Articulated Pose Estimation Using Discriminative Armlet Classifiers

By Georgia Gkioxari, Pablo Arbeláez, Lubomir D. Bourdev, Jitendra Malik. 2013

106 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Towards Accurate Multi-person Pose Estimation in the Wild (2017, background): “[15], which spurred a large body of work on probabilistic graphical models for 2-D human pose inference [3, 12, 39, 47, 11, 28, 34, 40, 18].”
DeepPose: Human Pose Estimation via Deep Neural Networks (2013, background): “More recently, Gkioxari et al. [10] propose a semi-global classiﬁer for part conﬁg-uration.”
Strong Appearance and Expressive Spatial Models for Human Pose Estimation (2013, methodology): “This requires models which in contrast to more traditional approaches focus on part detection and rely either on loose geometric features [26] or ignore them altogether [27, 15].”
Pose Machines: Articulated Pose Estimation via Inference Machines (2014, methodology): “Recent methods have also explored using part hierarchies [16,17] and condition the detection of smaller parts that model regions around anatomical joints on the localization of larger composite parts or poselets [11,10,18,19] that model limbs in canonical configurations and tend to be easier to dete”
Efficient ConvNet-based marker-less motion capture in general scenes with a low number of cameras (2015, background): “[20] shows good performance on real-world data, however, it is demonstrated only on arms.”
Do Convnets Learn Correspondence? (2014, methodology): “Human pose estimation has been approached using tree structured methods to model the spatial relationships between parts [12, 13, 14], and also using poselets [15] as an intermediate step to localize human keypoints [16, 17].”
Multi-task Recurrent Neural Network for Immediacy Prediction (2015, methodology): “Both holistic models [28, 11, 19, 20, 33] and local models [31, 8, 39, 6, 9, 30, 24, 10, 26, 14, 29, 35, 25, 1, 21, 4] were used for estimating the pose of a single person.”
Bottom-Up and Top-Down Reasoning with Hierarchical Rectified Gaussians (2015, background): “[5] Georgia Gkioxari, Pablo Arbeláez, Lubomir Bourdev, and Jagannath Malik.”
Actions and Attributes from Wholes and Parts (2014, methodology): “We use a greedy clustering algorithm, similar to [14].”
R-CNNs for Pose Estimation and Action Detection (2014, methodology): “This is the standard dataset for benchmarking human pose estimation in PASCAL [13]”
Multi-source Deep Learning for Human Pose Estimation (2014, background): “Pose estimation is considered as holistic recognition in [14, 32, 33].”
Cascaded Pyramid Network for Multi-person Pose Estimation (2017, background): “More specifically, the classical works [1, 34, 13, 33, 8, 44, 29, 20] formulate the problem of human keypoints estimation as a tree-structured or graphical model problem and predict keypoint locations based on hand-crafted features.”
Monocular human pose estimation: A survey of deep learning-based methods (2020, background): “And percentage curves for each limb can be obtained with the variation of threshold in the metric (Gkioxari et al., 2013).”
2D Human Pose Estimation: New Benchmark and State of the Art Analysis (2014, methodology): “Our dataset is complementary to the J-HMDB dataset [11] and provides more images and a wider coverage of ac- tivities (491 in our dataset vs. 21 in J-HMDB), whereas J-HMDB provides densely annotated image sequences and larger number of videos for each activity.”
MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation (2014, methodology): “[42] incorporates edges, contours, and color histograms in addition to the HoG features.”
Body Parts Dependent Joint Regressors for Human Pose Estimation in Still Images (2014, background): “…independently and modeling the spatial and orientation relations between part templates by a loopy model, we therefore propose a more discriminative template representation that already takes co-occurrences and relations to other parts to some extent into account, as illustrated in Figure 1.”