Papers › Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition
Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition
Kai Wang, Xiaojiang Peng, Jianfei Yang, Debin Meng, Yu Qiao
Occlusion and pose variations, which can change facial appearance significantly, are two major obstacles for automatic Facial Expression Recognition (FER). Though automatic FER has made substantial progresses in the past few decades, occlusion-robust and pose-invariant issues of FER have received relatively less attention, especially in real-world scenarios. This paper addresses the real-world pose and occlusion robust FER problem with three-fold contributions. First, to stimulate the research of FER under real-world occlusions and variant poses, we build several in-the-wild facial expression datasets with manual annotations for the community. Second, we propose a novel Region Attention Network (RAN), to adaptively capture the importance of facial regions for occlusion and pose variant FER. The RAN aggregates and embeds varied number of region features produced by a backbone convolutional neural network into a compact fixed-length representation. Last, inspired by the fact that facial expressions are mainly defined by facial action units, we propose a region biased loss to encourage high attention weights for the most important regions. We validate our RAN and region biased loss on both our built test datasets and four popular datasets: FERPlus, AffectNet, RAF-DB, and SFEW. Extensive experiments show that our RAN and region biased loss largely improve the performance of FER with occlusion and variant pose. Our method also achieves state-of-the-art results on FERPlus, AffectNet, RAF-DB, and SFEW. Code and the collected test data will be publicly available.
In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Facial Expression Recognition (FER) | AffectNet | RAN (ResNet-18+) | Accuracy (7 emotion) | - | #29 of 50 | Archive leaderboard | report |
| Facial Expression Recognition (FER) | AffectNet | RAN (ResNet-18+) | Accuracy (8 emotion) | 59.5 | #29 of 50 | Archive leaderboard | report |
| Facial Expression Recognition (FER) | FERPlus | RAN (VGG-16) | Accuracy(pretrained) | 89.16 | #2 of 4 | Archive leaderboard | report |
| Facial Expression Recognition (FER) | RAF-DB | RAN (ResNet-18) | Overall Accuracy | 86.9 | #29 of 35 | Archive leaderboard | report |
| Facial Expression Recognition (FER) | SFEW | RAN (VGG16+ResNet18) | Accuracy | 56.4 | #2 of 4 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections