidler, S.: Learning to act properly: predicting and explaining affordances from images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 975\u2013983 (2018)","DOI":"10.1109\/CVPR.2018.00108"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Delaitre, V., Fouhey, D., Laptev, I., Sivic, J., Gupta, A., Efros, A.: Scene semantics from long-term observation of people. In: Proceedings of 12th European Conference on Computer Vision (2012)","DOI":"10.1007\/978-3-642-33783-3_21"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR09 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"29_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1007\/978-3-030-58558-7_35","volume-title":"Computer Vision","author":"A Diba","year":"2020","unstructured":"Diba, A., et al.: Large scale holistic video understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 593\u2013610. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_35"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Divvala, S.K., Hoiem, D., Hays, J.H., Efros, A.A., Hebert, M.: An empirical study of context in object detection. In: 2009 IEEE Conference on computer vision and Pattern Recognition, pp. 1271\u20131278. IEEE (2009)","DOI":"10.1109\/CVPRW.2009.5206532"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Epstein, D., Chen, B., Vondrick, C.: Oops! predicting unintentional action in video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 919\u2013929 (2020)","DOI":"10.1109\/CVPR42600.2020.00100"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Fan, A., Lewis, M., Dauphin, Y.: Hierarchical neural story generation. arXiv preprint arXiv:1805.04833 (2018)","DOI":"10.18653\/v1\/P18-1082"},{"key":"29_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"732","DOI":"10.1007\/978-3-642-33715-4_53","volume-title":"Computer Vision","author":"DF Fouhey","year":"2012","unstructured":"Fouhey, D.F., Delaitre, V., Gupta, A., Efros, A.A., Laptev, I., Sivic, J.: People watching: human actions as a cue for single view geometry. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 732\u2013745. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_53"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Fouhey, D.F., Kuo, W.C., Efros, A.A., Malik, J.: From lifestyle vlogs to everyday interactions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4991\u20135000 (2018)","DOI":"10.1109\/CVPR.2018.00524"},{"key":"29_CR23","unstructured":"Fouhey, D.F., Wang, X., Gupta, A.: In defense of the direct perception of affordances (2015)"},{"key":"29_CR24","volume-title":"The Ecological Approach to Visual Perception","author":"JJ Gibson","year":"1979","unstructured":"Gibson, J.J.: The Ecological Approach to Visual Perception. Houghton Mifflin, Boston (1979)"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Doll\u00e1r, P., He, K.: Detecting and recognizing human-object interactions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8359\u20138367 (2018)","DOI":"10.1109\/CVPR.2018.00872"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Goetschalckx, L., Andonian, A., Oliva, A., Isola, P.: Ganalyze: toward visual definitions of cognitive image properties. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5744\u20135753 (2019)","DOI":"10.1109\/ICCV.2019.00584"},{"key":"29_CR27","unstructured":"Goodfellow, I.J., et al.: Generative adversarial networks. arXiv preprint arXiv:1406.2661 (2014)"},{"key":"29_CR28","doi-asserted-by":"publisher","unstructured":"Grabner, H., Gall, J., Van Gool, L.: What makes a chair a chair? In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1529\u20131536, June 2011. https:\/\/doi.org\/10.1109\/CVPR.2011.5995327","DOI":"10.1109\/CVPR.2011.5995327"},{"key":"29_CR29","doi-asserted-by":"crossref","unstructured":"Gupta, A., Satkin, S., Efros, A.A., Hebert, M.: From 3d scene geometry to human workspace. In: Computer Vision and Pattern Recognition (CVPR) (2011)","DOI":"10.1109\/CVPR.2011.5995448"},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Hassan, M., Ghosh, P., Tesch, J., Tzionas, D., Black, M.J.: Populating 3D scenes by learning human-scene interaction. In: Proceedings IEEE\/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), June 2021","DOI":"10.1109\/CVPR46437.2021.01447"},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"29_CR32","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS 2017, pp. 6629\u20136640 (2017)"},{"key":"29_CR33","unstructured":"Holtzman, A., Buys, J., Du, L., Forbes, M., Choi, Y.: The curious case of neural text degeneration. arXiv preprint arXiv:1904.09751 (2019)"},{"key":"29_CR34","unstructured":"H\u00e4rk\u00f6nen, E., Hertzmann, A., Lehtinen, J., Paris, S.: Ganspace: discovering interpretable GAN controls. In: Proceedings of NeurIPS (2020)"},{"key":"29_CR35","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3. 