Research map / Time series / Causal and generative time series
Affect2MM: Affective Analysis of Multimedia Content Using Emotion Causality
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 |
|---|---|---|---|
| Use Affect2MM rather than MFT | SENDv1, FAT · SENDv1 test | CCC: $.440$ -> $.597$ | Helped |
| Use Affect2MM rather than EmotionNet | MovieGraphs · MovieGraphs test | Top-1 accuracy: $27.90$ -> $30.58$ | Helped |
| Use Affect2MM rather than the strongest listed baseline | LIRIS-ACCEDE valence prediction · LIRIS-ACCEDE test, valence | MSE: $0.071$ -> $0.068$ | Helped |
| Add co-attention and Granger causality (ablation) | Affect2MM · SENDv1 | CCC: $.570$ -> $.597$ | Helped |
| Add co-attention and Granger causality (ablation) | Affect2MM · MovieGraphs | Accuracy: $28.290$ -> $30.580$ | Helped |
| Add co-attention and Granger causality (ablation) | Affect2MM · LIRIS-ACCEDE valence | MSE: $0.122$ -> $0.068$ | Helped |
| Add co-attention and Granger causality (ablation) | Affect2MM · LIRIS-ACCEDE arousal | MSE: $0.143$ -> $0.128$ | Helped |
| Add Granger causality (ablation) | Affect2MM with co-attention · SENDv1 | CCC: $.585$ -> $.597$ | Helped |
| Add Granger causality (ablation) | Affect2MM with co-attention · MovieGraphs | Accuracy: $29.450$ -> $30.580$ | Helped |
| Add Granger causality (ablation) | Affect2MM with co-attention · LIRIS-ACCEDE valence | MSE: $0.095$ -> $0.068$ | Helped |
| Add Granger causality (ablation) | Affect2MM with co-attention · LIRIS-ACCEDE arousal | MSE: $0.135$ -> $0.128$ | Helped |
Closest papers by meaning
- VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models (NeurIPS 2025 · similarity 0.87)
- MART: Masked Affective RepresenTation Learning via Masked Temporal Distribution Distillation (CVPR 2024 · similarity 0.86)
- AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models (ICML 2025 · similarity 0.86)
- $E^3$: Exploring Embodied Emotion Through A Large-Scale Egocentric Video Dataset (NeurIPS 2024 · similarity 0.86)
- Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approach (ICLR 2026 · similarity 0.86)
- Enhancing Multimodal Affective Analysis with Learned Live Comment Features (AAAI 2025 · 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.