Expandable Data-Driven Graphical Modeling of Human Actions Based on Salient Postures

By Wanqing Li, Zhengyou Zhang, Zicheng Liu. 2008

168 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

A novel hierarchical framework for human action recognition (2016, methodology): “Many classification methods have been introduced to action recognition, 207 among which action graphs [26] are an effective method to explicitly model 208 the action dynamics.”
Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification (2015, neutral): “For instance, Li et al. proposed to replace the hidden states in HMMs with visualizable salient poses estimated by Gaussian Mixture Models [24], and Tang et al. introduced latent variables over video frames to discover the most discriminative states of an event based on a variable duration HMM [39].”
High-level event recognition in unconstrained videos (2012, unknown): “[71] introduced an interesting methodology to model”
Dynamic Eye Movement Datasets and Learnt Saliency Models for Visual Action Recognition (2012, background): “In contrast, in the field of ‘pure’ computer vision, interest point detectors have been successfully used in the bag-of-visual-words framework for action classification[6, 1, 7, 22], but a variety of other methods exists, including random field models[23].”
Real-time human action recognition based on depth motion maps (2013, methodology): “In [9], the bi-gram maximum likelihood decoding (BMLD) for Gaussian Mixture Model (GMM) was adopted to mitigate the computational complexity with the complexity of O(J×KhD 2 ) [28], where J denotes the number of iterations, Kh the number of samples in the dataset and D the dimensionality of the stat”
Mining Mid-Level Features for Action Recognition Based on Effective Skeleton Representation (2014, methodology): “Regardless of the input source, there are two main approaches, space-time approach and sequential approach [5], [6], [7], to the representation of actions.”
A Survey on Human Motion Analysis from Depth Data (2013, methodology): “The authors employed the concept of bag-of-points in the expandable graphical model framework to construct the action graph [12] to encode the actions.”
Real-Time Gesture Recognition from Depth Data through Key Poses Learning and Decision Forests (2012, methodology): “The methods in the second category use global features such as silhouettes [2], [11], [12] and template based approaches [13], [14], where spatial context information are preserved.”
3D Activity Recognition Using Motion History and Binary Shape Templates (2014, background): “Such techniques can be typically categorized into local descriptor [1], [2], [3] and global descriptor-based [4], [5], [6] approaches.”
Action Recognition From Depth Maps Using Deep Convolutional Neural Networks (2016, background): “[2] sampled points from a depth map to obtain a bag of 3-D points to encode spatial information and employ an expandable graphical model to encode temporal information [18].”
A real time system for dynamic hand gesture recognition with a depth sensor (2012, methodology): “With the depth information, a skeleton tracking system has been developed by Microsoft.”
Video-Based Human Behavior Understanding: A Survey (2013, background): “[20], [128], [129], which represent the human body in terms”
Large-scale Isolated Gesture Recognition using Convolutional Neural Networks (2016, background): “Li et al. [2] sampled points from a depth map to obtain a bag of 3D points to encode spatial information and employ an expandable graphical model to encode temporal information [25].”
Action recognition based on a bag of 3D points (2010, methodology): “[9, 8] proposed to cluster all training poses (frames) into M clusters, each cluster representing a salient posture.”