{"type":"ScholarlyArticle","title":"XFormer: Fast and Accurate Monocular 3D Body Capture","authors":[{"name":"Lihui Qian","slug":"lihui-qian","given":"Lihui","family":"Qian","affiliation":""},{"name":"Xintong Han","slug":"xintong-han","given":"Xintong","family":"Han","affiliation":""},{"name":"Faqiang Wang","slug":"faqiang-wang","given":"Faqiang","family":"Wang","affiliation":""},{"name":"Hongyu Liu","slug":"hongyu-liu","given":"Hongyu","family":"Liu","affiliation":"Hong Kong University of Science and Technology"},{"name":"Haoye Dong","slug":"haoye-dong","given":"Haoye","family":"Dong","affiliation":"Carnegie Mellon University"},{"name":"Zhiwen Li","slug":"zhiwen-li","given":"Zhiwen","family":"Li","affiliation":""},{"name":"Huawei Wei","slug":"huawei-wei","given":"Huawei","family":"Wei","affiliation":"Tencent"},{"name":"Zhe Lin","slug":"zhe-lin","given":"Zhe","family":"Lin","affiliation":""},{"name":"Cheng-Bin Jin","slug":"cheng-bin-jin","given":"Cheng-Bin","family":"Jin","affiliation":""}],"abstract":"We present XFormer, a novel human mesh and motion capture method that achieves real-time performance on consumer CPUs given only monocular images as input. The proposed network architecture contains two branches: a keypoint branch that estimates 3D human mesh vertices given 2D keypoints, and an image branch that makes prediction directly from the RGB image features. At the core of our method is a cross-modal transformer block that allows information flow across these two branches by modeling the attention between 2D keypoint coordinates and image spatial features. Our architecture is smartly designed, which enables us to train on various types of datasets including images with 2D/3D annotations, images with 3D pseudo labels, and motion capture datasets that do not have associated images. This effectively improves the accuracy and generalization ability of our system. Built on a lightweight backbone (MobileNetV3), our method runs blazing fast (over 30fps on a single CPU core) and still yields competitive accuracy. Furthermore, with a HRNet backbone, XFormer delivers state-of-the-art performance on Huamn3.6 and 3DPW datasets.","doi":"10.24963/ijcai.2023/148","url":"https://ijcai.org/proceedings/2023/148","pdf":"https://ijcai.org/proceedings/2023/0148.pdf","markdown":"https://ijcai.org/proceedings/2023/148.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/148","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Computer Vision","track":"Main Track","number":148,"pages":{"first":1331,"last":1339},"keywords":["Computer Vision: CV: 3D computer vision"],"videos":[],"references":[{"position":1,"raw":"[Andriluka et al., 2014] Mykhaylo Andriluka, Leonid Pishchulin, Peter Gehler, and Bernt Schiele. 2D Human Pose Estimation: New Benchmark and State of the Art Analysis. In CVPR, June 2014.","title":"2D Human Pose Estimation: New Benchmark and State of the Art Analysis","authors":"Mykhaylo Andriluka, Leonid Pishchulin, Peter Gehler, Bernt Schiele","year":"2014","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Andriluka et al., 2018] Mykhaylo Andriluka, Umar Iqbal, Eldar Insafutdinov, Leonid Pishchulin, Anton Milan, Juer- gen Gall, and Bernt Schiele. Posetrack: A benchmark for human pose estimation and tracking. In CVPR, 2018.","title":"Posetrack: A benchmark for human pose estimation and tracking","authors":"Mykhaylo Andriluka, Umar Iqbal, Eldar Insafutdinov, Leonid Pishchulin, Anton Milan, Juergen Gall, Bernt Schiele","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bazarevsky et al., 2020] Valentin Bazarevsky, Ivan Gr- ishchenko, Karthik Raveendran, Tyler Zhu, Fan Zhang, and Matthias Grundmann. Blazepose: On-device real-time body pose tracking. arXiv preprint arXiv:2006.10204, 2020.","title":"Blazepose: On-device real-time body pose tracking","authors":"Valentin Bazarevsky, Ivan Grishchenko, Karthik Raveendran, Tyler Zhu, Fan Zhang, Matthias Grundmann","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bogo et al., 2016] Federica Bogo, Angjoo Kanazawa, Christoph Lassner, Peter Gehler, Javier Romero, and Michael J Black. Keep it smpl: Automatic estimation of 