Research map / Video / Video-language understanding
Multimodal Keyless Attention Fusion for Video Classification
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 |
|---|---|---|---|
| keyless attention instead of averaging BiLSTM outputs (ablation) | RGB BiLSTM classifier · Kinetics val | top-1 accuracy: 73.2 -> 73.8 | Helped |
| keyless attention instead of last hidden state (ablation) | RGB BiLSTM classifier · ActivityNet val | mAP: 71.4 -> 72.0 | Helped |
| attention fusion instead of probability fusion (ablation) | multimodal video classifier · Kinetics val | top-1 accuracy: 74.9 -> 77.0 | Helped |
| attention fusion instead of probability fusion (ablation) | multimodal video classifier · YouTube-8M 60K val | GAP@20: 79.1 -> 80.9 | Helped |
| attention fusion instead of feature fusion (ablation) | multimodal video classifier · UCF101 | accuracy: 94.1 -> 94.8 | Helped |
| LSTM fusion instead of feature fusion (ablation) | multimodal video classifier · Kinetics val | top-1 accuracy: 76.1 -> 76.2 | No clear effect |
| fuse RGB, flow and audio with attention fusion vs RGB only (ablation) | keyless attention model · Kinetics val | top-1 accuracy: 73.8 -> 77.0 | Helped |
Closest papers by meaning
- Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion (ICML 2024 · similarity 0.85)
- Beyond Modality Fusion: Deep Ensembles for Multimodal Classification (NeurIPS 2026 · similarity 0.84)
- Adaptive Multimodal Fusion: Dynamic Attention Allocation for Intent Recognition (AAAI 2025 · similarity 0.84)
- Bidirectional Sparse Attention for Faster Video Diffusion Training (NeurIPS 2026 · similarity 0.84)
- Faster Video Diffusion with Trainable Sparse Attention (NeurIPS 2025 · similarity 0.83)
- MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning (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.