{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:03:20Z","timestamp":1777655000255,"version":"3.51.4"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726637","type":"print"},{"value":"9783031726644","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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\/978-3-031-72664-4_2","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T17:02:04Z","timestamp":1729875724000},"page":"19-37","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Pose-Aware Self-supervised Learning with\u00a0Viewpoint Trajectory Regularization"],"prefix":"10.1007","author":[{"given":"Jiayun","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yubei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stella X.","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"2_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Alexa, M.: Super-fibonacci spirals: fast, low-discrepancy sampling of SO(3). In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8291\u20138300 (2022)","DOI":"10.1109\/CVPR52688.2022.00811"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Bai, Y., et al.: Sequential modeling enables scalable learning for large vision models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22861\u201322872 (2024)","DOI":"10.1109\/CVPR52733.2024.02157"},{"key":"2_CR4","unstructured":"Bardes, A., Ponce, J., LeCun, Y.: VICReg: variance-invariance-covariance regularization for self-supervised learning. arXiv preprint arXiv:2105.04906 (2021)"},{"key":"2_CR5","unstructured":"Bardes, A., Ponce, J., LeCun, Y.: VICRegL: self-supervised learning of local visual features. In: Advances in Neural Information Processing Systems, vol. 35, pp. 8799\u20138810 (2022)"},{"key":"2_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/978-3-030-01264-9_9","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Caron","year":"2018","unstructured":"Caron, M., Bojanowski, P., Joulin, A., Douze, M.: Deep clustering for unsupervised learning of visual features. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 139\u2013156. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_9"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"2_CR8","unstructured":"Chang, A.X., et\u00a0al.: ShapeNet: an information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Chen, B., Chin, T.J., Klimavicius, M.: Occlusion-robust object pose estimation with holistic representation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2929\u20132939 (2022)","DOI":"10.1109\/WACV51458.2022.00228"},{"key":"2_CR10","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"2_CR11","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple Siamese representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, S., He, K.: An empirical study of training self-supervised vision transformers. arXiv preprint arXiv:2104.02057 (2021)","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"2_CR14","unstructured":"Chen, Y., Bardes, A., Li, Z., LeCun, Y.: Bag of image patch embedding behind the success of self-supervised learning. arXiv preprint arXiv:2206.08954 (2022)"},{"key":"2_CR15","unstructured":"Chen, Y., Paiton, D., Olshausen, B.: The sparse manifold transform. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"issue":"1","key":"2_CR16","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1017\/S1351324916000334","volume":"23","author":"KW Church","year":"2017","unstructured":"Church, K.W.: Word2vec. Nat. Lang. Eng. 23(1), 155\u2013162 (2017)","journal-title":"Nat. Lang. Eng."},{"key":"2_CR17","unstructured":"Dangovski, R., et al.: Equivariant contrastive learning. arXiv preprint arXiv:2111.00899 (2021)"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3d objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13142\u201313153 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"2_CR19","unstructured":"Devillers, A., Lefort, M.: EquiMod: an equivariance module to improve self-supervised learning. arXiv preprint arXiv:2211.01244 (2022)"},{"issue":"3","key":"2_CR20","doi-asserted-by":"publisher","first-page":"1677","DOI":"10.1007\/s10462-020-09888-5","volume":"54","author":"G Du","year":"2021","unstructured":"Du, G., Wang, K., Lian, S., Zhao, K.: Vision-based robotic grasping from object localization, object pose estimation to grasp estimation for parallel grippers: a review. Artif. Intell. Rev. 54(3), 1677\u20131734 (2021)","journal-title":"Artif. Intell. Rev."