{"type":"ScholarlyArticle","title":"HDFormer: High-order Directed Transformer for 3D Human Pose Estimation","authors":[{"name":"Hanyuan Chen","slug":"hanyuan-chen","given":"Hanyuan","family":"Chen","affiliation":"DAMO Academy , Alibaba Group"},{"name":"Jun-Yan He","slug":"jun-yan-he","given":"Jun-Yan","family":"He","affiliation":"DAMO Academy , Alibaba Group"},{"name":"Wangmeng Xiang","slug":"wangmeng-xiang","given":"Wangmeng","family":"Xiang","affiliation":"DAMO Academy , Alibaba Group"},{"name":"Zhi-Qi Cheng","slug":"zhi-qi-cheng","given":"Zhi-Qi","family":"Cheng","affiliation":"Carnegie Mellon University , Pittsburgh , PA , USA"},{"name":"Wei Liu","slug":"wei-liu","given":"Wei","family":"Liu","affiliation":"DAMO Academy , Alibaba Group"},{"name":"Hanbing Liu","slug":"hanbing-liu","given":"Hanbing","family":"Liu","affiliation":"Tsinghua University , Beijing , China"},{"name":"Bin Luo","slug":"bin-luo","given":"Bin","family":"Luo","affiliation":"DAMO Academy , Alibaba Group"},{"name":"Yifeng Geng","slug":"yifeng-geng","given":"Yifeng","family":"Geng","affiliation":"DAMO Academy , Alibaba Group"},{"name":"Xuansong Xie","slug":"xuansong-xie","given":"Xuansong","family":"Xie","affiliation":"DAMO Academy , Alibaba Group"}],"abstract":"Human pose estimation is a challenging task due to its structured data sequence nature. Existing methods primarily focus on pair-wise interaction of body joints, which is insufficient for scenarios involving overlapping joints and rapidly changing poses. To overcome these issues, we introduce a novel approach, the High-order Directed Transformer (HDFormer), which leverages high-order bone and joint relationships for improved pose estimation. Specifically, HDFormer incorporates both self-attention and high-order attention to formulate a multi-order attention module. This module facilitates first-order \"joint-joint\", second-order \"bone-joint\", and high-order \"hyperbone-joint\" interactions, effectively addressing issues in complex and occlusion-heavy situations. In addition, modern CNN techniques are integrated into the transformer-based architecture, balancing the trade-off between performance and efficiency. HDFormer significantly outperforms state-of-the-art (SOTA) models on Human3.6M and MPI-INF-3DHP datasets, requiring only 1/10 of the parameters and significantly lower computational costs. Moreover, HDFormer demonstrates broad real-world applicability, enabling real-time, accurate 3D pose estimation. The source code is in https://github.com/hyer/HDFormer.","doi":"10.24963/ijcai.2023/65","url":"https://ijcai.org/proceedings/2023/65","pdf":"https://ijcai.org/proceedings/2023/0065.pdf","markdown":"https://ijcai.org/proceedings/2023/65.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/65","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":65,"pages":{"first":581,"last":589},"keywords":["Computer Vision: CV: 3D computer vision","Computer Vision: CV: Video analysis and understanding"],"videos":[],"references":[{"position":1,"raw":"B, 2, J, T] [B, 16, J, T] [B, 32, J, T/2] [B, 64, J, T/4] [B, 128, J, T/8] [B, 128, J, T/8] [B, 64, J, T/4] [B, 32, J, T/2] [B, 16, J, T] [B, 16, J, T] [B, 16, J, T] [B, 16, J, T] [B, 3, J, T] [B, 16, J, T] [B, 32, J, T/2] [B, 64, J, T/4] [B, 128, J, T/8] [B, 16, J, T] 3D pose sequence Figure 3: Overview of our framework: A High-order Directed Transformer with a U-shaped design for 3D human pose estimation. The framework includes downsampling, upsampling, and merging stages, incorporating