3d human pose and shape from a single image. In ECCV, 2016.","title":"Keep it smpl: Automatic estimation of 3d human pose and shape from a single image","authors":"Federica Bogo, Angjoo Kanazawa, Christoph Lassner, Peter Gehler, Javier Romero, Michael J Black","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cao et al., 2019] Zhe Cao, Gines Hidalgo, Tomas Simon, Shih-En Wei, and Yaser Sheikh. Openpose: realtime multi-person 2d pose estimation using part affinity fields. TPAMI, 2019.","title":"Openpose: realtime multi-person 2d pose estimation using part affinity fields","authors":"Zhe Cao, Gines Hidalgo, Tomas Simon, Shih-En Wei, Yaser Sheikh","year":"2019","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Choi et al., 2020] Hongsuk Choi, Gyeongsik Moon, and Kyoung Mu Lee. Pose2mesh: Graph convolutional net- work for 3d human pose and mesh recovery from a 2d hu- man pose. In ECCV, 2020.","title":"Pose2mesh: Graph convolutional network for 3d human pose and mesh recovery from a 2d human pose","authors":"Choi","year":"2020","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. In CVPR, 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hinton et al., 2015] Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531, 2015.","title":"Distilling the knowledge in a neural network","authors":"Geoffrey Hinton, Oriol Vinyals, Jeff Dean","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Howard et al., 2019] Andrew Howard, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang, Yukun Zhu, Ruoming Pang, Vijay Vasudevan, et al. Searching for mobilenetv3. In ICCV, 2019.","title":"Searching for mobilenetv3","authors":"Andrew Howard, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang, Yukun Zhu, Ruoming Pang, Vijay Vasudevan","year":"2019","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Ionescu et al., 2013] Catalin Ionescu, Dragos Papava, Vlad Olaru, and Cristian Sminchisescu. Human3. 6m: Large scale datasets and predictive methods for 3d human sens- ing in natural environments. TPAMI, 2013.","title":"Human3. 6m: Large scale datasets and predictive methods for 3d human sensing in natural environments","authors":"Catalin Ionescu, Dragos Papava, Vlad Olaru, Cristian Sminchisescu","year":"2013","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Johnson and Everingham, 2010] Sam Johnson and Mark Everingham. Clustered pose and nonlinear appearance models for human pose estimation. In BMVC, 2010.","title":"Clustered pose and nonlinear appearance models for human pose estimation","authors":"Johnson, Everingham, Sam Johnson, Mark Everingham","year":"2010","venue":"BMVC","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Johnson and Everingham, 2011] Sam Johnson and Mark Everingham. Learning effective human pose estimation from inaccurate annotation. In CVPR, 2011.","title":"Learning effective human pose estimation from inaccurate annotation","authors":"Johnson, Everingham, Sam Johnson, Mark Everingham","year":"2011","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Joo et al., 2021] Hanbyul Joo, Natalia Neverova, and An- drea Vedaldi. Exemplar fine-tuning for 3d human pose fitting towards in-the-wild 3d human pose estimation. In 3DV, 2021.","title":"Hanbyul Joo, Natalia Neverova, and Andrea Vedaldi. Exemplar fine-tuning for 3d human pose fitting towards in-the-wild 3d human pose estimation","authors":"Joo","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kanazawa et al., 2018] Angjoo Kanazawa, Michael J. Black, David W. Jacobs, and Jitendra Malik. End-to-end recovery of human shape and pose. In CVPR, 2018.","title":"End-to-end recovery of human shape and pose","authors":"Kanazawa","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kanazawa et al., 2019] Angjoo Kanazawa, Jason Y Zhang, Panna Felsen, and Jitendra Malik. Learning 3d human dy- namics from video. In CVPR, 2019.","title":"Learning 3d human dynamics from video","authors":"Kanazawa","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Kocabas et al., 2020] Muhammed Kocabas, Nikos Athana- siou, and Michael J. Black. Vibe: Video inference for hu- man body pose and shape estimation. In