Learning Maximum Margin Temporal Warping for Action Recognition

By Jiang Wang, Ying Wu. 2013

70 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

Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos (2016, background): “Recent single modality action recognition methods on depth signals can be divided into two major groups: depth map analysis methods [35, 41, 45, 79] and skeleton based methods [36, 65, 11, 73, 74].”
Multimodal Multipart Learning for Action Recognition in Depth Videos (2015, neutral): “This way (8) will be expanded to:”
3D Human Activity Recognition with Reconfigurable Convolutional Neural Networks (2014, background): “For example, Wang and Wu [31] proposed to solve the temporal alignment of actions by maximum margin temporal warping.”
Skeleton-Based Human Action Recognition With Global Context-Aware Attention LSTM Networks (2017, neutral): “nition have been proposed [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41].”
Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates (2017, neutral): “re presented in section 4. Finally, the paper is concluded in section 5. 2. Related Work Skeleton-based action recognition has been explored in different aspects during recent years [33], [34], [35], [36], [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47]. In this section, we limit ou”
3D skeleton-based human action classification: A survey (2016, background): “In [140] action alignment and classi ﬁ cation are solved together by means of maximum margin temporal warping (MMTW), which learns temporal action alignment for max-margin classi ﬁ cation.”
Global Context-Aware Attention LSTM Networks for 3D Action Recognition (2017, background): “Various feature extractors and classifier learning methods for 3D action recognition have been proposed in the past few years [28, 37, 31, 65, 54, 26, 34, 5, 47, 59, 38, 56, 32, 2].”
A Deep Structured Model with Radius–Margin Bound for 3D Human Activity Recognition (2015, background): “For example, Wang and Wu [43] proposed to solve the temporal alignment of actions by maximum margin temporal warping.”
A discussion on the validation tests employed to compare human action recognition methods using the MSR Action3D dataset (2014, result): “Many works have compared their results with Li et al. and most of them used ten subjects [5,21,22].”
Spectral Graph Skeletons for 3D Action Recognition (2014, methodology): “Our method falls just short of MMTW [30], but it should be noted that while MMTW discriminatively learns a non-uniform warping of the time axis, our method works with a mere uniform division of the action sequence due to our temporal pyramid pooling scheme.”
Efficient Pose-Based Action Recognition (2014, methodology): “It performs comparable to the state-of-the-art [33] and performs better than most other skeleton-based approaches.”
Rolling Rotations for Recognizing Human Actions from 3D Skeletal Data (2016, background): “Joint-based approaches consider human skeleton as a set of points, and represent it using features like joint positions [5, 8, 9, 13, 16, 21, 26], joint orientations in a fixed coordinate system [24, 37, 32, 22], pairwise relative joint positions [34, 35, 36, 39], etc.”
Enhanced Sequence Matching for Action Recognition from 3D Skeletal Data (2014, methodology): “70 Maximum Margin Temporal Warping(MMTW) [25] 92.”
3D human action segmentation and recognition using pose kinetic energy (2014, unknown): “9 MMTW [36] Yes 92.”