Research map / Vision-language and multimodal / Human and embodied modeling
EmotiCon: Context-Aware Multimodal Emotion Recognition Using Frege's Principle
Trisha Mittal, Pooja Guhan, Uttaran Bhattacharya, Rohan Chandra, Aniket Bera, Dinesh Manocha
Check 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 |
|---|---|---|---|
| Add all three context interpretations using depth-based Context 3 | EmotiCon · EMOTIC | mAP: 35.48 vs 28.42 | Improved |
| Add all three context interpretations using depth-based Context 3 | EmotiCon · GroupWalk | mAP: 65.83 vs 58.42 | Improved |
| Add all three context interpretations using depth-based Context 3 | EmotiCon · IEMOCAP | mean classification accuracy: 84.5% vs 82.7% | Improved |
| Add Context 2 (semantic background) to Context 1 (ablation) | EmotiCon · EMOTIC | mAP: 24.06 -> 31.53 | Improved |
| Add Context 3 (socio-dynamic context) to Context 1 (ablation) | EmotiCon · EMOTIC | mAP: 24.06 -> 29.63 | Improved |
| Add Context 3 to Contexts 1 and 2 (ablation) | EmotiCon · EMOTIC | mAP: 31.53 -> 35.48 | Improved |
| Add Context 2 to Contexts 1 and 3 (ablation) | EmotiCon · EMOTIC | mAP: 29.63 -> 35.48 | Improved |
| Add Context 2 (semantic background) to Context 1 (ablation) | EmotiCon · GroupWalk | mAP: 55.57 -> 59.20 | Improved |
| Add Context 3 (socio-dynamic context) to Context 1 (ablation) | EmotiCon · GroupWalk | mAP: 55.57 -> 62.38 | Improved |
| Add Context 3 to Contexts 1 and 2 (ablation) | EmotiCon · GroupWalk | mAP: 59.20 -> 65.83 | Improved |
| Add Context 2 to Contexts 1 and 3 (ablation) | EmotiCon · GroupWalk | mAP: 62.38 -> 65.83 | Improved |
| Use depth maps rather than a GCN for Context 3 | EmotiCon · EMOTIC | mAP: 32.03 -> 35.48 | Improved |
Closest papers by meaning
- AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models (ICML 2025 · similarity 0.88)
- OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition (ICML 2025 · similarity 0.87)
- $E^3$: Exploring Embodied Emotion Through A Large-Scale Egocentric Video Dataset (NeurIPS 2024 · similarity 0.87)
- EmoNet-Face: An Expert-Annotated Benchmark for Synthetic Emotion Recognition (NeurIPS 2025 · similarity 0.87)
- Uncertain Multimodal Intention and Emotion Understanding in the Wild (CVPR 2025 · similarity 0.86)
- AffectGPT-RL: Revealing Roles of Reinforcement Learning in Open-Vocabulary Emotion Recognition (NeurIPS 2026 · 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.