CVPR, 2020.","title":"Vibe: Video inference for human body pose and shape estimation","authors":"Muhammed Kocabas, Nikos Athanasiou, Michael J Black","year":"2020","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Kocabas et al., 2021] Muhammed Kocabas, Chun-Hao P Huang, Otmar Hilliges, and Michael J Black. Pare: Part at- tention regressor for 3d human body estimation. In ICCV, 2021.","title":"Pare: Part attention regressor for 3d human body estimation","authors":"Muhammed Kocabas, Chun-Hao P Huang, Otmar Hilliges, Michael J Black","year":"2021","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Kolotouros et al., 2019] Nikos Kolotouros, Georgios Pavlakos, Michael J Black, and Kostas Daniilidis. Learning to reconstruct 3d human pose and shape via model-fitting in the loop. In ICCV, 2019.","title":"Learning to reconstruct 3d human pose and shape via model-fitting in the loop","authors":"Nikos Kolotouros, Georgios Pavlakos, Michael J Black, Kostas Daniilidis","year":"2019","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Kolotouros et al., 2021] Nikos Kolotouros, Georgios Pavlakos, Dinesh Jayaraman, and Kostas Daniilidis. Probabilistic modeling for human mesh recovery. In ICCV, 2021.","title":"Probabilistic modeling for human mesh recovery","authors":"Nikos Kolotouros, Georgios Pavlakos, Dinesh Jayaraman, Kostas Daniilidis","year":"2021","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Lassner et al., 2017] Christoph Lassner, Javier Romero, Martin Kiefel, Federica Bogo, Michael J. Black, and Pe- ter V. Gehler. Unite the people: Closing the loop between 3d and 2d human representations. In CVPR, 2017.","title":"Unite the people: Closing the loop between 3d and 2d human representations","authors":"Christoph Lassner, Javier Romero, Martin Kiefel, Federica Bogo, Michael J Black, Peter V Gehler","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Li et al., 2021] Wenhao Li, Hong Liu, Runwei Ding, Mengyuan Liu, and Pichao Wang. Lifting transformer for 3d human pose estimation in video. arXiv preprint arXiv:2103.14304, 2021.","title":"Lifting transformer for 3d human pose estimation in video","authors":"Wenhao Li, Hong Liu, Runwei Ding, Mengyuan Liu, Pichao Wang","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Li et al., 2022] Wenhao Li, Hong Liu, Hao Tang, Pichao Wang, and Luc Van Gool. Mhformer: Multi-hypothesis transformer for 3d human pose estimation. In CVPR, 2022.","title":"Mhformer: Multi-hypothesis transformer for 3d human pose estimation","authors":"Wenhao Li, Hong Liu, Hao Tang, Pichao Wang, Luc Van Gool","year":"2022","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Lin et al., 2014] Tsung-Yi Lin, Michael Maire, Serge Be- longie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick. Microsoft coco: Com- mon objects in context. In ECCV, 2014.","title":"Microsoft coco: Common objects in context","authors":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, C Lawrence, Zitnick","year":"2014","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Lin et al., 2021a] Kevin Lin, Lijuan Wang, and Zicheng Liu. End-to-end human pose and mesh reconstruction with transformers. In CVPR, 2021.","title":"End-to-end human pose and mesh reconstruction with transformers","authors":"Lin","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Lin et al., 2021b] Kevin Lin, Lijuan Wang, and Zicheng Liu. Mesh graphormer. In ICCV, 2021.","title":"Mesh graphormer","authors":"Lin","year":"2021","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Loper et al., 2015] Matthew Loper, Naureen Mahmood, Javier Romero, Gerard Pons-Moll, and Michael J. Black. SMPL: A skinned multi-person linear model. TOG, 2015.","title":"SMPL: A skinned multi-person linear model","authors":"Matthew Loper, Naureen Mahmood, Javier Romero, Gerard Pons-Moll, Michael J Black","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Lu et al., 2019] Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. Vilbert: Pretraining task-agnostic visiolinguis- tic representations for vision-and-language tasks. arXiv preprint arXiv:1908.02265, 