Cross-Domain Facial Expression Recognition
4 papers with code • 2 benchmarks • 0 datasets
Cross-domain Facial Expression Recognition (CD-FER) aims to transfer the ability of recognizing facial expression from the source domain to the target domain, when only the training images of the target domain is available (i.e., the annotation of traget domain is missing).
Benchmarks
These leaderboards are used to track progress in Cross-Domain Facial Expression Recognition
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
Most implemented papers
Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning
HCPLab-SYSU/CD-FER-Benchmark
•
•
Although each declares to achieve superior performance, fair comparisons are lacking due to the inconsistent choices of the source/target datasets and feature extractors.
Adversarial Graph Representation Adaptation for Cross-Domain Facial Expression Recognition
HCPLab-SYSU/CD-FER-Benchmark
•
•
However, most of these works focus on holistic feature adaptation, and they ignore local features that are more transferable across different datasets.
Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition
altndrr/clup
•
•
Automatically understanding emotions from visual data is a fundamental task for human behaviour understanding.
Adaptive Global-Local Representation Learning and Selection for Cross-Domain Facial Expression Recognition
Specifically, the framework consists of separate global-local adversarial learning modules that learn domain-invariant global and local features independently.
