{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T04:20:31Z","timestamp":1778127631043,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,11,7]],"date-time":"2022-11-07T00:00:00Z","timestamp":1667779200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["GA863146"],"award-info":[{"award-number":["GA863146"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Engineering Research Board","award":["SRG\/2021\/000768"],"award-info":[{"award-number":["SRG\/2021\/000768"]}]},{"name":"Wellcome \/ EPSRC Centre for Interventional and Surgical Sciences","award":["203145\/Z\/16\/Z"],"award-info":[{"award-number":["203145\/Z\/16\/Z"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,11,7]]},"DOI":"10.1145\/3536221.3556596","type":"proceedings-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T15:54:14Z","timestamp":1667577254000},"page":"83-93","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Generalized Product-of-Experts for Learning Multimodal Representations in Noisy Environments"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6756-1126","authenticated-orcid":false,"given":"Abhinav","family":"Joshi","sequence":"first","affiliation":[{"name":"Computer Science and Engineering, Indian Institute of Technology Kanpur, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9908-4272","authenticated-orcid":false,"given":"Naman","family":"Gupta","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Indian Institute of Technology, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3081-5345","authenticated-orcid":false,"given":"Jinang","family":"Shah","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Kanpur, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7171-6469","authenticated-orcid":false,"given":"Binod","family":"Bhattarai","sequence":"additional","affiliation":[{"name":"University College London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0962-8350","authenticated-orcid":false,"given":"Ashutosh","family":"Modi","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Indian Institute of Technology Kanpur, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0980-3227","authenticated-orcid":false,"given":"Danail","family":"Stoyanov","sequence":"additional","affiliation":[{"name":"University College London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,11,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Noise Flow: Noise Modeling With Conditional Normalizing Flows. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Abdelhamed A.","year":"2019","unstructured":"A. Abdelhamed , Marcus\u00a0 A. Brubaker , and M.\u00a0 S. Brown . 2019 . Noise Flow: Noise Modeling With Conditional Normalizing Flows. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019), 3165\u20133173. A. Abdelhamed, Marcus\u00a0A. Brubaker, and M.\u00a0S. Brown. 2019. Noise Flow: Noise Modeling With Conditional Normalizing Flows. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019), 3165\u20133173."},{"key":"e_1_3_2_1_2_1","unstructured":"Rianne van\u00a0den Berg Leonard Hasenclever Jakub\u00a0M Tomczak and Max Welling. 2018. Sylvester normalizing flows for variational inference. arXiv preprint arXiv:1803.05649(2018).  Rianne van\u00a0den Berg Leonard Hasenclever Jakub\u00a0M Tomczak and Max Welling. 2018. Sylvester normalizing flows for variational inference. arXiv preprint arXiv:1803.05649(2018)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_41"},{"key":"e_1_3_2_1_4_1","unstructured":"Yanshuai Cao and David\u00a0J. Fleet. 2014. Generalized Product of Experts for Automatic and Principled Fusion of Gaussian Process Predictions. CoRR abs\/1410.7827(2014). arXiv:1410.7827http:\/\/arxiv.org\/abs\/1410.7827  Yanshuai Cao and David\u00a0J. Fleet. 2014. Generalized Product of Experts for Automatic and Principled Fusion of Gaussian Process Predictions. CoRR abs\/1410.7827(2014). arXiv:1410.7827http:\/\/arxiv.org\/abs\/1410.7827"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_21"},{"key":"e_1_3_2_1_6_1","volume-title":"Robust Multimodal Brain Tumor Segmentation via Feature Disentanglement and Gated Fusion. CoRR","author":"Chen Cheng","year":"2020","unstructured":"Cheng Chen , Qi Dou , Yueming Jin , Hao Chen , Jing Qin , and Pheng-Ann Heng . 