},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"El\u00a0Banani, M., et al.: Probing the 3D awareness of visual foundation models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21795\u201321806 (2024)","DOI":"10.1109\/CVPR52733.2024.02059"},{"key":"2_CR22","unstructured":"Ermolov, A., Siarohin, A., Sangineto, E., Sebe, N.: Whitening for self-supervised representation learning. In: International Conference on Machine Learning, pp. 3015\u20133024. PMLR (2021)"},{"key":"2_CR23","unstructured":"Falorsi, L., et al.: Explorations in homeomorphic variational auto-encoding. arXiv preprint arXiv:1807.04689 (2018)"},{"issue":"2","key":"2_CR24","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1162\/neco.1991.3.2.194","volume":"3","author":"P F\u00f6ldi\u00e1k","year":"1991","unstructured":"F\u00f6ldi\u00e1k, P.: Learning invariance from transformation sequences. Neural Comput. 3(2), 194\u2013200 (1991)","journal-title":"Neural Comput."},{"key":"2_CR25","unstructured":"Garrido, Q., Najman, L., Lecun, Y.: Self-supervised learning of split invariant equivariant representations. arXiv preprint arXiv:2302.10283 (2023)"},{"key":"2_CR26","unstructured":"Goroshin, R., Mathieu, M.F., LeCun, Y.: Learning to linearize under uncertainty. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"2_CR27","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":"2_CR28","unstructured":"Grill, J.B., et al.: Bootstrap your own latent-a new approach to self-supervised learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 21271\u201321284 (2020)"},{"key":"2_CR29","unstructured":"Hardin, D.P., Michaels, T., Saff, E.B.: A comparison of popular point configurations on S2. arXiv preprint arXiv:1607.04590 (2016)"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2_CR31","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":"2_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1007\/978-3-642-21735-7_6","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2011","author":"GE Hinton","year":"2011","unstructured":"Hinton, G.E., Krizhevsky, A., Wang, S.D.: Transforming auto-encoders. In: Honkela, T., Duch, W., Girolami, M., Kaski, S. (eds.) ICANN 2011. LNCS, vol. 6791, pp. 44\u201351. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-21735-7_6"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Iwase, S., Liu, X., Khirodkar, R., Yokota, R., Kitani, K.M.: RePOSE: fast 6D object pose refinement via deep texture rendering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3303\u20133312 (2021)","DOI":"10.1109\/ICCV48922.2021.00329"},{"issue":"3","key":"2_CR34","doi-asserted-by":"publisher","first-page":"1864","DOI":"10.1109\/LRA.2018.2795645","volume":"3","author":"D Kappler","year":"2018","unstructured":"Kappler, D., et al.: Real-time perception meets reactive motion generation. IEEE Rob. Autom. Lett. 3(3), 1864\u20131871 (2018)","journal-title":"IEEE Rob. Autom. Lett."},{"key":"2_CR35","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: Proceedings of the IEEE International Conference on Computer Vision, pp. 1521\u20131529 (2017)","DOI":"10.1109\/ICCV.2017.169"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Kendall, A., Grimes, M., Cipolla, R.: PoseNet: a convolutional network for real-time 6-DOF camera relocalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2938\u20132946 (2015)","DOI":"10.1109\/ICCV.2015.336"},{"key":"2_CR37","unstructured":"Lee, H., Lee, K., Lee, K., Lee, H., Shin, J.: Improving transferability of representations via augmentation-aware self-supervision. In: Advances in Neural Information Processing Systems, vol. 34, pp. 17710\u201317722 (2021)"},{"key":"2_CR38","unstructured":"Li, J., et\u00a0al.: DataComp-LM: in search of the next generation of training sets for language models. arXiv preprint arXiv:2406.11794 (2024)"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Lin, A., Zhang, J.Y., Ramanan, D., Tulsiani, S.: RelPose++: recovering 6D poses from sparse-view observations. arXiv preprint arXiv:2305.04926 (2023)","DOI":"10.1109\/3DV62453.2024.00126"},{"key":"2_CR40","unstructured":"Macklin, M.: Warp: a high-performance python framework for GPU simulation and graphics. In: NVIDIA GPU Technology Conference (GTC) (2022)"},{"key":"2_CR41","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"2_CR42","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Pantazis, O., Brostow, G.J., Jones, K.E., Mac\u00a0Aodha, O.: Focus on the positives: self-supervised learning for biodiversity monitoring. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10583\u201310592 (2021)","DOI":"10.1109\/ICCV48922.2021.01041"},{"key":"2_CR44","unstructured":"Park, J.Y., Biza, O., Zhao, L., van\u00a0de Meent, J.W., Walters, R.: Learning symmetric embeddings for equivariant world models. arXiv preprint arXiv:2204.11371 (2022)"},{"key":"2_CR45","unstructured":"Ravi, N., et al.: Accelerating 3D deep learning with PyTorch3D. arXiv:2007.08501 (2020)"},{"key":"2_CR46","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 25278\u201325294 (2022)"},{"key":"2_CR47","unstructured":"Sergeant-Perthuis, G., Ruet, N., Rudrauf, D., Ognibene, D., Tisserand, Y.: Influence of the geometry of the world model on curiosity based exploration. arXiv preprint arXiv:2304.00188 (2023)"},{"key":"2_CR48","unstructured":"Shakerinava, M., Mondal, A.K., Ravanbakhsh, S.: Structuring representations using group invariants. In: Advances in Neural Information Processing Systems, vol. 35, pp. 34162\u201334174 (2022)"},{"key":"2_CR49","unstructured":"Shaler, B., McDonald, D., McDonald, M., McDonald, M., Cukierski, P., Cukierski, W.: Carvana image masking challenge. https:\/\/kaggle.com\/competitions\/carvana-image-masking-challenge (2017)"},{"key":"2_CR50","doi-asserted-by":"crossref","unstructured":"Shoemake, K.: Animating rotation with quaternion curves. In: Proceedings of the 12th Annual Conference on Computer Graphics and Interactive Techniques, pp. 245\u2013254 (1985)","DOI":"10.1145\/325334.325242"},{"key":"2_CR51","unstructured":"Sun, W., et al.: Canonical capsules: self-supervised capsules in canonical pose. In: Advances in Neural Information Processing Systems, vol. 34, pp. 24993\u201325005 (2021)"},{"key":"2_CR52","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/978-3-031-25063-7_17","volume-title":"ECCV 2022","author":"J Wang","year":"2022","unstructured":"Wang, J., Jeon, S., Yu, S.X., Zhang, X., Arora, H., Lou, Y.: Unsupervised scene sketch to photo synthesis. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) ECCV 2022. LNCS, vol. 13802, pp. 273\u2013289. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-25063-7_17"},{"key":"2_CR53","unstructured":"Winter, R., Bertolini, M., Le, T., No\u00e9, F., Clevert, D.A.: Unsupervised learning of group invariant and equivariant representations. In: Advances in Neural Information Processing Systems, vol. 35, pp. 31942\u201331956 (2022)"},{"issue":"4","key":"2_CR54","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1162\/089976602317318938","volume":"14","author":"L Wiskott","year":"2002","unstructured":"Wiskott, L., Sejnowski, T.J.: Slow feature analysis: unsupervised learning of invariances. Neural Comput. 14(4), 715\u2013770 (2002)","journal-title":"Neural Comput."},{"key":"2_CR55","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3733\u20133742 (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"2_CR56","unstructured":"You, Y., Gitman, I., Ginsburg, B.: Large batch training of convolutional networks. arXiv preprint arXiv:1708.03888 (2017)"},{"key":"2_CR57","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"592","DOI":"10.1007\/978-3-031-19821-2_34","volume-title":"ECCV 2022","author":"JY Zhang","year":"2022","unstructured":"Zhang, J.Y., Ramanan, D., Tulsiani, S.: RelPose: predicting probabilistic relative rotation for single objects in the wild. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13691, pp. 592\u2013611. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19821-2_34"},{"key":"2_CR58","unstructured":"Zimmermann, R.S., Sharma, Y., Schneider, S., Bethge, M., Brendel, W.: Contrastive learning inverts the data generating process. In: International Conference on Machine Learning, pp. 12979\u201312990. PMLR (2021)"}],"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\/978-3-031-72664-4_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T17:02:31Z","timestamp":1729875751000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72664-4_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031726637","9783031726644"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72664-4_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 October 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"}}]}}