Research map / Vision-language and multimodal / Visual question answering
HAIR: Hierarchical Visual-Semantic Relational Reasoning for Video Question Answering
Fei Liu, Jing Liu, Weining Wang, Hanqing Lu
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 |
|---|---|---|---|
| add frame-level reasoning on top of object-level reasoning (ablation) | HAIR · TGIF-QA Action | accuracy: 73.5 -> 77.8 | Improved |
| add object-level reasoning on top of frame-level reasoning (ablation) | HAIR · TGIF-QA Action | accuracy: 71.2 -> 77.8 | Improved |
| use hierarchical reasoning instead of two parallel streams (ablation) | HAIR · TGIF-QA Action | accuracy: 75.3 -> 77.8 | Improved |
| add visual graph memory (ablation) | HAIR · TGIF-QA Action | accuracy: 70.6 -> 77.8 | Improved |
| add semantic graph memory (ablation) | HAIR · TGIF-QA Action | accuracy: 74.6 -> 77.8 | Improved |
| add semantic graph memory (ablation) | HAIR · TGIF-QA FrameQA | accuracy: 56.0 -> 60.2 | Improved |
| add visual graph memory (ablation) | HAIR · TGIF-QA FrameQA | accuracy: 57.4 -> 60.2 | Improved |
| add both visual and semantic graph memory (ablation) | HAIR · TGIF-QA Action | accuracy: 68.4 -> 77.8 | Improved |
| use graph memory instead of GCN (ablation) | HAIR · TGIF-QA Action | accuracy: 73.4 -> 77.8 | Improved |
| use graph memory instead of self-attention (ablation) | HAIR · TGIF-QA Action | accuracy: 73.9 -> 77.8 | Improved |
| use graph memory instead of memory network (ablation) | HAIR · TGIF-QA Action | accuracy: 72.4 -> 77.8 | Improved |
| use graph memory instead of GCN on fused features (ablation) | HAIR · TGIF-QA Count | MSE: 3.95 -> 3.88 | Improved |
Later papers that compared with this method
1 later accepted paper reports HAIR as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering (TPAMI 2023 · better on 1 of 1 shared result)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection (CVPR 2025 · similarity 0.88)
- Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding (NeurIPS 2025 · similarity 0.88)
- Not Another Text Benchmark: Putting the “Visual" Back in Visual Question Answering for Large Video Models (NeurIPS 2026 · similarity 0.88)
- Divide and Conquer: Exploring Language-centric Tree Reasoning for Video Question-Answering (ICML 2025 · similarity 0.88)
- Language-aware Visual Semantic Distillation for Video Question Answering (CVPR 2024 · similarity 0.88)
- Commonsense Video Question Answering through Video-Grounded Entailment Tree Reasoning (CVPR 2025 · similarity 0.87)
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.