2020. Robust Multimodal Brain Tumor Segmentation via Feature Disentanglement and Gated Fusion. CoRR ( 2020 ). arXiv:2002.09708https:\/\/arxiv.org\/abs\/2002.09708 Cheng Chen, Qi Dou, Yueming Jin, Hao Chen, Jing Qin, and Pheng-Ann Heng. 2020. Robust Multimodal Brain Tumor Segmentation via Feature Disentanglement and Gated Fusion. CoRR (2020). arXiv:2002.09708https:\/\/arxiv.org\/abs\/2002.09708"},{"key":"e_1_3_2_1_7_1","volume-title":"Image Blind Denoising with Generative Adversarial Network Based Noise Modeling. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chen Jingwen","year":"2018","unstructured":"Jingwen Chen , Jiawei Chen , Hongyang Chao , and Ming Yang . 2018 . Image Blind Denoising with Generative Adversarial Network Based Noise Modeling. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2018), 3155\u20133164. Jingwen Chen, Jiawei Chen, Hongyang Chao, and Ming Yang. 2018. Image Blind Denoising with Generative Adversarial Network Based Noise Modeling. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2018), 3155\u20133164."},{"key":"e_1_3_2_1_8_1","volume-title":"Blender - a 3D modelling and rendering package","author":"Community Blender\u00a0Online","unstructured":"Blender\u00a0Online Community . 2018. Blender - a 3D modelling and rendering package . Blender Foundation, Stichting Blender Foundation, Amsterdam . http:\/\/www.blender.org Blender\u00a0Online Community. 2018. Blender - a 3D modelling and rendering package. Blender Foundation, Stichting Blender Foundation, Amsterdam. http:\/\/www.blender.org"},{"key":"#cr-split#-e_1_3_2_1_9_1.1","doi-asserted-by":"crossref","unstructured":"Imant Daunhawer Thomas\u00a0M. Sutter Ricards Marcinkevics and Julia\u00a0E. Vogt. 2020. Self-supervised Disentanglement of Modality-Specific and Shared Factors Improves Multimodal Generative Models. In GCPR. 459-473. https:\/\/doi.org\/10.1007\/978-3-030-71278-5_33 10.1007\/978-3-030-71278-5_33","DOI":"10.1007\/978-3-030-71278-5_33"},{"key":"#cr-split#-e_1_3_2_1_9_1.2","doi-asserted-by":"crossref","unstructured":"Imant Daunhawer Thomas\u00a0M. Sutter Ricards Marcinkevics and Julia\u00a0E. Vogt. 2020. Self-supervised Disentanglement of Modality-Specific and Shared Factors Improves Multimodal Generative Models. In GCPR. 459-473. https:\/\/doi.org\/10.1007\/978-3-030-71278-5_33","DOI":"10.1007\/978-3-030-71278-5_33"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00878"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC46164.2021.9630806"},{"key":"e_1_3_2_1_12_1","volume-title":"Ffjord: Free-form continuous dynamics for scalable reversible generative models. arXiv preprint arXiv:1810.01367(2018).","author":"Grathwohl Will","year":"2018","unstructured":"Will Grathwohl , Ricky\u00a0 TQ Chen , Jesse Bettencourt , Ilya Sutskever , and David Duvenaud . 2018 . Ffjord: Free-form continuous dynamics for scalable reversible generative models. arXiv preprint arXiv:1810.01367(2018). Will Grathwohl, Ricky\u00a0TQ Chen, Jesse Bettencourt, Ilya Sutskever, and David Duvenaud. 2018. Ffjord: Free-form continuous dynamics for scalable reversible generative models. arXiv preprint arXiv:1810.01367(2018)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_14_1","unstructured":"Irina Higgins Lo\u00efc Matthey Arka Pal Christopher\u00a0P. Burgess Xavier Glorot Matthew\u00a0M. Botvinick Shakir Mohamed and Alexander Lerchner. 2017. beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework. In ICLR.  Irina Higgins Lo\u00efc Matthey Arka Pal Christopher\u00a0P. Burgess Xavier Glorot Matthew\u00a0M. Botvinick Shakir Mohamed and Alexander Lerchner. 2017. beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework. In ICLR."},{"key":"e_1_3_2_1_15_1","unstructured":"Xun Huang Arun Mallya Ting-Chun Wang and Ming-Yu Liu. 2021. Multimodal Conditional Image Synthesis with Product-of-Experts GANs. arXiv preprint arXiv:2112.05130(2021).  