Action Recognition with Exemplar Based 2.5D Graph Matching

By Bangpeng Yao, Li Fei-Fei. 2012

114 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): “is the most widely studied displacement feature for human representation [121] [129] [130] [132] [136] [138].”
Cross-View Action Modeling, Learning, and Recognition (2014, background): “[22] estimates the 2D poses from the images, and matches the estimated poses with a set of representative poses.”
Fast Exact Hyper-graph Matching with Dynamic Programming for Spatio-temporal Data (2014, unknown): “In [55], Yao and Fei-Fei structure salient points on the human body, namely skeletal joints, into a graph.”
Patch to the Future: Unsupervised Visual Prediction (2014, background): “While prediction has been extensively studied in the realm of biological vision [1], in the field of computational vision, most of the research focus has been on understanding and inferring semantic [7, 27, 32] and geometric [10, 14] knowledge of what can be seen in an image or a video.”
A survey on still image based human action recognition (2014, methodology): “…detectors to determine the occurrence of individual objects for action recognition [25,36,30,38], some works integrate objects with the scene as context, e.g., Zheng et al. [43] learned context-based classifiers, which uses image content from both the foreground and the background as the context.”
Exploring discriminative pose sub-patterns for effective action classification (2013, background): “Most of the action classification works focus on recognizing actions using visual appearance features extracted from videos [14, 27, 23] or still images [32, 22, 34].”
Zero-Shot Learning via Visual Abstraction (2014, background): “Pose Estimation and Action Recognition: Automatically estimating human pose [2, 27] and recognizing human actions [1, 28] in images has received a lot of attention in the vision community.”
Watching Unlabeled Video Helps Learn New Human Actions from Very Few Labeled Snapshots (2013, methodology): “While researchers have trained activity models from video data for many years, there is increasing interest in methods that can learn an action category from static image snapshots [17, 33, 34, 7, 36, 35].”
A Discriminative Model with Multiple Temporal Scales for Action Prediction (2014, unknown): “In addition, recognizing human actions from a set of keyframes [12,22] and static images [25,24] have also been investigated in previous studies.”
Jointly Learning Heterogeneous Features for RGB-D Activity Recognition (2015, background): “Human pose and its dynamics are one of the key elements in activities [10], [49].”