{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T07:18:18Z","timestamp":1761808698885,"version":"3.40.3"},"publisher-location":"Cham","reference-count":76,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031732010"},{"type":"electronic","value":"9783031732027"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"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\/978-3-031-73202-7_4","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T14:18:46Z","timestamp":1732112326000},"page":"57-75","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Bidirectional Progressive Transformer for\u00a0Interaction Intention Anticipation"],"prefix":"10.1007","author":[{"given":"Zichen","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongchen","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Kang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"issue":"4","key":"4_CR1","doi-asserted-by":"publisher","first-page":"6033","DOI":"10.1109\/LRA.2020.3010742","volume":"5","author":"V Adeli","year":"2020","unstructured":"Adeli, V., Adeli, E., Reid, I., Niebles, J.C., Rezatofighi, H.: Socially and contextually aware human motion and pose forecasting. IEEE Robot. Autom. Lett. 5(4), 6033\u20136040 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Adeli, V., et al.: TRiPOD: human trajectory and pose dynamics forecasting in the wild. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13390\u201313400 (2021)","DOI":"10.1109\/ICCV48922.2021.01314"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Bahl, S., Gupta, A., Pathak, D.: Human-to-robot imitation in the wild. arXiv preprint arXiv:2207.09450 (2022)","DOI":"10.15607\/RSS.2022.XVIII.026"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Bao, W., et al.: Uncertainty-aware state space transformer for egocentric 3D hand trajectory forecasting. arXiv preprint arXiv:2307.08243 (2023)","DOI":"10.1109\/ICCV51070.2023.01260"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Bertasius, G., Park, H.S., Yu, S.X., Shi, J.: First person action-object detection with egonet. arXiv preprint arXiv:1603.04908 (2016)","DOI":"10.15607\/RSS.2017.XIII.012"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Bertasius, G., Soo\u00a0Park, H., Yu, S.X., Shi, J.: Unsupervised learning of important objects from first-person videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1956\u20131964 (2017)","DOI":"10.1109\/ICCV.2017.216"},{"key":"4_CR7","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: ICML, vol.\u00a02, p.\u00a04 (2021)"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Bewley, A., Ge, Z., Ott, L., Ramos, F., Upcroft, B.: Simple online and realtime tracking. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 3464\u20133468. IEEE (2016)","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"4_CR9","unstructured":"Bharadhwaj, H., Gupta, A., Tulsiani, S., Kumar, V.: Zero-shot robot manipulation from passive human videos. arXiv preprint arXiv:2302.02011 (2023)"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Chen, C.F.R., Fan, Q., Panda, R.: CrossViT: cross-attention multi-scale vision transformer for image classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 357\u2013366 (2021)","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Chen, G., Chen, Z., Fan, S., Zhang, K.: Unsupervised sampling promoting for stochastic human trajectory prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17874\u201317884 (2023)","DOI":"10.1109\/CVPR52729.2023.01714"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Choi, C., Dariush, B.: Looking to relations for future trajectory forecast. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00101"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Damen, D., et al.: Scaling egocentric vision: the epic-kitchens dataset. In: European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01225-0_44"},{"key":"4_CR15","unstructured":"Dessalene, E., Devaraj, C., Maynord, M., Fermuller, C., Aloimonos, Y.: Forecasting action through contact representations from first person video. IEEE Trans. Pattern Anal. Mach. Intell. (2021)"},{"key":"4_CR16","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Fan, C., Lee, J., Ryoo, M.S.: Forecasting hands and objects in future frames. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops (2018)","DOI":"10.1007\/978-3-030-11015-4_12"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Fang, K., Wu, T.L., Yang, D., Savarese, S., Lim, J.J.: Demo2Vec: reasoning object affordances from online videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2139\u20132147 (2018)","DOI":"10.1109\/CVPR.2018.00228"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"4_CR20","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1016\/j.jvcir.2017.10.004","volume":"49","author":"A Furnari","year":"2017","unstructured":"Furnari, A., Battiato, S., Grauman, K., Farinella, G.M.: Next-active-object prediction from egocentric videos. J. Vis. Commun. Image Represent. 49, 401\u2013411 (2017)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Furnari, A., Battiato, S., Maria\u00a0Farinella, G.: Leveraging uncertainty to rethink loss functions and evaluation measures for egocentric action anticipation. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops (2018)","DOI":"10.1007\/978-3-030-11021-5_24"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Furnari, A., Farinella, G.M.: What would you expect? Anticipating egocentric actions with rolling-unrolling LSTMs and modality attention. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6252\u20136261 (2019)","DOI":"10.1109\/ICCV.2019.00635"},{"issue":"11","key":"4_CR23","doi-asserted-by":"publisher","first-page":"4021","DOI":"10.1109\/TPAMI.2020.2992889","volume":"43","author":"A Furnari","year":"2020","unstructured":"Furnari, A., Farinella, G.M.: Rolling-unrolling LSTMs for action anticipation from first-person video. IEEE Trans. Pattern Anal. Mach. Intell. 43(11), 4021\u20134036 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Geng, Y., An, B., Geng, H., Chen, Y., Yang, Y., Dong, H.: End-to-end affordance learning for robotic manipulation. arXiv preprint arXiv:2209.12941 (2022)","DOI":"10.1109\/ICRA48891.2023.10161571"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Grauman, K.: Anticipative video transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13505\u201313515 (2021)","DOI":"10.1109\/ICCV48922.2021.01325"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Gong, D., Lee, J., Kim, M., Ha, S.J., Cho, M.: Future transformer for long-term action anticipation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3052\u20133061 (2022)","DOI":"10.1109\/CVPR52688.2022.00306"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Gong, J., Foo, L.G., Fan, Z., Ke, Q., Rahmani, H., Liu, J.: DiffPose: toward more reliable 3D pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13041\u201313051 (2023)","DOI":"10.1109\/CVPR52729.2023.01253"},{"key":"4_CR28","unstructured":"Grauman, K., et\u00a0al.: Ego4D: around the world in 3,000 hours of egocentric video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18995\u201319012 (2022)"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Gupta, A., Johnson, J., Fei-Fei, L., Savarese, S., Alahi, A.: Social GAN: socially acceptable trajectories with generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2255\u20132264 (2018)","DOI":"10.1109\/CVPR.2018.00240"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Jiang, H., Liu, S., Wang, J., Wang, X.: Hand-object contact consistency reasoning for human grasps generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11107\u201311116 (2021)","DOI":"10.1109\/ICCV48922.2021.01092"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Judd, T., Ehinger, K., Durand, F., Torralba, A.: Learning to predict where humans look. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 2106\u20132113. IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459462"},{"issue":"1","key":"4_CR32","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.cviu.2010.08.002","volume":"115","author":"H Kjellstr\u00f6m","year":"2011","unstructured":"Kjellstr\u00f6m, H., Romero, J., Kragi\u0107, D.: Visual object-action recognition: inferring object affordances from human demonstration. Comput. Vis. Image Underst. 115(1), 81\u201390 (2011)","journal-title":"Comput. Vis. Image Underst."},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Lee, N., Choi, W., Vernaza, P., Choy, C.B., Torr, P.H., Chandraker, M.: DESIRE: distant future prediction in dynamic scenes with interacting agents. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 336\u2013345 (2017)","DOI":"10.1109\/CVPR.2017.233"},{"key":"4_CR34","doi-asserted-by":"publisher","first-page":"102471","DOI":"10.1016\/j.rcim.2022.102471","volume":"80","author":"C Li","year":"2023","unstructured":"Li, C., Zheng, P., Yin, Y., Pang, Y.M., Huo, S.: An AR-assisted deep reinforcement learning-based approach towards mutual-cognitive safe human-robot interaction. Robot. Comput.-Integr. Manuf. 80, 102471 (2023)","journal-title":"Robot. Comput.-Integr. Manuf."},{"key":"4_CR35","unstructured":"Li, K., et al.: UniFormerV2: spatiotemporal learning by arming image ViTs with video uniformer. arXiv preprint arXiv:2211.09552 (2022)"},{"key":"4_CR36","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: Proceedings of the European conference on computer vision (ECCV), pp. 619\u2013635 (2018)","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"4_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"704","DOI":"10.1007\/978-3-030-58452-8_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Liu","year":"2020","unstructured":"Liu, M., Tang, S., Li, Y., Rehg, J.M.: Forecasting human-object interaction: joint prediction of motor attention and\u00a0actions in first person video. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part I. LNCS, vol. 12346, pp. 704\u2013721. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_41"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Liu, S., Jiang, H., Xu, J., Liu, S., Wang, X.: Semi-supervised 3D hand-object poses estimation with interactions in time. