Research map / Label-efficient and robust learning / Recognition and long-tail
Most Important Person-Guided Dual-Branch Cross-Patch Attention for Group Affect Recognition
Hongxia Xie, Ming-Xian Lee, Tzu-Jui Chen, Hung-Jen Chen, Hou-I Liu, Hong-Han Shuai, Wen-Huang Cheng
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 |
|---|---|---|---|
| use only the Most Important Person face instead of all faces (ablation) | CrossViT with global + faces · GroupEmoW | accuracy (%): 85.01 -> 88.86 | Improved |
| add MIP input to global input (dual-path) (ablation) | CrossViT · GAF 3.0 | accuracy (%): 75.56 -> 77.29 | Improved |
| use MIP only without global image (ablation) | DCAT · GroupEmoW | accuracy (%): 89.55 -> 80.08 | Hurt |
| replace CrossViT class-token cross-attention with Cross-Patch Attention (ablation) | DCAT-ViT · GroupEmoW | accuracy (%): 87.86 -> 89.55 | Improved |
| add token ranking module to dual-path + CPA (ablation) | DCAT-ViT · GAF 3.0 | accuracy (%): 76.21 -> 77.29 | Improved |
| add CPA module on top of dual-path input (ablation) | DCAT-CSwin-L · GroupEmoW | accuracy (%): 90.12 -> 90.47 | Improved |
| add dual-pathway input (MIP) to CrossViT (ablation) | CrossViT · GroupEmoW | accuracy (%): 88.48 -> 88.86 | Improved |
| drop a certain percentage of tokens in MIP branch (ablation) | DCAT · dropping ratio study | accuracy | Improved |
Closest papers by meaning
- Emotional Attention: A Study of Image Sentiment and Visual Attention (CVPR 2018 · similarity 0.86)
- AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models (ICML 2025 · similarity 0.84)
- egoEMOTION: Egocentric Vision and Physiological Signals for Emotion and Personality Recognition in Real-world Tasks (NeurIPS 2025 · similarity 0.84)
- Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognition (CVPR 2025 · similarity 0.83)
- CocoER: Aligning Multi-Level Feature by Competition and Coordination for Emotion Recognition (CVPR 2025 · similarity 0.83)
- EmoNet-Face: An Expert-Annotated Benchmark for Synthetic Emotion Recognition (NeurIPS 2025 · similarity 0.83)
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.