6m: large scale datasets and predictive methods for 3d human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2013)","DOI":"10.1109\/TPAMI.2013.248"},{"key":"29_CR36","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Computer Vision and Pattern Recognition (CVPR), 2017 IEEE Conference on (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"29_CR37","unstructured":"Jahanian, A., Chai, L., Isola, P.: On the \u201csteerability\u201d of generative adversarial networks. In: International Conference on Learning Representations (2020)"},{"key":"29_CR38","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Koppula, H., Saxena, A.: Hallucinated humans as the hidden context for labeling 3d scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2013","DOI":"10.1109\/CVPR.2013.385"},{"key":"29_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"key":"29_CR40","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Zhang, J.Y., Felsen, P., Malik, J.: Learning 3d human dynamics from video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5614\u20135623 (2019)","DOI":"10.1109\/CVPR.2019.00576"},{"key":"29_CR41","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. In: International Conference on Learning Representations (2018), https:\/\/openreview.net\/forum?id=Hk99zCeAb"},{"key":"29_CR42","unstructured":"Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J., Aila, T.: Training generative adversarial networks with limited data. arXiv preprint arXiv:2006.06676 (2020)"},{"key":"29_CR43","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"29_CR44","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8110\u20138119 (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"29_CR45","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"29_CR46","unstructured":"Kingma, D.P., Dhariwal, P.: Glow: generative flow with invertible 1 $$\\times $$ 1 convolutions. In: NeurIPS, pp. 10236\u201310245 (2018). http:\/\/papers.nips.cc\/paper\/8224-glow-generative-flow-with-invertible-1x1-convolutions"},{"issue":"8","key":"29_CR47","doi-asserted-by":"publisher","first-page":"951","DOI":"10.1177\/0278364913478446","volume":"32","author":"HS Koppula","year":"2013","unstructured":"Koppula, H.S., Gupta, R., Saxena, A.: Learning human activities and object affordances from RGB-d videos. Int. J. Robot. Res. 32(8), 951\u2013970 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"29_CR48","doi-asserted-by":"crossref","unstructured":"Lee, J., Chai, J., Reitsma, P.S., Hodgins, J.K., Pollard, N.S.: Interactive control of avatars animated with human motion data. In: Proceedings of the 29th Annual Conference on Computer Graphics and Interactive Techniques, pp. 491\u2013500 (2002)","DOI":"10.1145\/566570.566607"},{"key":"29_CR49","doi-asserted-by":"crossref","unstructured":"Li, X., Liu, S., Kim, K., Wang, X., Yang, M.H., Kautz, J.: Putting humans in a scene: learning affordance in 3d indoor environments. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01265"},{"key":"29_CR50","doi-asserted-by":"crossref","unstructured":"Li, Y., Huang, C., Loy, C.C.: Dense intrinsic appearance flow for human pose transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019","DOI":"10.1109\/CVPR.2019.00381"},{"key":"29_CR51","doi-asserted-by":"crossref","unstructured":"Li, Y., Singh, K.K., Ojha, U., Lee, Y.J.: Mixnmatch: multifactor disentanglement and encoding for conditional image generation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00806"},{"key":"29_CR52","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of International Conference on Computer Vision (ICCV), December 2015","DOI":"10.1109\/ICCV.2015.425"},{"key":"29_CR53","doi-asserted-by":"crossref","unstructured":"Ma, L., Jia, X., Sun, Q., Schiele, B., Tuytelaars, T., Van Gool, L.: Pose guided person image generation. In: Advances in Neural Information Processing Systems, pp. 405\u2013415 (2017)","DOI":"10.1109\/CVPR.2018.00018"},{"key":"29_CR54","doi-asserted-by":"crossref","unstructured":"Ma, L., Sun, Q., Georgoulis, S., Van Gool, L., Schiele, B., Fritz, M.: Disentangled person image generation. In: The IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00018"},{"issue":"11","key":"29_CR55","first-page":"2579","volume":"9","author":"L Van der Maaten","year":"2008","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11), 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."},{"key":"29_CR56","unstructured":"Marchesi, M.: Megapixel size image creation using generative adversarial networks (2017)"},{"key":"29_CR57","unstructured":"Mescheder, L., Nowozin, S., Geiger, A.: Which training methods for GANs do actually converge? In: International Conference on Machine Learning (ICML) (2018)"},{"key":"29_CR58","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)"},{"key":"29_CR59","doi-asserted-by":"crossref","unstructured":"Mokady, R., et al.: Self-distilled stylegan: towards generation from internet photos. arXiv preprint arXiv:2202.12211 (2022)","DOI":"10.1145\/3528233.3530708"},{"issue":"2","key":"29_CR60","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1109\/TPAMI.2019.2901464","volume":"42","author":"M Monfort","year":"2019","unstructured":"Monfort, M., et al.: Moments in time dataset: one million videos for event understanding. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 502\u2013508 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR61","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., et al.: The role of context for object detection and semantic segmentation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 891\u2013898 (2014)","DOI":"10.1109\/CVPR.2014.119"},{"key":"29_CR62","unstructured":"Park, T., Zhu, J.Y., Wang, O., Lu, J., Shechtman, E., Efros, A.A., Zhang, R.: Swapping autoencoder for deep image manipulation. In: Advances in Neural Information Processing Systems (2020)"},{"key":"29_CR63","doi-asserted-by":"crossref","unstructured":"Peebles, W., Peebles, J., Zhu, J.Y., Efros, A.A., Torralba, A.: The hessian penalty: a weak prior for unsupervised disentanglement. In: Proceedings of European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58539-6_35"},{"key":"29_CR64","doi-asserted-by":"crossref","unstructured":"Rabinovich, A., Vedaldi, A., Galleguillos, C., Wiewiora, E., Belongie, S.: Objects in context. In: 2007 IEEE 11th International Conference on Computer Vision, pp. 1\u20138. IEEE (2007)","DOI":"10.1109\/ICCV.2007.4408986"},{"key":"29_CR65","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: International Conference on Machine Learning, pp. 1060\u20131069. PMLR (2016)"},{"key":"29_CR66","doi-asserted-by":"crossref","unstructured":"Sauer, A., Schwarz, K., Geiger, A.: Stylegan-xl: scaling stylegan to large diverse datasets. arXiv preprint arXiv:2202.00273 (2022)","DOI":"10.1145\/3528233.3530738"},{"key":"29_CR67","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Sangineto, E., Lathuiliere, S., Sebe, N.: Deformable GANs for pose-based human image generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3408\u20133416 (2018)","DOI":"10.1109\/CVPR.2018.00359"},{"key":"29_CR68","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1007\/978-3-319-46448-0_31","volume-title":"Computer Vision","author":"GA Sigurdsson","year":"2016","unstructured":"Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in homes: crowdsourcing data collection for activity understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 510\u2013526. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_31"},{"key":"29_CR69","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"29_CR70","doi-asserted-by":"crossref","unstructured":"Torralba, A., Murphy, K.P., Freeman, W.T., Rubin, M.A.: Context-based vision system for place and object recognition. In: Computer Vision, IEEE International Conference on. vol. 2, pp. 273\u2013273. IEEE Computer Society (2003)","DOI":"10.1109\/ICCV.2003.1238354"},{"key":"29_CR71","doi-asserted-by":"crossref","unstructured":"Wang, J., Xu, H., Xu, J., Liu, S., Wang, X.: Synthesizing long-term 3d human motion and interaction in 3d scenes (2020)","DOI":"10.1109\/CVPR46437.2021.00928"},{"key":"29_CR72","unstructured":"Wang, T.C., et al.: Video-to-video synthesis. In: Advances in Neural Information Processing Systems (NeurIPS) (2018)"},{"key":"29_CR73","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional GANs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00917"},{"key":"29_CR74","doi-asserted-by":"crossref","unstructured":"Wang, X., Girdhar, R., Gupta, A.: Binge watching: scaling affordance learning from sitcoms. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.359"},{"key":"29_CR75","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2. https:\/\/github.com\/facebookresearch\/detectron2 (2019)"},{"key":"29_CR76","doi-asserted-by":"crossref","unstructured":"Xu, N., et al.: Youtube-vos: sequence-to-sequence video object segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 585\u2013601 (2018)","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"29_CR77","doi-asserted-by":"crossref","unstructured":"Yao, B., Fei-Fei, L.: Modeling mutual context of object and human pose in human-object interaction activities. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 17\u201324 (2010)","DOI":"10.1109\/CVPR.2010.5540235"},{"key":"29_CR78","unstructured":"Yu, F., Zhang, Y., Song, S., Seff, A., Xiao, J.: Lsun: construction of a large-scale image dataset using deep learning with humans in the loop. CoRR abs\/1506.03365 (2015). http:\/\/dblp.uni-trier.de\/db\/journals\/corr\/corr1506.html#YuZSSX15"},{"key":"29_CR79","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"29_CR80","doi-asserted-by":"crossref","unstructured":"Zhang, W., Zhu, M., Derpanis, K.G.: From actemes to action: a strongly-supervised representation for detailed action understanding. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2248\u20132255 (2013)","DOI":"10.1109\/ICCV.2013.280"},{"key":"29_CR81","unstructured":"Zhao, S., Liu, Z., Lin, J., Zhu, J.Y., Han, S.: Differentiable augmentation for data-efficient GAN training. arXiv preprint arXiv:2006.10738 (2020)"},{"key":"29_CR82","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1007\/978-3-319-10605-2_27","volume-title":"Computer Vision","author":"Y Zhu","year":"2014","unstructured":"Zhu, Y., Fathi, A., Fei-Fei, L.: Reasoning about object affordances in a knowledge base representation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 408\u2013424. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10605-2_27"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19787-1_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T19:23:41Z","timestamp":1710357821000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19787-1_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197864","9783031197871"],"references-count":82,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19787-1_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"21 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}