high-order attention and multi-scale temporal information. The batch size, the number of nodes, and the sequence length are represented by symbols B, J, and T, respectively. (a) First-order Attention (b) High-order Attention 0: Hip 1: R.Hip 2: R.Knee 3: R.Ankle 4: L.Hip 5: L.Knee 6: L.Ankle 7: Spine 8: Thorax 9: Nose 10: Head 11: L.Shoulder 12: L.Elbow 13: L. Wrist 14: R.Shoulder 15: R.Elbow 16: R. Wrist Protocol #1 Dir. Disc Eat Greet Phone Photo Pose Purch. Sit SitD. Smoke Wait WalkD. Walk WalkT. Avg.","title":"J, T] 3D pose sequence Figure 3: Overview of our framework: A High-order Directed Transformer with a U-shaped design for 3D human pose estimation. The framework includes downsampling, upsampling, and merging stages, incorporating high-order attention and multi-scale temporal information. The batch size, the number of nodes, and the sequence length are represented by symbols B, J, and T, respectively. (a) First-order Attention (b) High-order Attention 0: Hip 1: R","authors":"J, T ] [b ;, J, T ] [b ;, J, T ;, J, T ; B ;, J, T ;, J, T ;, J, T ;, J, T ; B ;, J, T ] [b ;, J, T ] [b ;, J, T ] [b ;, J, T] [b, J, T ] [b ;, J, T ] [b ;, J, T ;, J, T ; B ;, J, T ; B","year":null,"venue":"R. Wrist Protocol #1 Dir. Disc Eat Greet Phone Photo Pose Purch. Sit SitD. Smoke Wait WalkD","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"Cai [Cai et al., 2019] (CPN, T=7) 44.6 47.4 45.6 48.8 50.8 59.0 47.2 43.9 57.9 61.9 49.7 46.6 51.3 37.1 39.4 48.8 Pavllo [Pavllo et al., 2018] (CPN, T=243) 45.2 46.7 43.3 45.6 48.1 55.1 44.6 44.3 57.3 65.8 47.1 44.0 49.0 32.8 33.9 46.Xu [Xu et al., 2020] (CPN, T=9) 37.4 43.5 42.7 42.7 46.6 59.7 41.3 45.1 52.7 60.2 45.8 43.1 47.7 33.7 37.1 45.Liu [Liu et al., 2020](CPN, T=243) 41.8 44.8 41.1 44.9 47.4 54.1 43.4 42.2 56.2 63.6 45.3 43.5 45.3 31.3 32.2 45.Wang [Wang et al., 2020] (CPN, T=96) 41.3 43.9 44.0 42.2 48.0 57.1 42.2 43.2 57.3 61.3 47.0 43.5 47.0 32.6 31.8 45.Hu [Hu et al., 2021] (CPN, T=96) 38.0 43.3 39.1 39.4 45.8 53.6 41.4 41.4 55.5 61.9 44.6 41.9 44.5 31.6 29.4 43.Zhang [Zhang et al., 2022] (CPN, T=81) 39.8 43.0 38.6 40.1 43.4 50.6 40.6 41.4 52.2 56.7 43.8 40.8 43.9 29.4 30.3 42.Wang [Wang et al., 2020] (HR-Net, T=96) 38.2 41.0 45.9 39.7 41.4 51.4 41.6 41.4 52.0 57.4 41.8 44.4 41.6 33.1 30.0 42.Hu [Hu et al., 2021] (HR-Net, T=96) 35.5 41.3 36.6 39.1 42.4 49.0 39.9 37.0 51.9 63.3 40.9 41.3 40.3 29.8 28.9 41.Zhang [Zhang et al., 2022] (HR-Net, T=243) 36.7 39.0 36.5 39.4 40.2 44.9 39.8 36.9 47.9 54.8 39.6 37.8 39.3 29.7 30.6 39.8 HDFormer(CPN, T=96) 38.1 43.1 39.3 39.4 44.3 49.1 41.3 40.8 53.1 62.1 43.3 41.8 43.1 31.0 29.7 42.6 HDFormer (HR-Net, T=96) 34.7 41.7 36.0 38.4 41.1 45.3 39.6 37.4 49.0 63.1 39.8 38.9 40.2 29.3 29.1 40.3 Protocol #2 Dir. Disc Eat Greet Phone Photo Pose Purch. Sit SitD. Smoke Wait WalkD. Walk WalkT. Avg.","title":"CPN","authors":"[ Cai, Cai","year":"2018","venue":"CPN","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"Cai [Cai et al., 2019] (CPN, T=7) 35.7 37.8 36.9 40.7 39.6 45.2 37.4 34.5 46.9 50.1 40.5 36.1 41.0 29.6 33.2 39.0 Pavllo [Pavllo et al., 2018] (CPN, T=243) 34.1 36.1 34.4 37.2 36.4 42.2 34.4 33.6 45.0 52.5 37.4 33.8 37.8 25.6 27.3 36.Xu [Xu et al., 2020] (CPN, T=9) 31.0 34.8 34.7 34.4 36.2 43.9 31.6 33.5 42.3 49.0 37.1 33.0 39.1 26.9 31.9 36.Liu [Liu et al., 2020](CPN, T=243) 32.3 35.2 33.3 35.8 35.9 41.5 33.2 32.7 44.6 50.9 37.0 32.4 37.0 25.2 27.2 35.Wang [Wang et al., 2020] (CPN, T=96) 32.9 35.2 35.6 34.4 36.4 42.7 31.2 32.5 45.6 50.2 37.3 32.8 36.3 26.0 23.9 35.Hu [Hu et al., 