Multi-modal feature fusion for action recognition in RGB-D sequences

By Amir Shahroudy, G. Wang, Tian-Tsong Ng. 2014

51 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Multimodal Learning, Signal Processing

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 Multimodal Learning

In Signal Processing

Citations in the corpus

NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis (2016, methodology): “A structured sparsity based multimodal feature fusion technique was introduced by [33] for action recognition in RGB+D domain.”
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (2019, methodology): “A structured sparsity-based multi-modal feature fusion technique was introduced by [57] for action recognition in RGB+D domain.”
Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos (2016, background): “The work of [55] proposed a structured sparsity based fusion for RGB+D local descriptors.”
Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, methodology): “[196] recently developed a multi-modal feature learning method to fuse the RGB-D and skeletal information into an integrated set of discriminative features.”
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): “Skeleton-based action recognition has been explored in different aspects in recent years [40], [41], [42], [43], [44], [45], [46], [47], [48], [49], [50], [51], [52], [53], [54], [55], [56], [57].”
3D Action Recognition from Novel Viewpoints (2016, methodology): “Many methods [23, 31, 34, 36–38, 44, 47, 48, 55–57, 63, 67, 68, 74] have been proposed which achieve impressive action recognition results when videos are acquired from a common viewpoint.”
Human Action Recognition From Various Data Modalities: A Review (2020, methodology): “Meanwhile, early fusion [52], [364] is generally feature-based, and it combines the features of different modalities to yield aggregated features that are often very discriminative and powerful and can then be used for HAR.”
Jointly Learning Heterogeneous Features for RGB-D Activity Recognition (2015, methodology): “[30] selected to fuse the RGB information and skeleton cues using a structured sparsity method; [5] simply concatenated the skeleton features and silhouette-based features together for classification.”
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].”
Learning a Deep Model for Human Action Recognition from Novel Viewpoints (2016, methodology): “To overcome this problem, some techniques infer 3D scene structure and use geometric transformations to achieve view invariance [3], [24], [25], [26], [27], [28], [29], [30], [31], [32].”