• Home
  • Search
  • Discriminative Relational Representation Learning for RGB-D Action Recognition.
  • Cite Icon30
  • https://doi.org/10.1109/tip.2016.2556940Copy DOI Icon

Discriminative Relational Representation Learning for RGB-D Action Recognition.

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

This paper addresses the problem of recognizing human actions from RGB-D videos. A discriminative relational feature learning method is proposed for fusing heterogeneous RGB and depth modalities, and classifying the actions in RGB-D sequences. Our method factorizes the feature matrix of each modality, and enforces the same semantics for them in order to learn shared features from multimodal data. This allows us to capture the complex correlations between the two modalities. To improve the discriminative power of the relational features, we introduce a hinge loss to measure the classification accuracy when the features are employed for classification. This essentially performs supervised factorization, and learns discriminative features that are optimized for classification. We formulate the recognition task within a maximum margin framework, and solve the formulation using a coordinate descent algorithm. The proposed method is extensively evaluated on two public RGB-D action data sets. We demonstrate that the proposed method can learn extremely low-dimensional features with superior discriminative power, and outperforms the state-of-the-art methods. It also achieves high performance when one modality is missing in testing or training.

Similar Papers
  • Research Article

Learning discriminative relational features for sequence labeling

  • Feb 28, 2017
  • arXiv: Learning
  • Naveen Nair
  • Conference Article
  • Citations2

Learning Discriminative Features with Region Attention and Refinement Network for Facial Expression Recognition in the Wild

  • Aug 21, 2022
  • Xiao Li +4
  • Research Article
  • Citations255

Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation

  • Jul 17, 2019
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Chao Chen +3
  • Conference Article
  • Citations5

Face Alignment by Discriminative Feature Learning

  • Sep 01, 2019
  • Weiliang Chen +2
  • Research Article
  • Citations77

Improving dense conditional random field for retinal vessel segmentation by discriminative feature learning and thin-vessel enhancement

  • Jun 24, 2017
  • Computer Methods and Programs in Biomedicine
  • Lei Zhou +4
  • PDF
  • Research Article
  • Citations10

Spectral–Spatial Discriminant Feature Learning for Hyperspectral Image Classification

  • Jun 29, 2019
  • Remote Sensing
  • Chunhua Dong +3
  • Research Article
  • Citations1

Discriminative supplementary representation learning for novel-category classification

  • Jul 25, 2019
  • Neurocomputing
  • Qiuli Liu +2
  • Research Article
  • Citations7

Learning informative and discriminative semantic features for robust facial expression recognition

  • Jan 23, 2024
  • Journal of Visual Communication and Image Representation
  • Yumei Tan +2
  • Research Article
  • Citations12

Max-Margin-Based Discriminative Feature Learning.

  • Feb 03, 2016
  • IEEE Transactions on Neural Networks and Learning Systems
  • Changsheng Li +5
  • PDF
  • Research Article
  • Citations72

Discriminative Learning for Alzheimer's Disease Diagnosis via Canonical Correlation Analysis and Multimodal Fusion

  • May 17, 2016
  • Frontiers in Aging Neuroscience
  • Baiying Lei +3
  • Research Article
  • Citations2

Discriminative feature learning for underwater fish recognition

  • Apr 12, 2021
  • Journal of Electronic Imaging
  • Zhixue Zhang +5
  • Book Chapter
  • Citations1

A Classification Algorithm Based on Discriminative Transfer Feature Learning for Early Diagnosis of Alzheimer’s Disease

  • Jan 01, 2022
  • Xinchun Cui +9
  • Research Article
  • Citations24

Multi-Task and Multi-Modal Learning for RGB Dynamic Gesture Recognition

  • Dec 01, 2021
  • IEEE Sensors Journal
  • Dinghao Fan +3
  • Research Article
  • Citations24

Worst-Case Discriminative Feature Learning via Max-Min Ratio Analysis.

  • Jan 01, 2024
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Zheng Wang +4
  • Research Article

Piece-wise max-margin-based discriminative feature learning

  • Oct 11, 2019
  • Journal of Experimental & Theoretical Artificial Intelligence
  • Yahya Forghani +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.