Research map / Vision-language and multimodal / Cross-modal learning
Multimodal Poisson Gamma Belief Network
Read the paperCheck 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 |
|---|---|---|---|
| add a second hidden layer (mPFA single layer -> mPGBN two layers) (ablation) | mPGBN · MIR-Flickr 25k classification | MAP: 0.515 -> 0.532 | Helped |
| add a second hidden layer (ablation) | mPGBN · MIR-Flickr 25k classification | Precision@50: 0.834 -> 0.844 | Helped |
| mPGBN vs multimodal DBM | mPGBN · MIR-Flickr 25k classification | MAP: 0.513 -> 0.532 | Helped |
| mPGBN vs multimodal DBM on individual classes (SKY, CLOUDS*) | mPGBN · MIR-Flickr 25k classification | AP per class: 0.883 -> 0.809 (SKY) | Mixed |
| increase network depth T with widths fixed (ablation) | mPGBN · MIR-Flickr 25k, 15k pairs | MAP | Helped |
| increase hidden layer width Kt with depth fixed (ablation) | mPGBN · MIR-Flickr 25k, 15k pairs | MAP | Helped |
| increase Vmax of discretized count input (ablation) | mPGBN T=3, Kt=400 · MIR-Flickr 25k | MAP | Mixed |
Closest papers by meaning
- Unity by Diversity: Improved Representation Learning for Multimodal VAEs (NeurIPS 2024 · similarity 0.83)
- Emu: Generative Pretraining in Multimodality (ICLR 2024 · similarity 0.83)
- Beyond Graph Convolution: Multimodal Recommendation with Topology-aware MLPs (AAAI 2025 · similarity 0.83)
- Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning (ICLR 2024 · similarity 0.82)
- Graph4MM: Weaving Multimodal Learning with Structural Information (ICML 2025 · similarity 0.82)
- Your Embedding Model Is SMARTer Than You Think (NeurIPS 2026 · similarity 0.82)
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.