Research map / Vision-language and multimodal / Visual question answering
Focal Visual-Text Attention for Visual Question Answering
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 |
|---|---|---|---|
| Use FVTA instead of the strongest listed attention baseline | MemexQA · MemexQA | accuracy: 0.630 -> 0.669 | Helped |
| Use FVTA instead of RWMN | MovieQA · MovieQA val | accuracy: 0.387 -> 0.410 | Helped |
| Use FVTA instead of RWMN | MovieQA · MovieQA test | accuracy: 0.363 -> 0.373 | Helped |
| Use FVTA attention rather than the strongest listed evidence-localization baseline | MemexQA · MemexQA evidence photos | HIT@1: 13.28% -> 15.48% | Helped |
| Replace the learned similarity representation with cosine similarity (ablation) | FVTA · MemexQA | accuracy: -4.9% | Hurt |
| Remove intra-sequence temporal dependency (ablation) | FVTA · MemexQA | accuracy: -10.0% | Hurt |
| Remove cross-sequence interaction (ablation) | FVTA · MemexQA | accuracy: -6.5% | Hurt |
| Remove question attention and use the last question LSTM state (ablation) | FVTA · MemexQA | accuracy: -4.0% | Hurt |
| Remove photos (ablation) | FVTA · MemexQA | accuracy: -9.1% | Hurt |
Closest papers by meaning
- Multi-Level Attention Networks for Visual Question Answering (CVPR 2017 · similarity 0.91)
- Structured Two-Stream Attention Network for Video Question Answering (AAAI 2019 · similarity 0.90)
- Where to Look: Focus Regions for Visual Question Answering (CVPR 2016 · similarity 0.90)
- Not Another Text Benchmark: Putting the “Visual" Back in Visual Question Answering for Large Video Models (NeurIPS 2026 · similarity 0.89)
- FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering (NeurIPS 2025 · similarity 0.89)
- VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning (CVPR 2024 · similarity 0.89)
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.