Hierarchical spatio-temporal context modeling for action recognition

By Ju Sun, Xiao Wu, Shuicheng Yan, Loong Fah Cheong, Tat-seng Chua, Jintao Li. 2009

450 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

Beyond Gaussian Pyramid: Multi-skip Feature Stacking for action recognition (2014, methodology): “Among them, the trajectory based approaches [18, 35, 38, 40, 8], especially the Dense Trajectory method proposed by Wang et al.”
A Robust and Efficient Video Representation for Action Recognition (2015, unknown): “Feature trajectories (Matikainen et al, 2009; Messing et al, 2009; Sun et al, 2009; Wang et al, 2013a) have been shown to be a good way for capturing the intrinsic dynamics of video data.”
Modeling Scene and Object Contexts for Human Action Retrieval With Few Examples (2011, background): “Fei-Fei et al. [23] proposed a Bayesian formulation for learning object categories from very few images.”
Learning a hierarchy of discriminative space-time neighborhood features for human action recognition (2010, methodology): “When using the global grid-based histograms, performance improves when one chooses or learns the most discriminative bins [15, 31, 11].”
Discovering discriminative action parts from mid-level video representations (2012, methodology): “However, we note that the multi-grid spatial binning approach [17, 27] cannot be used in support of other tasks, such as the localization that our model performs.”
Real-time human action recognition based on depth motion maps (2013, methodology): “In [3], SIFT-feature trajectories modeled in a hierarchy of three abstraction levels were used to recognize actions in video sequences.”
Human activity recognition using multi-features and multiple kernel learning (2014, methodology): “[25] extracted trajectories through pairwise Scale Invariant Feature Transform (SIFT) correspondences between two consecutive frames.”
Effective 3D action recognition using EigenJoints (2014, methodology): “Trajectory-based approaches have been widely explored for recognizing human activities as well [5,12,22].”
High-level event recognition in unconstrained videos (2012, methodology): “[132] also applied KLT to track DoG-SIFT key-points.”
Better Exploiting Motion for Better Action Recognition (2013, background): “More recent techniques assume some underlying temporal motion model involving trajectories [2, 6, 7, 17, 18, 25, 29, 32].”
Real-Time Gesture Recognition from Depth Data through Key Poses Learning and Decision Forests (2012, methodology): “This approach has attracted a lot of attention in the past few years [5], [6], [7], [8] and an example of largely used local feature is the SpaceTime Interest Point (STIP) presented by Laptev and Lindeberg [9].”
Learning latent spatio-temporal compositional model for human action recognition (2013, background): “Some researchers proposed to enrich the action model with the appearance information or context information [40, 34].”
Dense Trajectories and Motion Boundary Descriptors for Action Recognition (2013, unknown): “Some recent methods (Matikainen et al, 2009; Messing et al, 2009; Sun et al, 2009, 2010) show good results for action recognition by leveraging the motion information of trajectories.”
Activity recognition using the velocity histories of tracked keypoints (2009, methodology): “[22] recently used similar techniques to model SIFT-feature trajectories.”
Accurate and real-time human action recognition based on 3D skeleton (2013, methodology): “[10] proposes a method to extract view-invariant features from body joints, while [11] uses a three-layer model to represent motion precisely.”