Human Pose Estimation Using a Joint Pixel-wise and Part-wise Formulation

By Lubor Ladicky, Philip H. S. Torr, Andrew Zisserman. 2013

115 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Towards Accurate Multi-person Pose Estimation in the Wild (2017, methodology): “A probabilistic approach to part grouping and labeling is proposed also by Ladickly et al. [28].”
Stacked Hourglass Networks for Human Pose Estimation (2016, background): “[24], research on human pose estimation started to shift from the classic approaches [2,3,4,1,5,6,7,8,9] to”
DeeperCut: A Deeper, Stronger, and Faster Multi-person Pose Estimation Model (2016, background): “Previous work has addressed this problem as sequence of person detection and pose estimation [21,22,23].”
Self Adversarial Training for Human Pose Estimation (2017, background): “Early work often tackles the problem using graphical models [2, 13, 22] and random field inference [23, 35] with handcrafted image features.”
An Exemplar-Based CRF for Multi-instance Object Segmentation (2014, unknown): “[13] integrates a part-based layout model with pixellevel labeling for human pose and layout estimation.”
Iterated Second-Order Label Sensitive Pooling for 3D Human Pose Estimation (2014, methodology): “Body labeling methods have also been proposed in the context of person detection[4], to learn a model of the body[13] and recently for 2D pose prediction[21, 11], but not within models and algorithms carrying all the way to 3D pose estimation.”
Towards Unified Human Parsing and Pose Estimation (2014, background): “Only very recently, some works [3, 2] began to link these two tasks with the strategy of performing parsing and pose estimation sequentially or iteratively.”
A High Performance CRF Model for Clothes Parsing (2014, background): “However, most approaches have focused on figure/ground labeling [19,20].”
Human Pose Regression by Combining Indirect Part Detection and Contextual Information (2017, unknown): “This can be seen as the shift from classical approaches [32, 25] to deep architectures.”
Multi-person Pose Estimation with Local Joint-to-Person Associations (2016, background): “[14, 15] define a joint pose estimation model for all detected persons, and utilize several occlusion clues to model interactions between people.”
Human Pose Estimation with Fields of Parts (2014, methodology): “Examples of better appearance models are the local image conditioned features used in [25], the use of mid-level representations via Poselets [14,3,22], or semantic segmentation information to include background evidence [10,31,20,4].”
AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time (2022, background): “In conventional body-only pose estimation, recognizing the pose of multiple persons in the wild is more challenging than recognizing the pose of a single person in an image [4], [5], [6], [7], [8].”