Recognizing human actions in videos acquired by uncalibrated moving cameras

By Alper Yilmaz, Mubarak Shah. 2005

202 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

Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “[174] Action Space Conc Lowlv Hand X X X X Yilma and Shah [175] Multiview Geometry Conc Lowlv Hand X X Gong et al.”
Using learning analytics to assess students' behavior in open-ended programming tasks (2011, background): “[17] were able to detect basic human actions related to movement.”
Action Recognition from Arbitrary Views using 3 D Exemplars (2007, background): “[6, 20] assume a known parametric model, typically a kinematic model, and represent actions in a joint or parameter space.”
View-Invariant Action Recognition Using Latent Kernelized Structural SVM (2012, background): “Some existing approaches address the view-invariant action recognition by using epipolar geometry [6] [7] or a full 3D reconstruction [8] [9].”
Exploring discriminative pose sub-patterns for effective action classification (2013, background): “Similar methodologies can be found in [26, 35, 28, 3], where either trajectories formed by joints [28, 35, 3] or curvature patterns of trajectories formed from body parts [26] are treated as features.”
Hierarchical spatio-temporal context modeling for action recognition (2009, background): “Therefore the action recognition algorithms [22, 23], which aimed to achieve the robustness to viewpoint change based on geometric reconstruction, are doomed due to their reliance on exact knowledge of the object contours or multiple view geometries, which are prone to errors in unconstrained videos”
Conditional models for contextual human motion recognition (2006, background): “Yilmaz and Shah [ 32 ] recognize human motion using multiple uncalibrated cameras and a criteria based on the condition number of a matrix that stores 3d reconstructed points on the human body.”
Capturing Global and Local Dynamics for Human Action Recognition (2014, methodology): “Given some specifically designed features, template matching [16], neighborhood-based method [22] and other models are typically used to make predictions.”
Learning Motion Categories using both Semantic and Structural Information (2007, background): “The parts can be trajectories [16] or flow vectors [15, 5] of corners, profiles generated from silhouettes [1] and ST interest points [9, 3, 8].”
Inverse Dynamics for Action Recognition (2013, background): “Yilmaz and Shah [14] extended the standard epipolar geometry to the”
Action Recognition from Arbitrary Views using 3D Exemplars (2007, methodology): “[6, 20] assume a known parametric model, typically a kinematic model, and represent actions in a joint or parameter space.”
Cross-View Action Recognition over Heterogeneous Feature Spaces (2013, unknown): “One possible solution [14, 18, 19, 11] is building a view-independent 3D model of human body via the 3D reconstruction from multiple calibrated cameras or epipolar geometry reasoning based on point correspondences.”
Human activity analysis (2011, background): “D volumes [Laptev and Lindeberg 2003; Dollar et al. 2005; Niebles et al. 2006; Yilmaz and Shah 2005a; Ryoo and Aggarwal 2009b].”
Cross-View Action Recognition from Temporal Self-similarities (2008, methodology): “To address the multi-view problem, [3,4] employ the use of epipolar geometry.”