{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T09:10:30Z","timestamp":1788945030958,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370976","type":"print"},{"value":"9783032370983","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37098-3_24","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T09:02:13Z","timestamp":1788944533000},"page":"437-453","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ObjectForesight: Predicting Future 3D Object Trajectories from\u00a0Human Videos"],"prefix":"10.1007","author":[{"given":"Rustin","family":"Soraki","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Homanga","family":"Bharadhwaj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Farhadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roozbeh","family":"Mottaghi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"24_CR1","unstructured":"Assran, M., et al.: V-jepa 2: Self-supervised video models enable understanding, prediction and planning. arXiv preprint arXiv:2506.09985 (2025)"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Banerjee, P.,et al.: HOT3D: Hand and object tracking in 3D from egocentric multi-view videos. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00662"},{"key":"24_CR3","unstructured":"Bao, C., Xu, J., Wang, X., Gupta, A., Bharadhwaj, H.: Handsonvlm: Vision-language models for hand-object interaction prediction. Trans. Mach. Learn. Res. (2025)"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Bharadhwaj, H., Mottaghi, R., Gupta, A., Tulsiani, S.: Track2act: Predicting point tracks from internet videos enables generalizable robot manipulation. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73116-7_18"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Brahmbhatt, S., Handa, A., Hays, J., Fox, D.: Contactgrasp: Functional multi-finger grasp synthesis from contact. In: IROS (2019)","DOI":"10.1109\/IROS40897.2019.8967960"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Chen, K., Ramanan, D., Khurana, T.: Using diffusion priors for video amodal segmentation. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02131"},{"key":"24_CR7","unstructured":"Chen, M., et\u00a0al.: Flowing from reasoning to motion: Learning 3d hand trajectory prediction from egocentric human interaction videos. arXiv preprint arXiv:2512.16907 (2025)"},{"key":"24_CR8","unstructured":"Chen, X., et al.: Sam 3d: 3dfy anything in images. arXiv preprint arXiv:2511.16624 (2025)"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Damen, D., et al.: Scaling egocentric vision: The epic-kitchens dataset. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01225-0_44"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Das, P., Xu, C., Doell, R.F., Corso, J.J.: A thousand frames in just a few words: Lingual description of videos through latent topics and sparse object stitching. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.340"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Doersch, C., et al.: Tapir: Tracking any point with per-frame initialization and temporal refinement. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00923"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Ge, L., Ren, Z., Li, Y., Xue, Z., Wang, Y., Cai, J., Yuan, J.: 3d hand shape and pose estimation from a single rgb image, In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01109"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Goyal, M., Modi, S., Goyal, R., Gupta, S.: Human hands as probes for interactive object understanding. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00329"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Goyal, R., et\u00a0al.: The\" something something\" video database for learning and evaluating visual common sense. In: CVPR (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"24_CR15","unstructured":"Grauman, K., et\u00a0al.: Ego4d: Around the world in 3,000 hours of egocentric video. In: CVPR (2022)"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Gu, J., et al.: Vip3d: End-to-end visual trajectory prediction via 3d agent queries. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00532"},{"key":"24_CR17","unstructured":"Hafner, D., Lillicrap, T.P., Ba, J., Norouzi, M.: Dream to control: Learning behaviors by latent imagination. arXiv preprint arXiv:1912.01603 (2019)"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Harley, A.W., et\u00a0al.: Alltracker: Efficient dense point tracking at high resolution. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.00499"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Hasson, Y., et al.: Learning joint reconstruction of hands and manipulated objects. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01208"},{"key":"24_CR20","doi-asserted-by":"crossref","unstructured":"He, Y., Sun, W., Huang, H., Liu, J., Fan, H., Sun, J.: Pvn3d: A deep point-wise 3d keypoints voting network for 6dof pose estimation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01165"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Hu, Y., Hugonot, J., Fua, P., Salzmann, M.: Segmentation-driven 6d object pose estimation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00350"},{"key":"24_CR22","doi-asserted-by":"crossref","unstructured":"Iqbal, U., Molchanov, P., Breuel Juergen, Gall, T., Kautz, J.: Hand pose estimation via latent 2.5 d heatmap regression. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01252-6_8"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Jeannerod, M.: Neural simulation of action: a unifying mechanism for motor cognition. Neuroimage 14(1) (2001)","DOI":"10.1006\/nimg.2001.0832"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Karaev, N., Rocco, I., Graham, B., Neverova, N., Vedaldi, A., Rupprecht, C.: Cotracker: It is better to track together. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Kehl, W., Manhardt, F., Tombari, F., Ilic, S., Navab, N.: Ssd-6d: Making rgb-based 3d detection and 6d pose estimation great again. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.169"},{"key":"24_CR26","unstructured":"Kipf, T., van\u00a0der Pol, E., Welling, M.: Contrastive learning of structured world models. In: ICLR (2020)"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Li, K., Li, P., Liu, T., Li, Y., Huang, S.: Maniptrans: Efficient dexterous bimanual manipulation transfer via residual learning. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00656"},{"key":"24_CR28","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, M., Rehg, J.M.: In the eye of beholder: Joint learning of gaze and actions in first person video. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Liu, S., Tripathi, S., Majumdar, S., Wang, X.: Joint hand motion and interaction hotspots prediction from egocentric videos. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00328"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Mo, K., Guibas, L.J., Mukadam, M., Gupta, A., Tulsiani, S.: Where2act: From pixels to actions for articulated 3d objects. In: CVPR (2020)","DOI":"10.1109\/ICCV48922.2021.00674"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., Bagherinezhad, H., Rastegari, M., Farhadi, A.: Newtonian image understanding: Unfolding the dynamics of objects in static images. In: CVPR (2015)","DOI":"10.1109\/CVPR.2016.383"},{"key":"24_CR32","doi-asserted-by":"crossref","unstructured":"Nagarajan, T., Feichtenhofer, C., Grauman, K.: Grounded human-object interaction hotspots from video. In: CVPR (2019)","DOI":"10.1109\/ICCV.2019.00878"},{"key":"24_CR33","unstructured":"Padalkar, A., et al.: Open x-embodiment: Robotic learning datasets and rt-x models. arXiv preprint arXiv:2310.08864 (2023)"},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"24_CR35","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., de\u00a0Vries, H., Dumoulin, V., Courville, A.C.: Film: Visual reasoning with a general conditioning layer. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"24_CR36","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: Deep hierarchical feature learning on point sets in a metric space. In: NeurIPS (2017)"},{"key":"24_CR37","unstructured":"Ravi, N., et\u00a0al.: Sam 2: Segment anything in images and videos. In: ICLR (2025)"},{"key":"24_CR38","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"24_CR39","doi-asserted-by":"crossref","unstructured":"Rong, Y., Shiratori, T., Joo, H.: Frankmocap: Fast monocular 3d hand and body motion capture by regression and integration. arXiv preprint arXiv:2008.08324 (2020)","DOI":"10.1109\/ICCVW54120.2021.00201"},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Shan, D., Geng, J., Shu, M., Fouhey, D.: Understanding human hands in contact at internet scale. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00989"},{"key":"24_CR41","unstructured":"De\u00a0la Torre, F., et al.: Guide to the carnegie mellon university multimodal activity (cmu-mmac) database (2009)"},{"key":"24_CR42","unstructured":"Villegas, R., Yang, J., Hong, S., Lin, X., Lee, H.: Decomposing motion and content for natural video sequence prediction. In: ICLR (2017)"},{"key":"24_CR43","doi-asserted-by":"crossref","unstructured":"Walker, J., Doersch, C., Gupta, A., Hebert, M.: An uncertain future: Forecasting from static images using variational autoencoders. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46478-7_51"},{"key":"24_CR44","doi-asserted-by":"crossref","unstructured":"Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic graph cnn for learning on point clouds. ACM Trans. Graph. (2019)","DOI":"10.1145\/3326362"},{"key":"24_CR45","doi-asserted-by":"crossref","unstructured":"Wen, B., Yang, W., Kautz, J., Birchfield, S.T.: Foundationpose: Unified 6d pose estimation and tracking of novel objects. In: CVPR (2023)","DOI":"10.1109\/CVPR52733.2024.01692"},{"key":"24_CR46","doi-asserted-by":"crossref","unstructured":"Wu, X., et al.: Point transformer v3: Simpler, faster, stronger. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00463"},{"key":"24_CR47","doi-asserted-by":"crossref","unstructured":"Xiang, J., et al.: Structured 3d latents for scalable and versatile 3d generation. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"24_CR48","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Schmidt, T., Narayanan, V., Fox, D.: Posecnn: A convolutional neural network for 6d object pose estimation in cluttered scenes, arXiv (2018).","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"24_CR49","doi-asserted-by":"crossref","unstructured":"Xiao, Y., et al.: Spatialtrackerv2: Advancing 3d point tracking with explicit camera motion. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.00633"},{"key":"24_CR50","doi-asserted-by":"crossref","unstructured":"Yoshida, T., Kurita, S., Nishimura, T., Mori, S.: Generating 6dof object manipulation trajectories from action description in egocentric vision. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.01619"},{"key":"24_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhou, S., Stent, S., Shi, J.: Fine-grained egocentric hand-object segmentation: Dataset, model, and applications. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19818-2_8"},{"key":"24_CR52","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Barnes, C., Lu, J., Yang, J., Li, H.: On the continuity of rotation representations in neural networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00589"},{"key":"24_CR53","unstructured":"Zhu, J., et al.: Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (2025)"},{"key":"24_CR54","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Brox, T.: Learning to estimate 3d hand pose from single rgb images. In: CVPR (2017)","DOI":"10.1109\/ICCV.2017.525"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37098-3_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T09:02:38Z","timestamp":1788944558000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37098-3_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370976","9783032370983"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37098-3_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}