A survey of vision-based methods for action representation, segmentation and recognition

By Daniel Weinland, Rémi Ronfard, Edmond Boyer. 2011

1,099 citations recorded by the source corpus.

Subfields: Biomedical Engineering, 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 Biomedical Engineering

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Co-Occurrence Feature Learning for Skeleton Based Action Recognition Using Regularized Deep LSTM Networks (2016, background): “It facilitates a wide range of applications such as intelligent video surveillance, human-computer interaction, and video understanding (Poppe 2010; Weinland, Ronfard, and Boyerc 2011).”
Histogram of Oriented Principal Components for Cross-View Action Recognition (2014, background): “Since HOPC and STK-Distribution capture complimentary information, their combination significantly improves classification accuracy which is over 22% higher than the nearest competitor on both datasets.”
Interpretable 3D Human Action Analysis with Temporal Convolutional Networks (2017, background): “Applications of human activity recognition ranges from video surveillance, humancomputer interaction, robotics and skill evaluation [2, 35].”
Finding action tubes (2014, background): “We refer to [1, 30, 43] for recent surveys in the field.”
Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos (2015, background): “Thorough surveys of the literature include Poppe [27] and Weinland et al. [48].”
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data (2016, background): “One general approach focuses on the recognition from RGB videos (Weinland, Ronfard, and Boyerc 2011).”
End-to-End Learning of Action Detection from Frame Glimpses in Videos (2015, neutral): “The model is formulated as a reinforcement learning agent that interacts with a video over time.”
Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networks (2016, background): “For human action recognition and detection, many research works have been designed for RGB videos recorded by 2D cameras in the past couple of decades [1].”
Hierarchical Deep Temporal Models for Group Activity Recognition (2016, background): “f the approach, and end in Section 5 with a conclusion of this work. 2 RELATED WORK Human activity recognition is an active area of research, with many existing algorithms. Surveys by Weinland et al. [14] and Poppe [15] explore the vast literature in activity recognition. Here, we will focus on the ”
A Hierarchical Pose-Based Approach to Complex Action Understanding Using Dictionaries of Actionlets and Motion Poselets (2016, background): “There is a large body of work on human activity recognition in the computer vision literature [1, 21, 29, 36].”
See No Evil, Say No Evil: Description Generation from Densely Labeled Images (2014, background): “Activity recognition is an emerging area in images (Li and Fei-Fei, 2007; Yao et al., 2011; Sharma et al., 2013) and video (Weinland et al., 2011), although less studied than object recognition.”
Self-organizing neural integration of pose-motion features for human action recognition (2015, background): “Moreover, an enduring bottleneck for vision-based approaches regards the segmentation of human shape and motion from 2D image sequences, often constrained in terms of computational eﬃciency and robustness to illumination changes (Weinland et al., 2011).”
Asynchronous Temporal Fields for Action Recognition (2016, background): “Understanding activities and actions has an extensive history [32, 59, 22, 17, 23, 2, 26, 56, 29, 21].”
A survey on activity recognition and behavior understanding in video surveillance (2013, background): “Daniel 11 A survey of vision-based methods for action representation, segmentation and recognition [204]”
Fusing Spatiotemporal Features and Joints for 3D Action Recognition (2013, background): “In the past decades, many approaches have been proposed to solve the action recognition problem on the visible light or RGB video sequences [19] [1] [24].”
Accurate 3D action recognition using learning on the Grassmann manifold (2015, neutral): “Recent surveys can be found in the work of Aggarwal et al. [12], Weinland et al. [13], and Poppe [4].”