2019.","title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","authors":"Lu","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Mahmood et al., 2019] Naureen Mahmood, Nima Ghor- bani, Nikolaus F Troje, Gerard Pons-Moll, and Michael J Black. Amass: Archive of motion capture as surface shapes. In ICCV, 2019.","title":"Amass: Archive of motion capture as surface shapes","authors":"Naureen Mahmood, Nima Ghorbani, Gerard Nikolaus F Troje, Michael J Pons-Moll, Black","year":"2019","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Martinez et al., 2017] Julieta Martinez, Rayat Hossain, Javier Romero, and James J Little. A simple yet effective baseline for 3d human pose estimation. In ICCV, 2017.","title":"A simple yet effective baseline for 3d human pose estimation","authors":"Julieta Martinez, Rayat Hossain, Javier Romero, James J Little","year":"2017","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Mehta et al., 2017a] Dushyant Mehta, Helge Rhodin, Dan Casas, Pascal Fua, Oleksandr Sotnychenko, Weipeng Xu, and Christian Theobalt. Monocular 3d human pose estima- tion in the wild using improved cnn supervision. In 3DV, 2017.","title":"Monocular 3d human pose estimation in the wild using improved cnn supervision","authors":"Mehta","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Mehta et al., 2017b] Dushyant Mehta, Srinath Sridhar, Oleksandr Sotnychenko, Helge Rhodin, Mohammad Shafiei, Hans-Peter Seidel, Weipeng Xu, Dan Casas, and Christian Theobalt. Vnect: Real-time 3d human pose esti- mation with a single rgb camera. TOG, 2017.","title":"Vnect: Real-time 3d human pose estimation with a single rgb camera","authors":"Mehta","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Mehta et al., 2018] Dushyant Mehta, Oleksandr Sotny- chenko, Franziska Mueller, Weipeng Xu, Srinath Sridhar, Gerard Pons-Moll, and Christian Theobalt. Single-shot multi-person 3d pose estimation from monocular rgb. In 3DV, 2018.","title":"Single-shot multi-person 3d pose estimation from monocular rgb","authors":"Dushyant Mehta, Oleksandr Sotnychenko, Franziska Mueller, Weipeng Xu, Srinath Sridhar, Gerard Pons-Moll, Christian Theobalt","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Mehta et al., 2020] Dushyant Mehta, Oleksandr Sotny- chenko, Franziska Mueller, Weipeng Xu, Mohamed El- gharib, Pascal Fua, Hans-Peter Seidel, Helge Rhodin, Ger- ard Pons-Moll, and Christian Theobalt. Xnect: Real-time multi-person 3d motion capture with a single rgb camera. TOG, 2020.","title":"Xnect: Real-time multi-person 3d motion capture with a single rgb camera","authors":"Dushyant Mehta, Oleksandr Sotnychenko, Franziska Mueller, Weipeng Xu, Mohamed Elgharib, Pascal Fua, Hans-Peter Seidel, Helge Rhodin, Gerard Pons-Moll, Christian Theobalt","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Papandreou et al., 2017] George Papandreou, Tyler Zhu, Nori Kanazawa, Alexander Toshev, Jonathan Tompson, Chris Bregler, and Kevin Murphy. Towards accurate multi- person pose estimation in the wild. In CVPR, 2017.","title":"Towards accurate multiperson pose estimation in the wild","authors":"George Papandreou, Tyler Zhu, Nori Kanazawa, Alexander Toshev, Jonathan Tompson, Chris Bregler, Kevin Murphy","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Pavlakos et al., 2018] Georgios Pavlakos, Xiaowei Zhou, and Kostas Daniilidis. Ordinal depth supervision for 3D human pose estimation. In CVPR, 2018.","title":"Ordinal depth supervision for 3D human pose estimation","authors":"Georgios Pavlakos, Xiaowei Zhou, Kostas Daniilidis","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Rempe et al., 2021] Davis Rempe, Tolga Birdal, Aaron Hertzmann, Jimei Yang, Srinath Sridhar, and Leonidas J Guibas. Humor: 3d human motion model for robust pose estimation. In ICCV, 2021.","title":"Humor: 3d human motion model for robust pose estimation","authors":"Davis Rempe, Tolga Birdal, Aaron Hertzmann, Jimei Yang, Srinath Sridhar, Leonidas J Guibas","year":"2021","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Shan et al., 2022] Wenkang Shan, Zhenhua Liu, Xinfeng Zhang, Shanshe Wang, Siwei Ma, and Wen Gao. P-stmo: Pre-trained spatial temporal many-to-one model for 3d