Xun Huang Arun Mallya Ting-Chun Wang and Ming-Yu Liu. 2021. Multimodal Conditional Image Synthesis with Product-of-Experts GANs. arXiv preprint arXiv:2112.05130(2021)."},{"key":"e_1_3_2_1_16_1","volume-title":"GRDN:Grouped Residual Dense Network for Real Image Denoising and GAN-Based Real-World Noise Modeling. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2019)","author":"Kim Dong-Wook","year":"2019","unstructured":"Dong-Wook Kim , Jae\u2010Ryun Chung , and Seung-Won Jung . 2019 . GRDN:Grouped Residual Dense Network for Real Image Denoising and GAN-Based Real-World Noise Modeling. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2019) , 2086\u20132094. Dong-Wook Kim, Jae\u2010Ryun Chung, and Seung-Won Jung. 2019. GRDN:Grouped Residual Dense Network for Real Image Denoising and GAN-Based Real-World Noise Modeling. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2019), 2086\u20132094."},{"key":"e_1_3_2_1_17_1","unstructured":"Durk\u00a0P Kingma Shakir Mohamed Danilo Jimenez\u00a0Rezende and Max Welling. 2014. Semi-supervised Learning with Deep Generative Models. In Advances in Neural Information Processing Systems Vol.\u00a027.  Durk\u00a0P Kingma Shakir Mohamed Danilo Jimenez\u00a0Rezende and Max Welling. 2014. Semi-supervised Learning with Deep Generative Models. In Advances in Neural Information Processing Systems Vol.\u00a027."},{"key":"e_1_3_2_1_18_1","unstructured":"Diederik\u00a0P. Kingma Tim Salimans Rafal J\u00f3zefowicz Xi Chen Ilya Sutskever and Max Welling. 2016. Improving Variational Autoencoders with Inverse Autoregressive Flow. In NIPS. 4736\u20134744. http:\/\/papers.nips.cc\/paper\/6581-improving-variational-autoencoders-with-inverse-autoregressive-flow  Diederik\u00a0P. Kingma Tim Salimans Rafal J\u00f3zefowicz Xi Chen Ilya Sutskever and Max Welling. 2016. Improving Variational Autoencoders with Inverse Autoregressive Flow. In NIPS. 4736\u20134744. http:\/\/papers.nips.cc\/paper\/6581-improving-variational-autoencoders-with-inverse-autoregressive-flow"},{"key":"e_1_3_2_1_19_1","unstructured":"Diederik\u00a0P Kingma and Max Welling. 2014. Auto-Encoding Variational Bayes. arxiv:1312.6114\u00a0[stat.ML]  Diederik\u00a0P Kingma and Max Welling. 2014. Auto-Encoding Variational Bayes. arxiv:1312.6114\u00a0[stat.ML]"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00185"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01220"},{"key":"e_1_3_2_1_22_1","volume-title":"Person Recognition with HGR Maximal Correlation on Multimodal Data. In 2020 25th International Conference on Pattern Recognition (ICPR). IEEE Computer Society, 1\u20138. https:\/\/doi.org\/10","author":"Liang Y.","year":"2021","unstructured":"Y. Liang , F. Ma , Y. Li , and S. Huang . 2021 . Person Recognition with HGR Maximal Correlation on Multimodal Data. In 2020 25th International Conference on Pattern Recognition (ICPR). IEEE Computer Society, 1\u20138. https:\/\/doi.org\/10 .1109\/ICPR48806. 2021 .9413164 10.1109\/ICPR48806.2021.9413164 Y. Liang, F. Ma, Y. Li, and S. Huang. 2021. Person Recognition with HGR Maximal Correlation on Multimodal Data. In 2020 25th International Conference on Pattern Recognition (ICPR). IEEE Computer Society, 1\u20138. https:\/\/doi.org\/10.1109\/ICPR48806.2021.9413164"},{"key":"e_1_3_2_1_23_1","unstructured":"Navonil Majumder Soujanya Poria Gangeshwar Krishnamurthy Niyati Chhaya Rada Mihalcea and Alexander Gelbukh. 2019. Variational fusion for multimodal sentiment analysis. arXiv preprint arXiv:1908.06008(2019).  Navonil Majumder Soujanya Poria Gangeshwar Krishnamurthy Niyati Chhaya Rada Mihalcea and Alexander Gelbukh. 2019. Variational fusion for multimodal sentiment analysis. arXiv preprint arXiv:1908.06008(2019)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Ioannis Marras Grigorios\u00a0G. Chrysos Ioannis Alexiou Gregory\u00a0G. Slabaugh and Stefanos Zafeiriou. 2020. Reconstructing the Noise Variance Manifold for Image Denoising. In ECCV.  Ioannis Marras Grigorios\u00a0G. Chrysos Ioannis Alexiou Gregory\u00a0G. Slabaugh and Stefanos Zafeiriou. 2020. Reconstructing the Noise Variance Manifold for Image Denoising. In ECCV.","DOI":"10.1007\/978-3-030-58545-7_36"},{"key":"e_1_3_2_1_25_1","volume-title":"V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map. CoRR","author":"Moon Gyeongsik","year":"2017","unstructured":"Gyeongsik Moon , Ju\u00a0Yong Chang , and Kyoung\u00a0Mu Lee . 2017. V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map. CoRR ( 2017 ). arXiv:1711.07399 Gyeongsik Moon, Ju\u00a0Yong Chang, and Kyoung\u00a0Mu Lee. 2017. V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map. CoRR (2017). arXiv:1711.07399"},{"key":"e_1_3_2_1_26_1","volume-title":"Hands Deep in Deep Learning for Hand Pose Estimation. CoRR","author":"Oberweger Markus","year":"2015","unstructured":"Markus Oberweger , Paul Wohlhart , and Vincent Lepetit . 2015. Hands Deep in Deep Learning for Hand Pose Estimation. CoRR ( 2015 ). arXiv:1502.06807http:\/\/arxiv.org\/abs\/1502.06807 Markus Oberweger, Paul Wohlhart, and Vincent Lepetit. 2015. Hands Deep in Deep Learning for Hand Pose Estimation. CoRR (2015). arXiv:1502.06807http:\/\/arxiv.org\/abs\/1502.06807"},{"key":"e_1_3_2_1_27_1","unstructured":"Alec Radford Luke Metz and Soumith Chintala. 2016. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. arxiv:1511.06434\u00a0[cs.LG]  Alec Radford Luke Metz and Soumith Chintala. 2016. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. arxiv:1511.06434\u00a0[cs.LG]"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 32nd International Conference on International Conference on Machine Learning -","volume":"37","author":"Rezende Danilo\u00a0Jimenez","year":"2015","unstructured":"Danilo\u00a0Jimenez Rezende and Shakir Mohamed . 2015 . Variational Inference with Normalizing Flows . In Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37 (Lille, France) (ICML\u201915). JMLR.org, 1530\u20131538. Danilo\u00a0Jimenez Rezende and Shakir Mohamed. 2015. Variational Inference with Normalizing Flows. In Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37 (Lille, France) (ICML\u201915). JMLR.org, 1530\u20131538."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00333"},{"key":"e_1_3_2_1_30_1","unstructured":"Yuge Shi Brooks Paige Philip\u00a0HS Torr and N Siddharth. 2020. Relating by contrasting: A data-efficient framework for multimodal generative models. arXiv preprint arXiv:2007.01179(2020).  Yuge Shi Brooks Paige Philip\u00a0HS Torr and N Siddharth. 2020. Relating by contrasting: A data-efficient framework for multimodal generative models. arXiv preprint arXiv:2007.01179(2020)."},{"key":"e_1_3_2_1_31_1","volume-title":"\u00a0S. Torr","author":"Shi Yuge","year":"2019","unstructured":"Yuge Shi , N. Siddharth , Brooks Paige , and Philip H . \u00a0S. Torr . 2019 . Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models . arxiv:1911.03393\u00a0[stat.ML] Yuge Shi, N. Siddharth, Brooks Paige, and Philip H.\u00a0S. Torr. 2019. Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models. arxiv:1911.03393\u00a0[stat.ML]"},{"key":"e_1_3_2_1_32_1","unstructured":"L. Soler A. Hosteller V. Agnus A. Charnoz I. Fasquel I. Moreau A. Osswald M. Bouhadjar and I. Marescaux. 2010. 3D image reconstruction for comparison of algorithm database: A patient specific anatomical and medical image database.https:\/\/www.ircad.fr\/research\/data-sets\/liver-segmentation-3d-ircadb-01\/  L. Soler A. Hosteller V. Agnus A. Charnoz I. Fasquel I. Moreau A. Osswald M. Bouhadjar and I. Marescaux. 2010. 3D image reconstruction for comparison of algorithm database: A patient specific anatomical and medical image database.https:\/\/www.ircad.fr\/research\/data-sets\/liver-segmentation-3d-ircadb-01\/"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Adrian Spurr Jie Song Seonwook Park and Otmar Hilliges. 2018. Cross-modal Deep Variational Hand Pose Estimation. arxiv:1803.11404\u00a0[cs.CV]  Adrian Spurr Jie Song Seonwook Park and Otmar Hilliges. 