Human Pose Estimation with Fields of Parts

By Martin Kiefel, Peter Gehler. 2014

81 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Convolutional Pose Machines (2016, background): “[17] is based on the pictorial structures model but differs in the underlying graph representation.”
Higher Order Conditional Random Fields in Deep Neural Networks (2015, background): “Some early works that advocated gradient backpropagation through graphical model inference for parameter optimisation include [9, 19, 25] and [41].”
Pose-conditioned joint angle limits for 3D human pose reconstruction (2015, methodology): “Real results with automatic part-based detections [16] on the Leeds sports pose dataset on a few frames.”
Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image (2016, methodology): “Akhter and Black [4] run a different 2D detector [23] and show results for their method on a few images.”
RMPE: Regional Multi-person Pose Estimation (2016, unknown): “Graph based models such as random field models [20] and dependency graph models [14] have also been widely investigated in the literature [13, 32, 21, 26].”
Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks (2015, background): “Several works [32, 17, 29, 49, 39] demonstrate how to learn free parameters of the dense CRF model.”
Robust Optimization for Deep Regression (2015, unknown): “0 Kiefel&Gehler [21] 78.”
Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer (2015, methodology): “As our model comprises three sets of densely connected variables (namely P , L and P ↔ L), we exploit the algorithm of [21, 45] which generalizes [22] to multiple fields.”
Deep Multitask Architecture for Integrated 2D and 3D Human Sensing (2017, background): “In recent years, deep learning had a great impact over the state-of-the-art pose estimation models where different hierarchical feature extraction architectures have been combined with spatial constraints between the human body parts [46, 10, 45, 20, 30, 28, 23, 8, 13, 9, 43, 27, 24].”
Higher Order Potentials in End-to-End Trainable Conditional Random Fields (2015, background): “Some early works that advocated gradient backpropagation through graphical model inference for parameter optimization include [35, 8, 22] and [17].”
Human Pose Regression by Combining Indirect Part Detection and Contextual Information (2017, unknown): “s reported by Carreira et Table 1: Results on LSP test samples using the PCK measure at 0.2 with OC annotations. Method Head Sho. Elb. Wri. Hip Knee Ank. PCK Detection based methods Kiefel and Gehler [24] 83.5 73.7 55.9 36.2 73.7 70.5 66.9 65.8 Ramakrishnaet al. [35] 84.9 77.8 61.4 47.2 73.6 69.1 68”