2021] (CPN, T=96) 29.8 34.4 31.9 31.5 35.1 40.0 30.3 30.8 42.6 49.0 35.9 31.8 35.0 25.7 23.6 33.Zhang [Zhang et al., 2022] (CPN, T=81) 32.0 34.2 31.7 33.7 34.4 39.2 32.0 31.8 42.9 46.9 35.5 32.0 34.4 23.6 25.2 33.Wang [Wang et al., 2020] (HR-Net, T=96) 28.4 32.5 34.4 32.3 32.5 40.9 30.4 29.3 42.6 45.2 33.0 32.0 33.2 24.2 22.9 32.Hu [Hu et al., 2021] (HR-Net, T=96) 27.7 32.7 29.4 31.3 32.5 37.2 29.3 28.5 39.2 50.9 32.9 31.4 32.1 23.6 22.8 32.Zhang [Zhang et al., 2022] (HR-Net, T=243) 28.0 30.9 28.6 30.7 30.4 34.6 28.6 28.1 37.1 47.3 30.5 29.7 30.5 21.6 20.0 30.6 HDFormer (CPN, T=96) 29.6 33.8 31.7 31.3 33.7 37.7 30.6 31.0 41.4 47.6 35.0 30.9 33.7 25.3 23.6 33.1 HDFormer (HR-Net, T=96) 27.9 32.8 29.7 30.6 32.5 35.0 28.9 29.2 38.3 50.0 32.9 30.1 31.8 23.6 22.8 31.7","title":"CPN","authors":"[ Cai, Cai","year":"2018","venue":"CPN","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cai et al., 2019] Yujun Cai, Liuhao Ge, Jun Liu, Jianfei Cai, Tat-Jen Cham, Junsong Yuan, and Nadia Magnenat- Thalmann. Exploiting spatial-temporal relationships for 3d pose estimation via graph convolutional networks. IEEE/CVF International Conference on Computer Vision, pages 2272-2281, 2019.","title":"Exploiting spatial-temporal relationships for 3d pose estimation via graph convolutional networks","authors":"Yujun Cai, Liuhao Ge, Jun Liu, Jianfei Cai, Tat-Jen Cham, Junsong Yuan, Nadia Magnenat-Thalmann","year":"2019","venue":"IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen et al., 2017] Yilun Chen, Zhicheng Wang, Yuxiang Peng, Zhiqiang Zhang, Gang Yu, and Jian Sun. Cas- caded pyramid network for multi-person pose estimation. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7103-7112, 2017.","title":"Cascaded pyramid network for multi-person pose estimation","authors":"Yilun Chen, Zhicheng Wang, Yuxiang Peng, Zhiqiang Zhang, Gang Yu, Jian Sun","year":"2017","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chen et al., 2021] Tianlang Chen, Chengjie Fang, Xiaohui Shen, Yiheng Zhu, Zhili Chen, and Jiebo Luo. Anatomy- aware 3d human pose estimation with bone-based pose de- composition. IEEE Transactions on Circuits and Systems for Video Technology, 32:198-209, 2021.","title":"Anatomyaware 3d human pose estimation with bone-based pose decomposition","authors":"Tianlang Chen, Chengjie Fang, Xiaohui Shen, Yiheng Zhu, Zhili Chen, Jiebo Luo","year":"2021","venue":"IEEE Transactions on Circuits and Systems for Video Technology","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Cheng et al., 2022] Zhi-Qi Cheng, Qi Dai, Siyao Li, Teruko Mitamura, and Alexander Hauptmann. Gsrformer: Grounded situation recognition transformer with alternate semantic attention refinement. In Proceedings of the 30th ACM International Conference on Multimedia, pages 3272-3281, 2022.","title":"Gsrformer: Grounded situation recognition transformer with alternate semantic attention refinement","authors":"Zhi-Qi Cheng, Qi Dai, Siyao Li, Teruko Mitamura, Alexander Hauptmann","year":"2022","venue":"Proceedings of the 30th ACM International Conference on Multimedia","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Ding et al., 2019] Jianbang Ding, Xuancheng Ren, Ruixuan Luo, and Xu Sun. An adaptive and momental bound method for stochastic learning. ArXiv, abs/1910.12249, 2019.","title":"An adaptive and momental bound method for stochastic learning","authors":"Ding","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Gilmer et al., 2017] Justin Gilmer, Samuel S. Schoenholz, Patrick F. Riley, Oriol Vinyals, and George E. Dahl. Neural message passing for quantum chemistry. ArXiv, abs/1704.01212, 2017.","title":"Neural message passing for quantum chemistry","authors":"Justin Gilmer, Samuel S Schoenholz, Patrick F Riley, Oriol Vinyals, George E Dahl","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gong et al., 2021] Kehong Gong, Jianfeng Zhang, and Ji- ashi Feng. Poseaug: A differentiable pose augmenta- tion framework for 3d human pose estimation. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8571-8580, 2021.","title":"Poseaug: A differentiable pose augmentation framework for 3d human pose estimation","authors":"Gong","year":"2021","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[He et al., 2021] Jun-Yan He, Xiao Wu, Zhi-Qi Cheng, Zhaoquan Yuan, and Yu-Gang Jiang. Db-lstm: Densely- connected bi-directional lstm for human action recogni- tion. Neurocomputing, 444:319-331, 2021.","title":"Db-lstm: Denselyconnected bi-directional lstm for human action recognition","authors":"He","year":"2021","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[He et al., 2023] Jun-Yan He, Zhi-Qi Cheng, Chenyang Li, Wangmeng Xiang, Binghui Chen, Bin Luo, Yifeng Geng, and Xuansong Xie. Damo-streamnet: Optimizing stream- ing perception in autonomous driving. arXiv preprint arXiv:2303.17144, 2023.","title":"Damo-streamnet: Optimizing streaming perception in autonomous driving","authors":"He","year":"2023","venue":null,"doi":null,"url":null,"internal_url":"/proceedings/2023/90"},{"position":13,"raw":"[Hu et al., 2021] Wenbo Hu, Changgong Zhang, Fangneng Zhan, Lei Zhang, and Tien-Tsin Wong. Conditional di- rected graph convolution for 3d human pose estimation. Proceedings of the 29th ACM International Conference on Multimedia, 2021.","title":"Conditional directed graph convolution for 3d human pose estimation","authors":"Wenbo Hu, Changgong Zhang, Fangneng Zhan, Lei Zhang, Tien-Tsin Wong","year":"2021","venue":"Proceedings of the 29th ACM International Conference on Multimedia","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Huang et al., 2021] Siyu Huang, Haoyi Xiong, Zhi-Qi Cheng, Qingzhong Wang, Xingran Zhou, Bihan Wen, Jun Huang, and Dejing Dou. Generating person images with appearance-aware pose stylizer. In International Joint Conference on Artificial Intelligence, pages 623-629. In- ternational Joint Conferences on Artificial Intelligence, 2021.","title":"Generating person images with appearance-aware pose stylizer","authors":"Siyu Huang, Haoyi Xiong, Zhi-Qi Cheng, Qingzhong Wang, Xingran Zhou, Bihan Wen, Jun Huang, Dejing Dou","year":"2021","venue":"International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2020/87"},{"position":15,"raw":"[Ionescu et al., 2014] 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. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36:1325-1339, 2014.","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":"2014","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Iskakov et al., 2019] Karim Iskakov, Egor Burkov, Victor S. Lempitsky, and Yury Malkov. Learnable triangulation of human pose. IEEE/CVF International Conference on Computer Vision, pages 7717-7726, 2019.","title":"Learnable triangulation of human pose","authors":"Karim Iskakov, Egor Burkov, Victor S Lempitsky, Yury Malkov","year":"2019","venue":"IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Li et al., 2020] Shichao Li, Lei Ke, Kevin Pratama, Yu- Wing Tai, Chi-Keung Tang, and Kwang-Ting Cheng. Cas- caded deep monocular 3d human pose estimation with evolutionary training data. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6172- 6182, 2020.","title":"Cascaded deep monocular 3d human pose estimation with evolutionary training data","authors":"Li","year":"2020","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Li et al., 2021] Wenhao Li, Hong Liu, Runwei Ding, Mengyuan Liu, Pichao Wang, and Wenming Yang. Ex- ploiting temporal contexts with strided transformer for 3d human pose estimation. IEEE Transactions on Multime- dia, 25:1282-1293, 2021.","title":"Exploiting temporal contexts with strided transformer for 3d human pose estimation","authors":"Wenhao Li, Hong Liu, Runwei Ding, Mengyuan Liu, Pichao Wang, Wenming Yang","year":"2021","venue":"IEEE Transactions on Multimedia","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Lin and Lee, 2019] Jiahao Lin and Gim Hee Lee. Trajectory space factorization for deep video-based 3d human pose estimation. ArXiv, abs/1908.08289, 2019.","title":"Trajectory space factorization for deep video-based 3d human pose estimation","authors":"Lin, Lee ; ] Jiahao Lin, Gim Hee, Lee","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Liu et al., 2020] Ruixu Liu, Ju Shen, He Wang, Chen Chen, Sen ching S. Cheung, and Vijayan K. Asari. Attention mechanism exploits temporal contexts: Real-time 3d hu- man pose reconstruction. IEEE/CVF Conference on Com- puter Vision and Pattern Recognition, pages 5063-5072, 2020.","title":"Attention mechanism exploits temporal contexts: Real-time 3d human pose reconstruction","authors":"Liu","year":"2020","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Mehta et al., 2016a] Dushyant Mehta, Helge Rhodin, Dan Casas, Pascal V. Fua, Oleksandr Sotnychenko, Weipeng Xu, and Christian Theobalt. Monocular 3d human pose es- timation in the wild using improved cnn supervision. Inter- national Conference on 3D Vision, pages 506-516, 2016.","title":"Monocular 3d human pose estimation in the wild using improved cnn supervision","authors":"Mehta","year":"2016","venue":"International Conference on 3D Vision","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Mehta et al., 2016b] Dushyant Mehta, Helge Rhodin, Dan Casas, Pascal V. Fua, Oleksandr Sotnychenko, Weipeng Xu, and Christian Theobalt. Monocular 3d human pose es- timation in the wild using improved cnn supervision. Inter- national Conference on 3D Vision, pages 506-516, 2016.","title":"Monocular 3d human pose estimation in the wild using improved cnn supervision","authors":"Mehta","year":"2016","venue":"International Conference on 3D Vision","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Mehta et al., 2017] Dushyant Mehta, Srinath Sridhar, Olek- sandr Sotnychenko, Helge Rhodin, Mohammad Shafiei, Hans-Peter Seidel, Weipeng Xu, Dan Casas, and Chris- tian Theobalt. Vnect: Real-time 3d human pose estimation with a single rgb camera. ACM Trans. Graph., 36:44:1- 44:14, 2017.","title":"Vnect: Real-time 3d human pose estimation with a single rgb camera","authors":"Dushyant Mehta, Srinath Sridhar, Oleksandr Sotnychenko, Helge Rhodin, Mohammad Shafiei, Hans-Peter Seidel, Weipeng Xu, Dan Casas, Christian Theobalt","year":"2017","venue":"ACM Trans. Graph","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Pavllo et al., 2018] Dario Pavllo, Christoph Feichtenhofer, David Grangier, and Michael Auli. 3d human pose es- timation in video with temporal convolutions and semi- supervised training. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7745-7754, 2018.","title":"3d human pose estimation in video with temporal convolutions and semisupervised training","authors":"Dario Pavllo, Christoph Feichtenhofer, David Grangier, Michael Auli","year":"2018","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Qiao et al., 2022] Jian-Jun Qiao, Zhi-Qi Cheng, Xiao Wu, Wei Li, and Ji Zhang. Real-time semantic segmentation with parallel multiple views feature augmentation. In Pro- ceedings of the 30th ACM International Conference on Multimedia, pages 6300-6308, 2022.","title":"Real-time semantic segmentation with parallel multiple views feature augmentation","authors":"Jian-Jun Qiao, Zhi-Qi Cheng, Xiao Wu, Wei Li, Ji Zhang","year":"2022","venue":"Proceedings of the 30th ACM International Conference on Multimedia","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Qiu et al., 2019] Haibo Qiu, Chunyu Wang, Jingdong Wang, Naiyan Wang, and Wenjun Zeng. Cross view fu- sion for 3d human pose estimation. IEEE/CVF Interna- tional Conference on Computer Vision, pages 4341-4350, 2019.","title":"Cross view fusion for 3d human pose estimation","authors":"Haibo Qiu, Chunyu Wang, Jingdong Wang, Naiyan Wang, Wenjun Zeng","year":"2019","venue":"IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Scarselli et al., 2009] Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner, and Gabriele Monfardini. The graph neural network model. IEEE Transactions on Neural Networks, 20:61-80, 2009.","title":"The graph neural network model","authors":"Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner, Gabriele Monfardini","year":"2009","venue":"IEEE Transactions on Neural Networks","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Shi et al., 2018] Lei Shi, Yifan Zhang, Jian Cheng, and Hanqing Lu. Two-stream adaptive graph convolu- tional networks for skeleton-based action recognition. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12018-12027, 2018.","title":"Two-stream adaptive graph convolutional networks for skeleton-based action recognition","authors":"Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu","year":"2018","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Shi et al., 2019] Lei Shi, Yifan Zhang, Jian Cheng, and Hanqing Lu. Skeleton-based action recognition with di- rected graph neural networks. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7904- 7913, 2019.","title":"Skeleton-based action recognition with directed graph neural networks","authors":"Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu","year":"2019","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Sun et al., 2019] Ke Sun, Bin Xiao, Dong Liu, and Jing- dong Wang. Deep high-resolution representation learn- ing for human pose estimation. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5686- 5696, 2019.","title":"Deep high-resolution representation learning for human pose estimation","authors":"Ke Sun, Bin Xiao, Dong Liu, Jingdong Wang","year":"2019","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Tu et al., 2023] Shuyuan Tu, Qi Dai, Zuxuan Wu, Zhi-Qi Cheng, Han Hu, and Yu-Gang Jiang. Implicit temporal modeling with learnable alignment for video recognition. ArXiv, abs/2304.10465, 2023.","title":"Implicit temporal modeling with learnable alignment for video recognition","authors":"Shuyuan Tu, Qi Dai, Zuxuan Wu, Zhi-Qi Cheng, Han Hu, Yu-Gang Jiang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam M. Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In NIPS, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam M Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, Illia Polosukhin","year":"2017","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Wang et al., 2020] Jingbo Wang, Sijie Yan, Yuanjun Xiong, and Dahua Lin. Motion guided 3d pose estimation from videos. ArXiv, abs/2004.13985, 2020.","title":"Motion guided 3d pose estimation from videos","authors":"Jingbo Wang, Sijie Yan, Yuanjun Xiong, Dahua Lin","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Wang et al., 2021] Wenxiao Wang, Lulian Yao, Long Chen, Binbin Lin, Deng Cai, Xiaofei He, and Wei Liu. Cross- former: A versatile vision transformer hinging on cross- scale attention. ArXiv, abs/2303.06908, 2021.","title":"Crossformer: A versatile vision transformer hinging on crossscale attention","authors":"Wang","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Xiang et al., 2022] Wangmeng Xiang, Chao Li, Yuxuan Zhou, Biao Wang, and Lei Zhang. Language supervised training for skeleton-based action recognition. ArXiv, abs/2208.05318, 2022.","title":"Language supervised training for skeleton-based action recognition","authors":"Xiang","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Xu et al., 2020] Jingwei Xu, Zhenbo Yu, Bingbing Ni, Jiancheng Yang, Xiaokang Yang, and Wenjun Zhang. Deep kinematics analysis for monocular 3d human pose estimation. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 896-905, 2020.","title":"Deep kinematics analysis for monocular 3d human pose estimation","authors":"Xu","year":"2020","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Yan et al., 2019] Sijie Yan, Zhizhong Li, Yuanjun Xiong, Huahan Yan, and Dahua Lin. Convolutional sequence gen- eration for skeleton-based action synthesis. IEEE/CVF In- ternational Conference on Computer Vision, pages 4393- 4401, 2019.","title":"Convolutional sequence generation for skeleton-based action synthesis","authors":"Sijie Yan, Zhizhong Li, Yuanjun Xiong, Huahan Yan, Dahua Lin","year":"2019","venue":"IEEE/CVF In-ternational Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Ye et al., 2022] Hang Ye, Wentao Zhu, Chun yu Wang, Ru- jie Wu, and Yizhou Wang. Faster voxelpose: Real-time 3d human pose estimation by orthographic projection. In European Conference on Computer Vision, 2022.","title":"Faster voxelpose: Real-time 3d human pose estimation by orthographic projection","authors":"Ye","year":"2022","venue":"European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Zeng et al., 2021] Ailing Zeng, Xiao Sun, Lei Yang, Nanx- uan Zhao, Minhao Liu, and Qiang Xu. Learning skele- tal graph neural networks for hard 3d pose estimation. IEEE/CVF International Conference on Computer Vision, pages 11416-11425, 2021.","title":"Learning skeletal graph neural networks for hard 3d pose estimation","authors":"Ailing Zeng, Xiao Sun, Lei Yang, Nanxuan Zhao, Minhao Liu, Qiang Xu","year":"2021","venue":"IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Zhang et al., 2022] Jinlu Zhang, Zhigang Tu, Jianyu Yang, Yujin Chen, and Junsong Yuan. Mixste: Seq2seq mixed spatio-temporal encoder for 3d human pose estimation in video. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13222-13232, 2022.","title":"Mixste: Seq2seq mixed spatio-temporal encoder for 3d human pose estimation in video","authors":"Zhang","year":"2022","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Zhao et al., 2018] Bo Zhao, Xiao Wu, Zhi-Qi Cheng, Hao Liu, Zequn Jie, and Jiashi Feng. Multi-view image gener- ation from a single-view. In Proceedings of the 26th ACM international conference on Multimedia, pages 383-391, 2018.","title":"Multi-view image generation from a single-view","authors":"Bo Zhao, Xiao Wu, Zhi-Qi Cheng, Hao Liu, Zequn Jie, Jiashi Feng","year":"2018","venue":"Proceedings of the 26th ACM international conference on Multimedia","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Zhao et al., 2019] Long Zhao, Xi Peng, Yu Tian, Mub- basir Kapadia, and Dimitris N. Metaxas. Semantic graph convolutional networks for 3d human pose regression. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3420-3430, 2019.","title":"Semantic graph convolutional networks for 3d human pose regression","authors":"Zhao","year":"2019","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Zhao et al., 2022] Weixi Zhao, Weiqiang Wang, and Yunjie Tian. Graformer: Graph-oriented transformer for 3d pose estimation. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 20406-20415, 2022.","title":"Graformer: Graph-oriented transformer for 3d pose estimation","authors":"Zhao","year":"2022","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Zheng et al., 2021] Ce Zheng, Sijie Zhu, Mat'ias Mendieta, Taojiannan Yang, Chen Chen, and Zhengming Ding. 3d human pose estimation with spatial and temporal trans- formers. IEEE/CVF International Conference on Com- puter Vision, pages 11636-11645, 2021.","title":"3d human pose estimation with spatial and temporal transformers","authors":"Ce Zheng, Sijie Zhu, Taojiannan Mat'ias Mendieta, Chen Yang, Zhengming Chen, Ding","year":"2021","venue":"IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Zhou et al., 2022] Yuxuan Zhou, Zhi-Qi Cheng, Chao Li, Yifeng Geng, Xuansong Xie, and Margret Keuper. Hyper- graph transformer for skeleton-based action recognition. ArXiv, abs/2211.09590, 2022.","title":"Hypergraph transformer for skeleton-based action recognition","authors":"Yuxuan Zhou, Zhi-Qi Cheng, Chao Li, Yifeng Geng, Xuansong Xie, Margret Keuper","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Zhou et al., 2023] Yuxuan Zhou, Zhi-Qi Cheng, Jun-Yan He, Bin Luo, Yifeng Geng, Xuansong Xie, and Margret Keuper. Overcoming topology agnosticism: Enhancing skeleton-based action recognition through redefined skele- tal topology awareness. arXiv preprint arXiv:2305.11468, 2023.","title":"Overcoming topology agnosticism: Enhancing skeleton-based action recognition through redefined skeletal topology awareness","authors":"Yuxuan Zhou, Zhi-Qi Cheng, Jun-Yan He, Bin Luo, Yifeng Geng, Xuansong Xie, Margret Keuper","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[Zhu et al., 2021] Yiran Zhu, Xing Xu, Fumin Shen, Yanli Ji, Lianli Gao, and Heng Tao Shen. Posegtac: Graph trans- former encoder-decoder with atrous convolution for 3d hu- man pose estimation. In International Joint Conference on Artificial Intelligence, 2021.","title":"Posegtac: Graph transformer encoder-decoder with atrous convolution for 3d human pose estimation","authors":"Yiran Zhu, Xing Xu, Fumin Shen, Yanli Ji, Lianli Gao, Heng Tao Shen","year":"2021","venue":"International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2021/188"},{"position":48,"raw":"[Zou and Tang, 2021] Zhiming Zou and Wei Tang. Modu- lated graph convolutional network for 3d human pose esti- mation. IEEE/CVF International Conference on Computer Vision, pages 11457-11467, 2021.","title":"Modulated graph convolutional network for 3d human pose estimation","authors":"Tang ; ] Zhiming Zou, Wei Zou, Tang","year":"2021","venue":"IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}