• Home
  • Search
  • Heterogeneous domain adaptation method for video annotation
  • Cite Icon9
  • https://doi.org/10.1049/iet-cvi.2016.0148Copy DOI Icon

Heterogeneous domain adaptation method for video annotation

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

In this study, the authors study the video annotation problem over heterogeneous domains, in which data from the image source domain and the video target domain is represented by heterogeneous features with different dimensions and physical meanings. A novel feature learning method, called heterogeneous discriminative analysis of canonical correlation (HDCC), is proposed to discover a common feature subspace in which heterogeneous features can be compared. The HDCC utilises discriminative information from the source domain as well as topology information from the target domain to learn two different projection matrices. By using these two matrices, heterogeneous data can be projected onto a common subspace and different features can be compared. They additionally design a group weighting learning framework for multi‐domain adaptation to effectively leverage knowledge learned from the source domain. Under this framework, source domain images are organised in groups according to their semantic meanings, and different weights are assigned to these groups according to their relevancies to the target domain videos. Extensive experiments on the Columbia Consumer Video and Kodak datasets demonstrate the effectiveness of their HDCC and group weighting methods.

Similar Papers
  • Research Article
  • Citations108

Domain Adaptation for Face Recognition: Targetize Source Domain Bridged by Common Subspace

  • Dec 31, 2013
  • International Journal of Computer Vision
  • Meina Kan +3
  • Conference Article
  • Citations6

Multi-source Domain Adaptation for Face Recognition

  • Aug 01, 2018
  • Haiyang Yi +3
  • Conference Article
  • Citations1

Incremental Discriminant Learning for Heterogeneous Domain Adaptation

  • Nov 01, 2015
  • Peng Han +1
  • Research Article
  • Citations157

Heterogeneous Domain Adaptation: An Unsupervised Approach.

  • Nov 30, 2020
  • IEEE Transactions on Neural Networks and Learning Systems
  • Feng Liu +2
  • Research Article
  • Citations29

A New Belief-Based Bidirectional Transfer Classification Method.

  • Aug 01, 2022
  • IEEE Transactions on Cybernetics
  • Zhun-Ga Liu +4
  • Research Article
  • Citations32

Heterogeneous Multidomain Recommender System Through Adversarial Learning.

  • Nov 01, 2023
  • IEEE Transactions on Neural Networks and Learning Systems
  • Wenhui Liao +4
  • Research Article
  • Citations503

Learning With Augmented Features for Supervised and Semi-Supervised Heterogeneous Domain Adaptation.

  • Jun 01, 2014
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Wen Li +3
  • Conference Article
  • Citations5

Deep Domain Adaptation based Cloud Type Detection using Active and Passive Satellite Data

  • Dec 10, 2020
  • Xin Huang +6
  • Conference Article
  • Citations3

Towards Adaptive Semantic Segmentation By Progressive Feature Refinement

  • Oct 01, 2020
  • Bin Zhang +2
  • Research Article
  • Citations2

Multi-Modal MR Image Segmentation Strategy for Brain Tumors Based on Domain Adaptation

  • Dec 19, 2024
  • Computers
  • Qihong Yang +2
  • PDF
  • Research Article

Learning Transferable Convolutional Proxy by SMI-Based Matching Technique

  • Oct 14, 2020
  • Shock and Vibration
  • Wei Jin +1
  • Research Article
  • Citations45

Structure preservation and distribution alignment in discriminative transfer subspace learning

  • Feb 01, 2019
  • Neurocomputing
  • Ting Xiao +4
  • Research Article
  • Citations9

Sample selection for visual domain adaptation via sparse coding

  • Apr 02, 2016
  • Signal Processing: Image Communication
  • Xiao Li +3
  • Research Article
  • Citations35

Unsupervised domain adaptation with self-attention for post-disaster building damage detection

  • Jul 14, 2020
  • Neurocomputing
  • Yundong Li +5
  • Research Article
  • Citations32

Attention Multisource Fusion-Based Deep Few-Shot Learning for Hyperspectral Image Classification

  • Jan 01, 2021
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Xuejian Liang +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.