Research map / Video / Action recognition
MIMAMO Net: Integrating Micro- and Macro-Motion for Video Emotion Recognition
Didan Deng, Zhaokang Chen, Yuqian Zhou, Bertram Shi
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Combine spatial ResNet50 features with the phase-difference temporal stream (ablation) | MIMAMO Net · OMG | Arousal CCC: 0.312 -> 0.377 | Improved |
| Combine spatial ResNet50 features with the phase-difference temporal stream (ablation) | MIMAMO Net · OMG | Valence CCC: 0.508 -> 0.529 | Improved |
| Combine spatial ResNet50 features with the phase-difference temporal stream (ablation) | MIMAMO Net · Aff-Wild | Arousal CCC: 0.411 -> 0.521 | Improved |
| Combine spatial ResNet50 features with the phase-difference temporal stream (ablation) | MIMAMO Net · Aff-Wild | Valence CCC: 0.514 -> 0.580 | Improved |
| Use phase differences instead of optical flow in the temporal stream (ablation) | MIMAMO Net · OMG | Arousal CCC: 0.364 -> 0.377 | Improved |
| Use phase differences instead of optical flow in the temporal stream (ablation) | MIMAMO Net · OMG | Valence CCC: 0.512 -> 0.529 | Improved |
| Use phase differences instead of optical flow in the temporal stream (ablation) | MIMAMO Net · Aff-Wild | Arousal CCC: 0.442 -> 0.521 | Improved |
| Use phase differences instead of optical flow in the temporal stream (ablation) | MIMAMO Net · Aff-Wild | Valence CCC: 0.578 -> 0.580 | Improved |
| Use 12 rather than 4, 8, or 16 phase-difference images (ablation) | MIMAMO Net temporal stream · OMG 5-fold cross-validation | Arousal CCC: 0.151, 0.183, 0.212, 0.191 | Mixed |
| Use 12 rather than 4, 8, or 16 phase-difference images (ablation) | MIMAMO Net temporal stream · OMG 5-fold cross-validation | Valence CCC: 0.048, 0.091, 0.151, 0.092 | Mixed |
| Add the temporal stream to the spatial stream (ablation) | MIMAMO Net · OMG | Arousal CCC: 20.8% | Improved |
| Add the temporal stream to the spatial stream (ablation) | MIMAMO Net · OMG | Valence CCC: 4% | Improved |
Closest papers by meaning
- MMAD: Multi-label Micro-Action Detection in Videos (ICCV 2025 · similarity 0.87)
- Amplify, Aggregate, and Adjust: VideoMAE-based Holistic-Subtle Aggregation for Micro-Action Recognition (ECCV 2026 · similarity 0.86)
- Learning Visual Emotion Representations From Web Data (CVPR 2020 · similarity 0.86)
- EmotioNet: An Accurate, Real-Time Algorithm for the Automatic Annotation of a Million Facial Expressions in the Wild (CVPR 2016 · similarity 0.86)
- AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models (ICML 2025 · similarity 0.85)
- $E^3$: Exploring Embodied Emotion Through A Large-Scale Egocentric Video Dataset (NeurIPS 2024 · similarity 0.85)
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.
