An Efficient Convolutional Network for Human Pose Estimation

By Umer Rafi, Bastian Leibe, Juergen Gall, Ilya Kostrikov. 2016

137 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

1. Juergen Gall
2. Bernt Schiele
3. Mykhaylo Andriluka
4. Leonid Pishchulin
5. Eldar Insafutdinov
6. Anton Milan
7. David Picard
8. Hedi Tabia

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Bernt Schiele
3. Yingli Tian
4. Juergen Gall
5. Xiaogang Wang
6. Dacheng Tao
7. Jitendra Malik
8. Yi Yang

In Human-Computer Interaction

1. Yingli Tian
2. Mingyi He
3. Yucheng Chen
4. Martin Garbade
5. David Picard
6. Hedi Tabia
7. Diogo Carbonera Luvizon
8. Bernt Schiele

Citations in the corpus

• 2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning (2018, background): “The problem of human pose estimation has been intensively studied in the last years, from Pictorial Structures [2, 17, 37] to more recent CNN approaches [34, 25, 38, 20, 41, 54, 5, 51, 52, 36].”
• PoseTrack: A Benchmark for Human Pose Estimation and Tracking (2017, background): “Human pose estimation has recently made significant progress on the tasks of single person pose estimation in individual frames [46, 45, 44, 4, 49, 15, 18, 31, 2, 36] and videos [34, 6, 21, 12] as well as multi-person pose estimation in monocular images [35, 18, 20, 3, 32].”
• Adversarial PoseNet: A Structure-Aware Convolutional Network for Human Pose Estimation (2017, unknown): “1 [25] 97.”
• Human Pose Regression by Combining Indirect Part Detection and Contextual Information (2017, methodology): “More recent methods have shown significant improvements on accuracy by using fully convolutional models to generate belief maps (or heat maps) for joint probabilities [34, 3, 5, 27, 13].”
• Self Adversarial Training for Human Pose Estimation (2017, unknown): “[34], BMVC’16 97.”
• Integral Human Pose Regression (2017, unknown): “(Heat map based) [47] [39] [49] [5] [33] [50] H1 MS-H1 HG-H1”
• Pose for Action - Action for Pose (2016, background): “parts [10], [17], [20], [21], [28], [35].”
• Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation (2017, unknown): “, BMVC’16 [67] 97.”
• Fast Human Pose Estimation (2018, methodology): “When compared to the most efficient alternative competitor [21], our model is 2.”
• Toward fast and accurate human pose estimation via soft-gated skip connections (2020, unknown): “, BMVC’16 [27] 97.”
• Monocular human pose estimation: A survey of deep learning-based methods (2020, methodology): “, 2018), multi-scale inputs (Rafi et al., 2016), heatmap-based improvement (Papandreou et al.”
• Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation (2018, unknown): “[29] 97.”