Research map / Video / Video-language understanding
ANetQA: A Large-Scale Benchmark for Fine-Grained Compositional Reasoning Over Untrimmed Videos
Zhou Yu, Lixiang Zheng, Zhou Zhao, Fei Wu, Jianping Fan, Kui Ren, Jun Yu
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 |
|---|---|---|---|
| Use All-in-one rather than ClipBERT | VideoQA models on ANetQA · ANetQA test | accuracy: 43.92 -> 44.53 | Improved |
| Add vision clues instead of training blind | All-in-one · ANetQA test | accuracy: 36.48 -> 44.53 | Improved |
| Add high-frequency object words (ablation) | HCRN · ANetQA test | accuracy: 41.15 -> 41.18 | No clear effect |
| Add high-frequency relationship words (ablation) | HCRN · ANetQA test | accuracy: 41.15 -> 40.48 | Hurt |
| Add high-frequency attribute words (ablation) | HCRN · ANetQA test | accuracy: 41.15 -> 43.75 | Improved |
| Add high-frequency object, relationship, and attribute words together (ablation) | HCRN · ANetQA test | accuracy: 41.15 -> 45.45 | Improved |
| Inject oracle frames during training (ablation) | All-in-one · ANetQA test | accuracy: 44.53 -> 45.40 | Improved |
| Inject oracle frames during testing (ablation) | All-in-one · ANetQA test | accuracy: 44.53 -> 44.99 | Improved |
| Inject oracle frames during both training and testing (ablation) | All-in-one · ANetQA test | accuracy: 44.53 -> 46.07 | Improved |
Closest papers by meaning
- VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection (CVPR 2025 · similarity 0.91)
- Commonsense Video Question Answering through Video-Grounded Entailment Tree Reasoning (CVPR 2025 · similarity 0.91)
- MoReVQA: Exploring Modular Reasoning Models for Video Question Answering (CVPR 2024 · similarity 0.91)
- Align and Aggregate: Compositional Reasoning with Video Alignment and Answer Aggregation for Video Question-Answering (CVPR 2024 · similarity 0.90)
- LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding (NeurIPS 2024 · similarity 0.90)
- STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training (CVPR 2025 · similarity 0.90)
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.