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14687\u201314697 (2021)","DOI":"10.1109\/CVPR46437.2021.01445"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Liu, S., Tripathi, S., Majumdar, S., Wang, X.: Joint hand motion and interaction hotspots prediction from egocentric videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3282\u20133292 (2022)","DOI":"10.1109\/CVPR52688.2022.00328"},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"Liu, T., Lam, K.M.: A hybrid egocentric activity anticipation framework via memory-augmented recurrent and one-shot representation forecasting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13904\u201313913 (2022)","DOI":"10.1109\/CVPR52688.2022.01353"},{"key":"4_CR41","doi-asserted-by":"crossref","unstructured":"Luo, H., Zhai, W., Zhang, J., Cao, Y., Tao, D.: Learning affordance grounding from exocentric images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2252\u20132261 (2022)","DOI":"10.1109\/CVPR52688.2022.00229"},{"key":"4_CR42","doi-asserted-by":"crossref","unstructured":"Luo, H., Zhai, W., Zhang, J., Cao, Y., Tao, D.: Learning visual affordance grounding from demonstration videos. IEEE Transa. Neural Netw. Learn. Syst. (2023)","DOI":"10.1109\/TNNLS.2023.3298638"},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"Luo, H., Zhai, W., Zhang, J., Cao, Y., Tao, D.: Leverage interactive affinity for affordance learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 6809\u20136819 (2023)","DOI":"10.1109\/CVPR52729.2023.00658"},{"key":"4_CR44","doi-asserted-by":"crossref","unstructured":"Mandlekar, A., Xu, D., Mart\u00edn-Mart\u00edn, R., Savarese, S., Fei-Fei, L.: Learning to generalize across long-horizon tasks from human demonstrations. arXiv preprint arXiv:2003.06085 (2020)","DOI":"10.15607\/RSS.2020.XVI.061"},{"key":"4_CR45","doi-asserted-by":"crossref","unstructured":"Mangalam, K., An, Y., Girase, H., Malik, J.: From goals, waypoints & paths to long term human trajectory forecasting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15233\u201315242 (2021)","DOI":"10.1109\/ICCV48922.2021.01495"},{"key":"4_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1007\/978-3-030-58536-5_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"K Mangalam","year":"2020","unstructured":"Mangalam, K., et al.: It is not the journey but the destination: endpoint conditioned trajectory prediction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part II. LNCS, vol. 12347, pp. 759\u2013776. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_45"},{"key":"4_CR47","doi-asserted-by":"crossref","unstructured":"Mascar\u00f3, E.V., Ahn, H., Lee, D.: Intention-conditioned long-term human egocentric action anticipation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 6048\u20136057 (2023)","DOI":"10.1109\/WACV56688.2023.00599"},{"key":"4_CR48","doi-asserted-by":"crossref","unstructured":"Mendonca, R., Bahl, S., Pathak, D.: Structured world models from human videos. arXiv preprint arXiv:2308.10901 (2023)","DOI":"10.15607\/RSS.2023.XIX.012"},{"key":"4_CR49","doi-asserted-by":"crossref","unstructured":"Miech, A., Laptev, I., Sivic, J., Wang, H., Torresani, L., Tran, D.: Leveraging the present to anticipate the future in videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00351"},{"key":"4_CR50","doi-asserted-by":"crossref","unstructured":"Mohamed, A., Qian, K., Elhoseiny, M., Claudel, C.: Social-STGCNN: a social spatio-temporal graph convolutional neural network for human trajectory prediction. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 14424\u201314432 (2020)","DOI":"10.1109\/CVPR42600.2020.01443"},{"key":"4_CR51","doi-asserted-by":"crossref","unstructured":"Myers, A., Teo, C.L., Ferm\u00fcller, C., Aloimonos, Y.: Affordance detection of tool parts from geometric features. In: 2015 IEEE International Conference on Robotics and Automation (ICRA), pp. 1374\u20131381. IEEE (2015)","DOI":"10.1109\/ICRA.2015.7139369"},{"key":"4_CR52","doi-asserted-by":"crossref","unstructured":"Nagarajan, T., Feichtenhofer, C., Grauman, K.: Grounded human-object interaction hotspots from video. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8688\u20138697 (2019)","DOI":"10.1109\/ICCV.2019.00878"},{"key":"4_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1007\/978-3-031-19830-4_32","volume-title":"Computer Vision \u2013 ECCV 2022","author":"M Nawhal","year":"2022","unstructured":"Nawhal, M., Jyothi, A.A., Mori, G.: Rethinking learning approaches for long-term action anticipation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13694, pp. 558\u2013576. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19830-4_32"},{"key":"4_CR54","doi-asserted-by":"crossref","unstructured":"Parsaeifard, B., Saadatnejad, S., Liu, Y., Mordan, T., Alahi, A.: Learning decoupled representations for human pose forecasting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2294\u20132303 (2021)","DOI":"10.1109\/ICCVW54120.2021.00259"},{"issue":"18","key":"4_CR55","doi-asserted-by":"publisher","first-page":"2397","DOI":"10.1016\/j.visres.2005.03.019","volume":"45","author":"RJ Peters","year":"2005","unstructured":"Peters, R.J., Iyer, A., Itti, L., Koch, C.: Components of bottom-up gaze allocation in natural images. Vision. Res. 45(18), 2397\u20132416 (2005)","journal-title":"Vision. Res."