{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:14:15Z","timestamp":1771611255422,"version":"3.50.1"},"publisher-location":"Cham","reference-count":85,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198175","type":"print"},{"value":"9783031198182","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\/978-3-031-19818-2_8","type":"book-chapter","created":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T16:21:10Z","timestamp":1666369270000},"page":"127-145","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":47,"title":["Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and\u00a0Applications"],"prefix":"10.1007","author":[{"given":"Lingzhi","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Shenghao","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Simon","family":"Stent","sequence":"additional","affiliation":[]},{"given":"Jianbo","family":"Shi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,22]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Bambach, S., Lee, S., Crandall, D.J., Yu, C.: Lending a hand: detecting hands and recognizing activities in complex egocentric interactions. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1949\u20131957 (2015)","DOI":"10.1109\/ICCV.2015.226"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Brahmbhatt, S., Handa, A., Hays, J., Fox, D.: ContactGrasp: functional multi-finger grasp synthesis from contact. In: 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2386\u20132393. IEEE (2019)","DOI":"10.1109\/IROS40897.2019.8967960"},{"key":"8_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1007\/978-3-030-58601-0_22","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Brahmbhatt","year":"2020","unstructured":"Brahmbhatt, S., Tang, C., Twigg, C.D., Kemp, C.C., Hays, J.: ContactPose: a dataset of grasps with object contact and hand pose. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 361\u2013378. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_22"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Cai, M., Lu, F., Sato, Y.: Generalizing hand segmentation in egocentric videos with uncertainty-guided model adaptation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14392\u201314401 (2020)","DOI":"10.1109\/CVPR42600.2020.01440"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Cai, Y., Ge, L., Cai, J., Yuan, J.: Weakly-supervised 3D hand pose estimation from monocular RGB images. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 666\u2013682 (2018)","DOI":"10.1007\/978-3-030-01231-1_41"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Cao, Z., Radosavovic, I., Kanazawa, A., Malik, J.: Reconstructing hand-object interactions in the wild. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12417\u201312426 (2021)","DOI":"10.1109\/ICCV48922.2021.01219"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Corona, E., Pumarola, A., Alenya, G., Moreno-Noguer, F., Rogez, G.: GanHand: predicting human grasp affordances in multi-object scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5031\u20135041 (2020)","DOI":"10.1109\/CVPR42600.2020.00508"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Damen, D., et al.: Scaling egocentric vision: the epic-kitchens dataset. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 720\u2013736 (2018)","DOI":"10.1007\/978-3-030-01225-0_44"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Fang, H.S., Sun, J., Wang, R., Gou, M., Li, Y.L., Lu, C.: InstaBoost: boosting instance segmentation via probability map guided copy-pasting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 682\u2013691 (2019)","DOI":"10.1109\/ICCV.2019.00077"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Fathi, A., Ren, X., Rehg, J.M.: Learning to recognize objects in egocentric activities. In: CVPR 2011, pp. 3281\u20133288. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"8_CR11","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":"8_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1007\/978-3-030-58610-2_42","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C Gao","year":"2020","unstructured":"Gao, C., Saraf, A., Huang, J.-B., Kopf, J.: Flow-edge guided video completion. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 713\u2013729. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_42"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., et al.: Simple copy-paste is a strong data augmentation method for instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2918\u20132928 (2021)","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Malik, J., Johnson, J.: Mesh R-CNN. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9785\u20139795 (2019)","DOI":"10.1109\/ICCV.2019.00988"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Goyal, M., Modi, S., Goyal, R., Gupta, S.: Human hands as probes for interactive object understanding. arXiv preprint arXiv:2112.09120 (2021)","DOI":"10.1109\/CVPR52688.2022.00329"},{"key":"8_CR16","unstructured":"Grauman, K., et al.: Ego4D: around the world in 3,000 hours of egocentric video. arXiv preprint arXiv:2110.07058 (2021)"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Hasson, Y., Tekin, B., Bogo, F., Laptev, I., Pollefeys, M., Schmid, C.: Leveraging photometric consistency over time for sparsely supervised hand-object reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 571\u2013580 (2020)","DOI":"10.1109\/CVPR42600.2020.00065"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Hasson, Y., Varol, G., Schmid, C., Laptev, I.: Towards unconstrained joint hand-object reconstruction from RGB videos. In: 2021 International Conference on 3D Vision (3DV), pp. 659\u2013668. IEEE (2021)","DOI":"10.1109\/3DV53792.2021.00075"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Hasson, Y., et al.: Learning joint reconstruction of hands and manipulated objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11807\u201311816 (2019)","DOI":"10.1109\/CVPR.2019.01208"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Jiang, H., Liu, S., Wang, J., Wang, X.: Hand-object contact consistency reasoning for human grasps generation. arXiv preprint arXiv:2104.03304 (2021)","DOI":"10.1109\/ICCV48922.2021.01092"},{"issue":"1","key":"8_CR22","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1023\/A:1013200319198","volume":"46","author":"MJ Jones","year":"2002","unstructured":"Jones, M.J., Rehg, J.M.: Statistical color models with application to skin detection. Int. J. Comput. Vis. 46(1), 81\u201396 (2002). https:\/\/doi.org\/10.1023\/A:1013200319198","journal-title":"Int. J. Comput. Vis."},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Karunratanakul, K., Yang, J., Zhang, Y., Black, M.J., Muandet, K., Tang, S.: Grasping field: learning implicit representations for human grasps. In: 2020 International Conference on 3D Vision (3DV), pp. 333\u2013344. IEEE (2020)","DOI":"10.1109\/3DV50981.2020.00043"},{"key":"8_CR24","unstructured":"Kim, S., Chi, H.G.: First-person view hand segmentation of multi-modal hand activity video dataset. BMVC 2020 (2020)"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Wu, Y., He, K., Girshick, R.: Pointrend: Image segmentation as rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9799\u20139808 (2020)","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Kulon, D., Guler, R.A., Kokkinos, I., Bronstein, M.M., Zafeiriou, S.: Weakly-supervised mesh-convolutional hand reconstruction in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4990\u20135000 (2020)","DOI":"10.1109\/CVPR42600.2020.00504"},{"key":"8_CR27","unstructured":"Kulon, D., Wang, H., G\u00fcler, R.A., Bronstein, M., Zafeiriou, S.: Single image 3D hand reconstruction with mesh convolutions. arXiv preprint arXiv:1905.01326 (2019)"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Kundu, A., Li, Y., Rehg, J.M.: 3D-RCNN: instance-level 3D object reconstruction via render-and-compare. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3559\u20133568 (2018)","DOI":"10.1109\/CVPR.2018.00375"},{"key":"8_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1007\/978-3-030-58580-8_16","volume-title":"Computer Vision \u2013 ECCV 2020","author":"W Kuo","year":"2020","unstructured":"Kuo, W., Angelova, A., Lin, T.-Y., Dai, A.: Mask2CAD: 3D shape prediction by learning to segment and retrieve. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 260\u2013277. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_16"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Lee, S., Bambach, S., Crandall, D.J., Franchak, J.M., Yu, C.: This hand is my hand: a probabilistic approach to hand disambiguation in egocentric video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 543\u2013550 (2014)","DOI":"10.1109\/CVPRW.2014.86"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Li, C., Kitani, K.M.: Model recommendation with virtual probes for egocentric hand detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2624\u20132631 (2013)","DOI":"10.1109\/ICCV.2013.326"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Li, C., Kitani, K.M.: Pixel-level hand detection in ego-centric videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3570\u20133577 (2013)","DOI":"10.1109\/CVPR.2013.458"},{"key":"8_CR33","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":"8_CR34","doi-asserted-by":"crossref","unstructured":"Li, Y., Ye, Z., Rehg, J.M.: Delving into egocentric actions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 287\u2013295 (2015)","DOI":"10.1109\/CVPR.2015.7298625"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Lim, J.J., Pirsiavash, H., Torralba, A.: Parsing IKEA objects: fine pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2992\u20132999 (2013)","DOI":"10.1109\/ICCV.2013.372"},{"key":"8_CR36","unstructured":"Lin, F., Martinez, T.: Ego2Hands: a dataset for egocentric two-hand segmentation and detection. arXiv preprint arXiv:2011.07252 (2020)"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Lin, F., Wilhelm, C., Martinez, T.: Two-hand global 3D pose estimation using monocular RGB. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2373\u20132381 (2021)","DOI":"10.1109\/WACV48630.2021.00242"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Lin, G., Milan, A., Shen, C., Reid, I.: RefineNet: multi-path refinement networks for high-resolution semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1925\u20131934 (2017)","DOI":"10.1109\/CVPR.2017.549"},{"key":"8_CR39","doi-asserted-by":"publisher","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"8_CR41","unstructured":"Mandikal, P., Grauman, K.: DexVIP: learning dexterous grasping with human hand pose priors from video. In: 5th Annual Conference on Robot Learning (2021)"},{"key":"8_CR42","doi-asserted-by":"crossref","unstructured":"Mandikal, P., Grauman, K.: Learning dexterous grasping with object-centric visual affordances. In: IEEE International Conference on Robotics and Automation, ICRA 2021, 30 May\u20135 June 2021, Xi\u2019an, China, pp. 6169\u20136176. IEEE (2021)","DOI":"10.1109\/ICRA48506.2021.9561802"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Michel, F., et al.: Global hypothesis generation for 6D object pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 462\u2013471 (2017)","DOI":"10.1109\/CVPR.2017.20"},{"key":"8_CR44","doi-asserted-by":"crossref","unstructured":"Moon, G., Chang, J.Y., Lee, K.M.: V2V-PoseNet: voxel-to-voxel prediction network for accurate 3D hand and human pose estimation from a single depth map. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5079\u20135088 (2018)","DOI":"10.1109\/CVPR.2018.00533"},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"Mueller, F., et al.: GANerated hands for real-time 3D hand tracking from monocular RGB. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 49\u201359 (2018)","DOI":"10.1109\/CVPR.2018.00013"},{"key":"8_CR46","doi-asserted-by":"crossref","unstructured":"Muller, L., Osman, A.A., Tang, S., Huang, C.H.P., Black, M.J.: On self-contact and human pose. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9990\u20139999 (2021)","DOI":"10.1109\/CVPR46437.2021.00986"},{"key":"8_CR47","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":"8_CR48","unstructured":"Nagarajan, T., Grauman, K.: Shaping embodied agent behavior with activity-context priors from egocentric video. Adv. Neural Inf. Process. Syst. 34, 29794\u201329805 (2021)"},{"key":"8_CR49","doi-asserted-by":"crossref","unstructured":"Nagarajan, T., Li, Y., Feichtenhofer, C., Grauman, K.: Ego-topo: environment affordances from egocentric video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 163\u2013172 (2020)","DOI":"10.1109\/CVPR42600.2020.00024"},{"key":"8_CR50","first-page":"7841","volume":"33","author":"S Narasimhaswamy","year":"2020","unstructured":"Narasimhaswamy, S., Nguyen, T., Nguyen, M.H.: Detecting hands and recognizing physical contact in the wild. Adv. Neural. Inf. Process. Syst. 33, 7841\u20137851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR51","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10975\u201310985 (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"8_CR52","doi-asserted-by":"crossref","unstructured":"Ren, X., Gu, C.: Figure-ground segmentation improves handled object recognition in egocentric video. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3137\u20133144. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5540074"},{"key":"8_CR53","doi-asserted-by":"crossref","unstructured":"Romero, J., Kjellstr\u00f6m, H., Kragic, D.: Hands in action: real-time 3D reconstruction of hands in interaction with objects. In: 2010 IEEE International Conference on Robotics and Automation, pp. 458\u2013463. IEEE (2010)","DOI":"10.1109\/ROBOT.2010.5509753"},{"key":"8_CR54","doi-asserted-by":"crossref","unstructured":"Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together. ACM Trans. Graph. (Proc. SIGGRAPH Asia) 36(6) (2017)","DOI":"10.1145\/3130800.3130883"},{"key":"8_CR55","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":"8_CR56","doi-asserted-by":"crossref","unstructured":"Rother, C., Kolmogorov, V., Blake, A.: \u201cGrabCut\u201d interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. (TOG) 23(3), 309\u2013314 (2004)","DOI":"10.1145\/1015706.1015720"},{"key":"8_CR57","doi-asserted-by":"crossref","unstructured":"Sahasrabudhe, M., Shu, Z., Bartrum, E., Alp Guler, R., Samaras, D., Kokkinos, I.: Lifting autoencoders: unsupervised learning of a fully-disentangled 3D morphable model using deep non-rigid structure from motion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00500"},{"key":"8_CR58","doi-asserted-by":"crossref","unstructured":"Shan, D., Geng, J., Shu, M., Fouhey, D.F.: Understanding human hands in contact at internet scale. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9869\u20139878 (2020)","DOI":"10.1109\/CVPR42600.2020.00989"},{"key":"8_CR59","unstructured":"Shan, D., Higgins, R., Fouhey, D.: COHESIV: contrastive object and hand embedding segmentation in video. Adv. Neural Inf. Process. Syst. 34, 5898\u20135909 (2021)"},{"key":"8_CR60","doi-asserted-by":"crossref","unstructured":"Sharp, T., et al.: Accurate, robust, and flexible real-time hand tracking. In: Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems, pp. 3633\u20133642 (2015)","DOI":"10.1145\/2702123.2702179"},{"key":"8_CR61","unstructured":"Shilkrot, R., Narasimhaswamy, S., Vazir, S., Hoai, M.: WorkingHands: a hand-tool assembly dataset for image segmentation and activity mining. In: BMVC, p. 258 (2019)"},{"key":"8_CR62","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"8_CR63","doi-asserted-by":"crossref","unstructured":"Sridhar, S., Oulasvirta, A., Theobalt, C.: Interactive markerless articulated hand motion tracking using RGB and depth data. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2456\u20132463 (2013)","DOI":"10.1109\/ICCV.2013.305"},{"key":"8_CR64","doi-asserted-by":"crossref","unstructured":"Sun, X., et al.: Pix3D: dataset and methods for single-image 3D shape modeling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2974\u20132983 (2018)","DOI":"10.1109\/CVPR.2018.00314"},{"key":"8_CR65","doi-asserted-by":"crossref","unstructured":"Suvorov, R., et al.: Resolution-robust large mask inpainting with Fourier convolutions. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2149\u20132159 (2022)","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"8_CR66","doi-asserted-by":"crossref","unstructured":"Tagliasacchi, A., Schr\u00f6der, M., Tkach, A., Bouaziz, S., Botsch, M., Pauly, M.: Robust articulated-ICP for real-time hand tracking. In: Computer Graphics Forum, vol. 34, pp. 101\u2013114. Wiley Online Library (2015)","DOI":"10.1111\/cgf.12700"},{"key":"8_CR67","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/978-3-030-58548-8_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"O Taheri","year":"2020","unstructured":"Taheri, O., Ghorbani, N., Black, M.J., Tzionas, D.: GRAB: a dataset of whole-body human grasping of objects. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 581\u2013600. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_34"},{"key":"8_CR68","doi-asserted-by":"crossref","unstructured":"Tang, Y., Tian, Y., Lu, J., Feng, J., Zhou, J.: Action recognition in RGB-D egocentric videos. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 3410\u20133414. IEEE (2017)","DOI":"10.1109\/ICIP.2017.8296915"},{"key":"8_CR69","doi-asserted-by":"crossref","unstructured":"Tekin, B., Bogo, F., Pollefeys, M.: H+O: unified egocentric recognition of 3D hand-object poses and interactions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4511\u20134520 (2019)","DOI":"10.1109\/CVPR.2019.00464"},{"key":"8_CR70","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Wang, X., Chen, H.: BoxInst: high-performance instance segmentation with box annotations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5443\u20135452 (2021)","DOI":"10.1109\/CVPR46437.2021.00540"},{"key":"8_CR71","doi-asserted-by":"crossref","unstructured":"Tulsiani, S., Gupta, S., Fouhey, D.F., Efros, A.A., Malik, J.: Factoring shape, pose, and layout from the 2D image of a 3D scene. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 302\u2013310 (2018)","DOI":"10.1109\/CVPR.2018.00039"},{"issue":"2","key":"8_CR72","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1007\/s11263-016-0895-4","volume":"118","author":"D Tzionas","year":"2016","unstructured":"Tzionas, D., Ballan, L., Srikantha, A., Aponte, P., Pollefeys, M., Gall, J.: Capturing hands in action using discriminative salient points and physics simulation. Int. J. Comput. Vis. 118(2), 172\u2013193 (2016). https:\/\/doi.org\/10.1007\/s11263-016-0895-4","journal-title":"Int. J. Comput. Vis."},{"key":"8_CR73","unstructured":"Urooj, A., Borji, A.: Analysis of hand segmentation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4710\u20134719 (2018)"},{"key":"8_CR74","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3349\u20133364 (2020)","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"8_CR75","doi-asserted-by":"crossref","unstructured":"Xiang, D., Joo, H., Sheikh, Y.: Monocular total capture: posing face, body, and hands in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10965\u201310974 (2019)","DOI":"10.1109\/CVPR.2019.01122"},{"key":"8_CR76","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 preprint arXiv:1711.00199 (2017)","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"8_CR77","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 418\u2013434 (2018)","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"8_CR78","doi-asserted-by":"crossref","unstructured":"Yang, L., Yao, A.: Disentangling latent hands for image synthesis and pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9877\u20139886 (2019)","DOI":"10.1109\/CVPR.2019.01011"},{"key":"8_CR79","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/978-3-319-46484-8_21","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Q Ye","year":"2016","unstructured":"Ye, Q., Yuan, S., Kim, T.-K.: Spatial attention deep net with partial PSO for hierarchical hybrid hand pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 346\u2013361. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_21"},{"key":"8_CR80","doi-asserted-by":"crossref","unstructured":"Yuan, S., et al.: Depth-based 3d hand pose estimation: from current achievements to future goals. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2636\u20132645 (2018)","DOI":"10.1109\/CVPR.2018.00279"},{"key":"8_CR81","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1007\/978-3-030-58610-2_3","volume-title":"Computer Vision \u2013 ECCV 2020","author":"JY Zhang","year":"2020","unstructured":"Zhang, J.Y., Pepose, S., Joo, H., Ramanan, D., Malik, J., Kanazawa, A.: Perceiving 3D human-object spatial arrangements from a single image in the wild. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 34\u201351. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_3"},{"key":"8_CR82","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1007\/978-3-030-58601-0_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L Zhang","year":"2020","unstructured":"Zhang, L., Wen, T., Min, J., Wang, J., Han, D., Shi, J.: Learning object placement by inpainting for compositional data augmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 566\u2013581. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_34"},{"key":"8_CR83","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Habermann, M., Xu, W., Habibie, I., Theobalt, C., Xu, F.: Monocular real-time hand shape and motion capture using multi-modal data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5346\u20135355 (2020)","DOI":"10.1109\/CVPR42600.2020.00539"},{"key":"8_CR84","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1007\/978-3-319-16817-3_5","volume-title":"Computer Vision \u2013 ACCV 2014","author":"X Zhu","year":"2015","unstructured":"Zhu, X., Jia, X., Wong, K.-Y.K.: Pixel-level hand detection with shape-aware structured forests. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9006, pp. 64\u201378. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-16817-3_5"},{"key":"8_CR85","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Brox, T.: Learning to estimate 3D hand pose from single RGB images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4903\u20134911 (2017)","DOI":"10.1109\/ICCV.2017.525"}],"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\/978-3-031-19818-2_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T09:18:58Z","timestamp":1728206338000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19818-2_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198175","9783031198182"],"references-count":85,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19818-2_8","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":"22 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)"}}]}}