2018. Cross-modal Deep Variational Hand Pose Estimation. arxiv:1803.11404\u00a0[cs.CV]","DOI":"10.1109\/CVPR.2018.00017"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102187"},{"key":"e_1_3_2_1_35_1","volume-title":"Generalized Multimodal ELBO. In International Conference on Learning Representations.","author":"Sutter M","year":"2020","unstructured":"Thomas\u00a0 M Sutter , Imant Daunhawer , and Julia\u00a0 E Vogt . 2020 . Generalized Multimodal ELBO. In International Conference on Learning Representations. Thomas\u00a0M Sutter, Imant Daunhawer, and Julia\u00a0E Vogt. 2020. Generalized Multimodal ELBO. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_36_1","unstructured":"Masahiro Suzuki Kotaro Nakayama and Yutaka Matsuo. 2016. Joint Multimodal Learning with Deep Generative Models. arXiv preprint arXiv:1611.01891(2016).  Masahiro Suzuki Kotaro Nakayama and Yutaka Matsuo. 2016. Joint Multimodal Learning with Deep Generative Models. arXiv preprint arXiv:1611.01891(2016)."},{"key":"e_1_3_2_1_37_1","unstructured":"Mike Wu and Noah Goodman. 2018. Multimodal Generative Models for Scalable Weakly-Supervised Learning. arxiv:1802.05335\u00a0[cs.LG]  Mike Wu and Noah Goodman. 2018. Multimodal Generative Models for Scalable Weakly-Supervised Learning. arxiv:1802.05335\u00a0[cs.LG]"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00242"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Linlin Yang and Angela Yao. 2019. Disentangling Latent Hands for Image Synthesis and Pose Estimation. arxiv:1812.01002\u00a0[cs.CV]  Linlin Yang and Angela Yao. 2019. Disentangling Latent Hands for Image Synthesis and Pose Estimation. arxiv:1812.01002\u00a0[cs.CV]","DOI":"10.1109\/CVPR.2019.01011"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Yaoqing Yang Chen Feng Yiru Shen and Dong Tian. 2018. FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation. arxiv:1712.07262\u00a0[cs.CV]  Yaoqing Yang Chen Feng Yiru Shen and Dong Tian. 2018. FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation. arxiv:1712.07262\u00a0[cs.CV]","DOI":"10.1109\/CVPR.2018.00029"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_3"},{"key":"#cr-split#-e_1_3_2_1_42_1.1","doi-asserted-by":"crossref","unstructured":"Tongxue Zhou Su Ruan and St\u00e9phane Canu. 2019. A review: Deep learning for medical image segmentation using multi-modality fusion. Array 3-4(2019) 100004. https:\/\/doi.org\/10.1016\/j.array.2019.100004 10.1016\/j.array.2019.100004","DOI":"10.1016\/j.array.2019.100004"},{"key":"#cr-split#-e_1_3_2_1_42_1.2","doi-asserted-by":"crossref","unstructured":"Tongxue Zhou Su Ruan and St\u00e9phane Canu. 2019. A review: Deep learning for medical image segmentation using multi-modality fusion. Array 3-4(2019) 100004. https:\/\/doi.org\/10.1016\/j.array.2019.100004","DOI":"10.1016\/j.array.2019.100004"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Christian Zimmermann and Thomas Brox. 2017. Learning to Estimate 3D Hand Pose from Single RGB Images. arxiv:1705.01389\u00a0[cs.CV]  Christian Zimmermann and Thomas Brox. 2017. Learning to Estimate 3D Hand Pose from Single RGB Images. arxiv:1705.01389\u00a0[cs.CV]","DOI":"10.1109\/ICCV.2017.525"}],"event":{"name":"ICMI '22: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","location":"Bengaluru India","acronym":"ICMI '22","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2022 International Conference on Multimodal Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3536221.3556596","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3536221.3556596","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:48:53Z","timestamp":1750182533000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3536221.3556596"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,7]]},"references-count":45,"alternative-id":["10.1145\/3536221.3556596","10.1145\/3536221"],"URL":"https:\/\/doi.org\/10.1145\/3536221.3556596","relation":{},"subject":[],"published":{"date-parts":[[2022,11,7]]},"assertion":[{"value":"2022-11-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}