Research map / Video / Video segmentation and tracking
FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add LSTM temporal modeling to the VGG13 2D ConvNet | VGG13 on FERV39k · FERV39k, all scenes | WAR: 41.02 -> 43.37 | Helped |
| Add scene-context stream to I3D (ablation) | I3D on FERV39k · FERV39k, all scenes | WAR: 38.78 -> 41.30 | Helped |
| Pretrain on MS-Celeb-1M or DFEW before FERV39k training (ablation) | RS18-LSTM and RS50-LSTM · FERV39k | performance | No clear effect |
| Increase the number of sampled frames from 2 to 16 (ablation) | Four 2D ConvNet-LSTM networks · FERV39k | performance | Mixed |
| Add scene-context stream to face-only I3D (ablation) | I3D on FERV39k · Selected scenes across the four scenarios | performance | Helped |
| Use a two-stream 2D ConvNet-LSTM instead of a one-stream 2D ConvNet-LSTM | DFER on FERV39k · FERV39k, all scenes | WAR: 43.37 -> 44.54 | Helped |
| Evaluate on FERV39k rather than DFEW | Three baseline architectures · FERV39k versus DFEW | average performance: about 10\% | Hurt |
Closest papers by meaning
- Open-Set Facial Expression Recognition (AAAI 2024 · similarity 0.89)
- FAIR-FER: A Latent Alignment Approach for Mitigating Bias in Facial Expression Recognition (Student Abstract) (AAAI 2024 · similarity 0.87)
- OUS: Bridging Scene Context and Facial Features to Overcome the Rigid Cognitive Problem (AAAI 2025 · similarity 0.87)
- Multi-Energy Guided Image Translation with Stochastic Differential Equations for Near-Infrared Facial Expression Recognition (AAAI 2024 · similarity 0.86)
- Facial-R1: Aligning Reasoning and Recognition for Facial Emotion Analysis (AAAI 2026 · similarity 0.86)
- Navigating Label Ambiguity for Facial Expression Recognition in the Wild (AAAI 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.