The Recognition of Human Movement Using Temporal Templates

By Aaron F. Bobick, James W. Davis. 2001

3,135 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks (2017, background): “There are several ways to encode the video sequences into dynamic images [2, 25, 60, 51, 52, 1], but how to encode the scene flow vectors into one dynamic image still needs to be explored.”
Action bank: A high-level representation of activity in video (2012, methodology): “Later methods avoid the explicit computation of optical flow due to its complexity and limitations: Bobick and Davis [3] compute a two-vector of motion presence and”
View-invariant action recognition using fundamental ratios (2008, methodology): “Existing methods for action recognition such as [2, 17] consider an action as a whole, which usually requires known start and end frames and is limited when action execution rate varies.”
Multitype Activity Recognition in Robot-Centric Scenarios (2015, methodology): “Inspired by the well-known Motion History Image (MHI) [23], we embed the temporal information in our descriptor computing a series of temporal differences.”
The TUM Kitchen Data Set of everyday manipulation activities for motion tracking and action recognition (2009, background): “Holistic approaches [7, 15, 5] try to find a direct mapping between observable image cues and action labels, usually by training discriminative classifiers such as Support Vector Machines [15].”
Non-intrusive human activity monitoring in a smart home environment (2013, background): “Many of these algorithms are based on analyzing human silhouettes , tr ating them as three-dimensional (3D) objects (space-time) and using 3D object recognition techniques to classify human actions [10], [11].”
EigenJoints-based action recognition using Naïve-Bayes-Nearest-Neighbor (2012, background): “In order to compute accurate similarity measurement, a variety of spatio-temporal volume detection and representation approaches have been proposed [2] [4] [5] [6] [7].”
Going deeper into action recognition: A survey (2016, background): “Bobick and Davis (2001).”
Machine Recognition of Human Activities: A Survey (2008, background): “Bobick and Davis [34], [35] proposed ‘temporal templates’ as models for actions.”
Detecting Human Actions in Surveillance Videos (2009, methodology): “One system employs the brute force search method to test each space-time location in the video by a binary classifier on whether a specific event occurs.”
Learning to Recognize Activities from the Wrong View Point (2008, background): “At higher resolutions, appearance features include: braids [27]; characteristic spatio-temporal volumes [7]; motion energy images [9]; motion history images [9]; spatio-temporal interest points [23]; nonlinear dimensionality reduced stacks of silhouettes [38]; an extended radon transform [40]; and s”
Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words (2008, methodology): “Bobick and Davis (2001) use motion history images that capture motion and shape to represent actions .”
Slow Feature Analysis for Human Action Recognition (2012, methodology): “The detected local features preserve some translation/rotation invariance, which is desirable for the subsequent action recognition.”
Depth Induced Feature Representation for 4D Human Activity Recognition (2014, methodology): “Roughly, we divide activity recognition techniques into four categories, Bag-ofFeatures/SVM (BoF/SVM) approaches [17], Deformable Part Models (DPM) approaches[39], silhouette representation [3], [5], [14], [22], feature trajectories [38], [21], [23], [31].”