• Home
  • Search
  • Cross-View Action Recognition Over Heterogeneous Feature Spaces.
  • Open Access IconOpen Access
  • Cite Icon25
  • https://doi.org/10.1109/tip.2015.2445293Copy DOI Icon

Cross-View Action Recognition Over Heterogeneous Feature Spaces.

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

In cross-view action recognition, what you saw in one view is different from what you recognize in another view, since the data distribution even the feature space can change from one view to another. In this paper, we address the problem of transferring action models learned in one view (source view) to another different view (target view), where action instances from these two views are represented by heterogeneous features. A novel learning method, called heterogeneous transfer discriminant-analysis of canonical correlations (HTDCC), is proposed to discover a discriminative common feature space for linking source view and target view to transfer knowledge between them. Two projection matrices are learned to, respectively, map data from the source view and the target view into a common feature space via simultaneously minimizing the canonical correlations of interclass training data, maximizing the canonical correlations of intraclass training data, and reducing the data distribution mismatch between the source and target views in the common feature space. In our method, the source view and the target view neither share any common features nor have any corresponding action instances. Moreover, our HTDCC method is capable of handling only a few or even no labeled samples available in the target view, and can also be easily extended to the situation of multiple source views. We additionally propose a weighting learning framework for multiple source views adaptation to effectively leverage action knowledge learned from multiple source views for the recognition task in the target view. Under this framework, different source views are assigned different weights according to their different relevances to the target view. Each weight represents how contributive the corresponding source view is to the target view. Extensive experiments on the IXMAS data set demonstrate the effectiveness of HTDCC on learning the common feature space for heterogeneous cross-view action recognition. In addition, the weighting learning framework can achieve promising results on automatically adapting multiple transferred source-view knowledge to the target view.

Similar Papers
  • Conference Article
  • Citations78

Cross-View Action Recognition over Heterogeneous Feature Spaces

  • Dec 01, 2013
  • Xinxiao Wu +3
  • Book Chapter
  • Citations2

Heterogeneous Discriminant Analysis for Cross-View Action Recognition

  • Jan 01, 2015
  • Wanchen Sui +4
  • Research Article
  • Citations13

Heterogeneous discriminant analysis for cross-view action recognition

  • Feb 18, 2016
  • Neurocomputing
  • Wanchen Sui +3
  • Research Article
  • Citations6

Pan-sharpening using 2D CCA

  • Apr 28, 2015
  • Remote Sensing Letters
  • Songze Tang +4
  • Research Article
  • Citations21

An Adaptive Multi-Projection Metric Learning for Person Re-Identification Across Non-Overlapping Cameras

  • Sep 01, 2019
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Hai-Miao Hu +3
  • Conference Article
  • Citations30

Multistream Classification for Cyber Threat Data with Heterogeneous Feature Space

  • May 13, 2019
  • Yi-Fan Li +5
  • Research Article
  • Citations4

Partial least-squares regression on common feature space for single image superresolution

  • Sep 18, 2014
  • Journal of Electronic Imaging
  • Songze Tang +3
  • Research Article
  • Citations1

Fusing Time-Frequency Heterogeneous Features With Cross-Attention Mechanism for Pathological Voice Detection.

  • Oct 01, 2025
  • Journal of voice : official journal of the Voice Foundation
  • Zhang Jiaqing +2
  • Dissertation

Cross-view action recognition via joint dictionary and transfer learning

  • Jan 01, 2019
  • Deepak Kumar
  • Research Article
  • Citations23

Cross-view action recognition by cross-domain learning

  • Apr 30, 2016
  • Image and Vision Computing
  • Weizhi Nie +3
  • Conference Article
  • Citations17

Heterogeneous Multi-task Semantic Feature Learning for Classification

  • Oct 17, 2015
  • Xin Jin +5
  • Conference Article
  • Citations72

MSO: Multi-Feature Space Joint Optimization Network for RGB-Infrared Person Re-Identification

  • Oct 17, 2021
  • Yajun Gao +6
  • Research Article
  • Citations11

Batch Mode Query by Committee for Motor Imagery-Based BCI.

  • Nov 28, 2018
  • IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society
  • Ibrahim Hossain +3
  • Conference Article
  • Citations4

Discriminative Latent Feature Space Learning for Cross-Modal Retrieval

  • Jun 22, 2015
  • Xu Tang +2
  • Conference Article

Event Data Mining and Classification from Multiple Streaming Sources

  • Dec 01, 2010
  • Ashit Talukder
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.