},{"key":"4_CR56","unstructured":"Plizzari, C., et al.: An outlook into the future of egocentric vision. arXiv preprint arXiv:2308.07123 (2023)"},{"key":"4_CR57","unstructured":"Qi, H., Wang, X., Pathak, D., Ma, Y., Malik, J.: Learning long-term visual dynamics with region proposal interaction networks. arXiv preprint arXiv:2008.02265 (2020)"},{"key":"4_CR58","doi-asserted-by":"crossref","unstructured":"Ragusa, F., Farinella, G.M., Furnari, A.: StillFast: an end-to-end approach for short-term object interaction anticipation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3636\u20133645 (2023)","DOI":"10.1109\/CVPRW59228.2023.00371"},{"key":"4_CR59","doi-asserted-by":"publisher","first-page":"103252","DOI":"10.1016\/j.cviu.2021.103252","volume":"211","author":"I Rodin","year":"2021","unstructured":"Rodin, I., Furnari, A., Mavroeidis, D., Farinella, G.M.: Predicting the future from first person (egocentric) vision: a survey. Comput. Vis. Image Underst. 211, 103252 (2021)","journal-title":"Comput. Vis. Image Underst."},{"key":"4_CR60","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015, Part III. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"4_CR61","doi-asserted-by":"crossref","unstructured":"Shen, J., Dudley, J., Kristensson, P.O.: Fast and robust mid-air gesture typing for AR headsets using 3D trajectory decoding. IEEE Trans. Vis. Comput. Graph. (2023)","DOI":"10.1109\/TVCG.2023.3320218"},{"key":"4_CR62","unstructured":"Sohn, K., Lee, H., Yan, X.: Learning structured output representation using deep conditional generative models. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"4_CR63","doi-asserted-by":"crossref","unstructured":"Song, D., et al.: Predicting human intention in visual observations of hand\/object interactions. In: 2013 IEEE International Conference on Robotics and Automation, pp. 1608\u20131615. IEEE (2013)","DOI":"10.1109\/ICRA.2013.6630785"},{"key":"4_CR64","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"4_CR65","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"issue":"1","key":"4_CR66","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/BF00130487","volume":"7","author":"MJ Swain","year":"1991","unstructured":"Swain, M.J., Ballard, D.H.: Color indexing. Int. J. Comput. Vision 7(1), 11\u201332 (1991)","journal-title":"Int. J. Comput. Vision"},{"key":"4_CR67","doi-asserted-by":"crossref","unstructured":"Tu, Z., et al.: Consistent 3D hand reconstruction in video via self-supervised learning. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3247907"},{"key":"4_CR68","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"4_CR69","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Wang","year":"2016","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"key":"4_CR70","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: SegFormer: simple and efficient design for semantic segmentation with transformers. Adv. Neural. Inf. Process. Syst. 34, 12077\u201312090 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR71","doi-asserted-by":"crossref","unstructured":"Xu, H., Zhang, J., Cai, J., Rezatofighi, H., Tao, D.: GMFlow: learning optical flow via global matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8121\u20138130 (2022)","DOI":"10.1109\/CVPR52688.2022.00795"},{"key":"4_CR72","doi-asserted-by":"crossref","unstructured":"Yang, Y., Zhai, W., Luo, H., Cao, Y., Luo, J., Zha, Z.J.: Grounding 3D object affordance from 2D interactions in images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10905\u201310915 (2023)","DOI":"10.1109\/ICCV51070.2023.01001"},{"key":"4_CR73","doi-asserted-by":"crossref","unstructured":"Yang, Y., Zhai, W., Luo, H., Cao, Y., Zha, Z.J.: LEMON: learning 3D human-object interaction relation from 2D images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16284\u201316295 (2024)","DOI":"10.1109\/CVPR52733.2024.01541"},{"key":"4_CR74","doi-asserted-by":"crossref","unstructured":"Ye, Y., Singh, M., Gupta, A., Tulsiani, S.: Compositional video prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10353\u201310362 (2019)","DOI":"10.1109\/ICCV.2019.01045"},{"key":"4_CR75","doi-asserted-by":"crossref","unstructured":"Zhai, W., Cao, Y., Zhang, J., Xie, H., Tao, D., Zha, Z.J.: On exploring multiplicity of primitives and attributes for texture recognition in the wild. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3325230"},{"issue":"10","key":"4_CR76","doi-asserted-by":"publisher","first-page":"2472","DOI":"10.1007\/s11263-022-01642-4","volume":"130","author":"W Zhai","year":"2022","unstructured":"Zhai, W., Luo, H., Zhang, J., Cao, Y., Tao, D.: One-shot object affordance detection in the wild. Int. J. Comput. Vision 130(10), 2472\u20132500 (2022)","journal-title":"Int. J. Comput. Vision"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73202-7_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T15:05:09Z","timestamp":1732115109000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73202-7_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031732010","9783031732027"],"references-count":76,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73202-7_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}