Making Action Recognition Robust to Occlusions and Viewpoint Changes

By Daniel Weinland, Mustafa Özuysal, Pascal Fua. 2010

263 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering

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 Control and Systems Engineering

Citations in the corpus

View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data (2017, background): “One category of approaches requires multiple view videos for training [15, 8, 41, 44, 25].”
Action Classification with Locality-Constrained Linear Coding (2014, background): “Most of the previous approaches to action recognition have focused on using traditional RGB cameras [1]–[3].”
Action Recognition with Exemplar Based 2.5D Graph Matching (2012, background): “View-invariant feature descriptors have also been proposed [14, 15].”
View Adaptive Neural Networks for High Performance Skeleton-Based Human Action Recognition (2018, methodology): “Some attempts have been made in previous works to overcome the view variation problem for robust action recognition [3], [8], [9], [14], [15], [19], [24], [26], [31], [36], [37], [39], [40], [50], [52], [53], [60].”
The Action Similarity Labeling Challenge (2012, background): “This was usually done for specific purposes, such as studying viewing variations [10], occlusions [25], or recognizing daily actions in static scenes [14].”
Cross-View Action Recognition via Transferable Dictionary Learning (2016, methodology): “also developed a robust and viewinvariant hierarchical classification method based on 3D HOG to represent a test sequence [44].”
Learning View-Invariant Sparse Representations for Cross-View Action Recognition (2013, methodology): “[29] developed a robust and view-invariant hierarchical classification method based on 3D HOG to represent a test sequence.”
An efficient part-based approach to action recognition from RGB-D video with BoW-pyramid representation (2013, methodology): “Then, we classify the extracted features into different parts and organize them into BoW-Pyramid to represent an action for each part.”
View-Invariant Action Recognition Using Latent Kernelized Structural SVM (2012, methodology): “Compared with the methods [31] [8] [10], our method significantly improves the recognition performance in all five views with the same experimental setting.”
View-Invariant 3D Action Recognition Using Spatiotemporal Self-Similarities from Depth Camera (2014, background): “The problem of viewpoint change is a challenging issue in human action tracking and recognition tasks [3]–[6].”
Structured Time Series Analysis for Human Action Segmentation and Recognition (2014, methodology): “1 could be offline optimized by dynamic programming when Nc is given, which is out of the scope of this paper.”
Latent Multitask Learning for View-Invariant Action Recognition (2013, methodology): “We evaluate our approach on three benchmark datasets including: the IXMAS dataset [25], the newer version of IXMAS dataset [24] referred to as IXMAS(new), and the i3DPost multiview human action dataset [6].”
Dynamic Manifold Warping for view invariant action recognition (2011, methodology): “Under the STM model, we propose a novel approach Dynamic Manifold Warping (DMW), which aligns two multivariate time series with intrinsic manifold structure and provides a robust motion similarity score.”
Cross-view action recognition via view knowledge transfer (2011, background): “Our performance is better than that of [19] and [16], and competitive to [35].”