Research map / Vision-language and multimodal / Visual question answering
BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection
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 BLOCK fusion instead of MFH fusion | VQA 2.0 fusion model · VQA 2.0 test-dev | All accuracy: 65.72 -> 66.41 | Helped |
| Use BLOCK fusion instead of the strongest listed fusion baseline | VRD fusion model · VRD predicate prediction | Recall@50: 85.96 -> 86.58 | Helped |
| Use BLOCK fusion rather than the best listed non-BLOCK fusion | VRD fusion model · VRD phrase detection | Recall@50: 26.09 -> 26.32 | Helped |
| Use BLOCK fusion rather than the best listed non-BLOCK fusion | VRD fusion model · VRD relationship detection | Recall@50: 18.81 -> 19.06 | Helped |
| Use BLOCK instead of Counter | VQA2 model · VQA2 test-dev | All accuracy: 68.09 -> 67.58 | Hurt |
| Use BLOCK instead of Counter | VQA2 model · VQA2 test-std | All accuracy: 68.41 -> 67.92 | Hurt |
| Use the compact 3M-parameter BLOCK configuration | VQA 2.0 fusion model · VQA 2.0 test-dev | All accuracy: 64.91% | Mixed |
Closest papers by meaning
- FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering (CVPR 2025 · similarity 0.86)
- SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion (NeurIPS 2024 · similarity 0.85)
- MoDA: Modulation Adapter for Fine-Grained Visual Understanding in Instructional MLLMs (ICML 2026 · similarity 0.85)
- Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models (ICLR 2025 · similarity 0.85)
- Bidirectional Contrastive Split Learning for Visual Question Answering (AAAI 2024 · similarity 0.85)
- SkillCLIP: Skill Aware Modality Fusion Visual Question Answering (Student Abstract) (AAAI 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.