Research map / Vision-language and multimodal / Cross-modal learning
A Multimodal Deep Regression Bayesian Network for Affective Video Content Analyses
Quan Gan, Shangfei Wang, Longfei Hao, Qiang Ji
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 a joint multimodal representation instead of early fusion (ablation) | MMDRBN · MediaEval 2015 valence | accuracy (%): 43.74 -> 44.26 | Improved |
| use a joint multimodal representation instead of late fusion (ablation) | MMDRBN · MediaEval 2015 valence | accuracy (%): 42.22 -> 44.26 | Improved |
| use a joint multimodal representation instead of early fusion (ablation) | MMDRBN · MediaEval 2016 arousal | PCC: 0.31 -> 0.42 | Improved |
| use a joint multimodal representation instead of late fusion (ablation) | MMDRBN · MediaEval 2016 valence | PCC: 0.26 -> 0.39 | Improved |
| use a joint multimodal representation instead of early fusion (ablation) | MMDRBN · MediaEval 2016 valence | MSE: 0.34 -> 0.33 | Improved |
| use a joint multimodal representation instead of late fusion (ablation) | MMDRBN · MediaEval 2015 arousal | accuracy (%): 63.76 -> 64.30 | Improved |
| use directed RBN layers instead of RBM-based DCCAE (ablation) | MMDRBN · MediaEval 2016 arousal | PCC: 0.27 -> 0.42 | Improved |
| use directed RBN layers instead of RBM-based MMDBM (ablation) | MMDRBN · MediaEval 2016 valence | PCC: 0.19 -> 0.39 | Improved |
| use directed RBN layers instead of RBM-based MMDBM (ablation) | MMDRBN · MediaEval 2015 valence | accuracy (%): 41.38 -> 44.26 | Improved |
| use MMDRBN instead of the best MediaEval 2016 entry RUC (ablation) | MMDRBN · MediaEval 2016 valence | MSE: 0.218 -> 0.33 | Hurt |
Closest papers by meaning
- Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities (CVPR 2024 · similarity 0.85)
- Enriching Multimodal Sentiment Analysis Through Textual Emotional Descriptions of Visual-Audio Content (AAAI 2025 · similarity 0.84)
- AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models (ICML 2025 · similarity 0.84)
- Multiple Feature Refining Network for Visual Emotion Distribution Learning (AAAI 2025 · similarity 0.84)
- Multi-to-Single: Reducing Multimodal Dependency in Emotion Recognition Through Contrastive Learning (AAAI 2025 · similarity 0.84)
- MART: Masked Affective RepresenTation Learning via Masked Temporal Distribution Distillation (CVPR 2024 · similarity 0.84)
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.
