Coupled Action Recognition and Pose Estimation from Multiple Views

By Angela Yao, Juergen Gall, Luc Van Gool. 2012

140 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering, 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 Control and Systems Engineering

In Human-Computer Interaction

Citations in the corpus

Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, methodology): “Many other existing human representations are also based on low-level skeleton-based features [117], [118], [119], [123], [134], [139], [140], [141], [154], [157], [158], [162], [200] without modeling the hierarchy of the data.”
Cross-View Action Modeling, Learning, and Recognition (2014, methodology): “[21] proposes a coupled action recognition and pose estimation method by formulating pose estimation as an optimization over a set of action-specific manifold.”
2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning (2018, neutral): “Pose estimation and action recognition are usually handled as distinct problems [14] or the last is used as a prior for the first [57, 22].”
Efficient Pose-Based Action Recognition (2014, methodology): “Similar observations are reported in [16, 18] on larger and more complex datasets.”
Gesture Recognition Portfolios for Personalization (2014, background): “Random forests have been shown to work well for action and gesture recognition in the past, either through a voting framework [20] or by direct classiﬁcation [6].”
Real-Time Articulated Hand Pose Estimation Using Semi-supervised Transductive Regression Forests (2013, methodology): “Kinematics Inverse kinematics is a standard technique in model-based and tracking approaches for both body [28, 22] and hand poses estimation [8, 15, 25].”
Leveraging Hierarchical Parametric Networks for Skeletal Joints Based Action Segmentation and Recognition (2014, background): “Yao et al. [31] modified a subset of the relational pose features for action recognition and showed that with these features, it is not necessary to have perfect poses to perform action recognition.”
Joint action recognition and pose estimation from video (2015, background): “[31] is the only paper that tries to couple action recognition and pose estimation.”
Video-Based Human Behavior Understanding: A Survey (2013, background): “Depending on the quality of the camera view, position information can be complemented by other descriptors, such as the trajectories of body joints [9] or head pose changes [10].”
Monocular 3D Human Pose Estimation by Predicting Depth on Joints (2017, background): “ages [40, 26] or RGB images captured simultaneously at multiple viewpoints [2, 10].”
Spatio-temporal Matching for Human Detection in Video (2014, unknown): “Inspired by [23], Yu et al.”
Towards Understanding Action Recognition (2013, background): “Recently, human pose as a feature for action recognition has been revisited [10, 22, 26, 29, 34].”
Pose for Action - Action for Pose (2016, methodology): “There have been only few works [15], [39], [42] that couple action recognition and pose estimation to improve pose estimation.”
MotionBERT: A Unified Perspective on Learning Human Motion Representations (2022, background): “The pioneering works [69, 108, 120] point out the inherent connection be-tween action recognition and human pose estimation.”
Parsing occluded people by flexible compositions (2014, background): “Parsing humans into parts is an important visual task with many applications such as activity recognition [27, 29].”
A Survey on Human Motion Analysis from Depth Data (2013, background): “[38] where skeleton motion is encoded by relational pose features [39], as shown in Figure 12.”