{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T11:13:14Z","timestamp":1768734794003,"version":"3.49.0"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Carl-Zeiss Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3338079","type":"journal-article","created":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T18:24:49Z","timestamp":1701800689000},"page":"8432-8441","source":"Crossref","is-referenced-by-count":4,"title":["Self-Supervised Generative-Contrastive Learning of Multi-Modal Euclidean Input for 3D Shape Latent Representations: A Dynamic Switching Approach"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2186-3748","authenticated-orcid":false,"given":"Chengzhi","family":"Wu","sequence":"first","affiliation":[{"name":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4204-6758","authenticated-orcid":false,"given":"Julius","family":"Pfrommer","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB, Karlsruhe, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3395-162X","authenticated-orcid":false,"given":"Mingyuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3556-7181","authenticated-orcid":false,"given":"J\u00fcrgen","family":"Beyerer","sequence":"additional","affiliation":[{"name":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00967"},{"key":"ref2","article-title":"Generative and discriminative voxel modeling with convolutional neural networks","author":"Brock","year":"2016"},{"key":"ref3","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. 34th Conf. Neural Inf. Process. Syst.","author":"Caron","year":"2020"},{"key":"ref4","article-title":"Shapenet: An Information-rich 3D model repository","author":"Chang","year":"2015"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1111\/1467-8659.00669"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref7","article-title":"Isolating sources of disentanglement in variational autoencoders","volume":"31","author":"Chen","year":"2018","journal-title":"Neural Inf. Process. Syst."},{"key":"ref8","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_38"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00537"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00150"},{"key":"ref15","article-title":"Unsupervised representation learning by predicting image rotations","author":"Gidaris","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_29"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Goodfellow","year":"2015","journal-title":"Nature"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00649"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00038"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2904460"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","article-title":"Fusionnet: 3D object classification using multiple data representations","author":"Hegde","year":"2016"},{"key":"ref24","article-title":"beta-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Higgins","year":"2016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"ref27","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2014"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"key":"ref29","first-page":"1","article-title":"Probabilistic reconstruction networks for 3D shape inference from a single image","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Klokov","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.202"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"ref32","article-title":"Learning from 2D: Pixel-to-point knowledge transfer for 3D pretraining","author":"Liu","year":"2021"},{"key":"ref33","first-page":"2579","article-title":"Visualizing data using T-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353481"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00391"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.609"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/3dv62453.2024.00113"},{"key":"ref39","first-page":"5003","article-title":"Unsupervised learning of 3D structure from images","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Rezende","year":"2016"},{"key":"ref40","article-title":"An overview of gradient descent optimization algorithms","author":"Ruder","year":"2016"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_20"},{"issue":"4","key":"ref42","article-title":"Laplacian mesh processing","volume":"4","author":"Sorkine","year":"2005","journal-title":"Eurographics (State Art Rep.)"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2009.01515.x"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00306"},{"key":"ref46","article-title":"Can we solve 3D vision tasks starting from a 2D vision transformer?","author":"Wang","year":"2022"},{"key":"ref47","first-page":"82","article-title":"Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Wu","year":"2016"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00278"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01347-6"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298732"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref53","first-page":"1704","article-title":"Perspective transformer nets: Learning single-view 3 d object reconstruction without 3D supervision","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Yan","year":"2016"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.376"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/SPAC.2014.6982699"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00148"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10345609.pdf?arnumber=10345609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:32:40Z","timestamp":1722573160000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10345609\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3338079","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}