hu- man pose estimation. In ECCV, 2022.","title":"P-stmo: Pre-trained spatial temporal many-to-one model for 3d human pose estimation","authors":"Wenkang Shan, Zhenhua Liu, Xinfeng Zhang, Shanshe Wang, Siwei Ma, Wen Gao","year":"2022","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Sun et al., 2019] Yu Sun, Yun Ye, Wu Liu, Wenpeng Gao, Yili Fu, and Tao Mei. Human mesh recovery from monoc- ular images via a skeleton-disentangled representation. In ICCV, 2019.","title":"Human mesh recovery from monocular images via a skeleton-disentangled representation","authors":"Yu Sun, Yun Ye, Wu Liu, Wenpeng Gao, Yili Fu, Tao Mei","year":"2019","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Sun et al., 2021] Yu Sun, Qian Bao, Wu Liu, Yili Fu, Michael J Black, and Tao Mei. Monocular, one-stage, re- gression of multiple 3d people. In ICCV, 2021.","title":"Monocular, one-stage, regression of multiple 3d people","authors":"Yu Sun, Qian Bao, Wu Liu, Yili Fu, Michael J Black, Tao Mei","year":"2021","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Tekin et al., 2017] Bugra Tekin, Pablo Márquez-Neila, Mathieu Salzmann, and Pascal Fua. Learning to fuse 2d and 3d image cues for monocular body pose estimation. In ICCV, 2017.","title":"Learning to fuse 2d and 3d image cues for monocular body pose estimation","authors":"Pablo Bugra Tekin, Mathieu Márquez-Neila, Pascal Salzmann, Fua","year":"2017","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In Proc. NeurIPS, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, Illia Polosukhin","year":"2017","venue":"Proc. NeurIPS","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[von Marcard et al., 2018] Timo von Marcard, Roberto Hen- schel, Michael J Black, Bodo Rosenhahn, and Gerard Pons-Moll. Recovering accurate 3d human pose in the wild using imus and a moving camera. In ECCV, 2018.","title":"Recovering accurate 3d human pose in the wild using imus and a moving camera","authors":"Von Marcard","year":"2018","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Wang et al., 2018] Ting-Chun Wang, Ming-Yu Liu, Jun- Yan Zhu, Andrew Tao, Jan Kautz, and Bryan Catanzaro. High-resolution image synthesis and semantic manipula- tion with conditional gans. In CVPR, 2018.","title":"High-resolution image synthesis and semantic manipulation with conditional gans","authors":"Ting-Chun, Ming-Yu Wang, Jun-Yan Liu, Andrew Zhu, Jan Tao, Bryan Kautz, Catanzaro","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Zanfir et al., 2021] Mihai Zanfir, Andrei Zanfir, Ed- uard Gabriel Bazavan, William T Freeman, Rahul Sukthankar, and Cristian Sminchisescu. Thundr: Transformer-based 3d human reconstruction with mark- ers. arXiv preprint arXiv:2106.09336, 2021.","title":"Thundr: Transformer-based 3d human reconstruction with markers","authors":"Mihai Zanfir, Andrei Zanfir, Eduard Gabriel Bazavan, Rahul William T Freeman, Cristian Sukthankar, Sminchisescu","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Zhang et al., 2013] Weiyu Zhang, Menglong Zhu, and Kon- stantinos G Derpanis. From actemes to action: A strongly- supervised representation for detailed action understand- ing. In ICCV, 2013.","title":"From actemes to action: A stronglysupervised representation for detailed action understanding","authors":"Weiyu Zhang, Menglong Zhu, Konstantinos G Derpanis","year":"2013","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Zhao et al., 2019] Long Zhao, Xi Peng, Yu Tian, Mubbasir Kapadia, and Dimitris N Metaxas. Semantic graph convo- lutional networks for 3d human pose regression. In CVPR, 2019.","title":"Semantic graph convolutional networks for 3d human pose regression","authors":"Long Zhao, Xi Peng, Yu Tian, Mubbasir Kapadia, Dimitris N Metaxas","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[Zhao et al., 2022] Weixi Zhao, Yunjie Tian, Qixiang Ye, Jianbin Jiao, and Weiqiang Wang. Graformer: Graph con- volution transformer for 3d pose estimation. In CVPR, 2022.","title":"Graformer: Graph convolution transformer for 3d pose estimation","authors":"Zhao","year":"2022","venue":"CVPR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}