AI Paper Atlas

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

CVPR 2023 · Video › Video-language understanding · approach: Video question answering · 12 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use All-in-one rather than ClipBERTVideoQA models on ANetQA · ANetQA testaccuracy: 43.92 -> 44.53Improved
Add vision clues instead of training blindAll-in-one · ANetQA testaccuracy: 36.48 -> 44.53Improved
Add high-frequency object words (ablation)HCRN · ANetQA testaccuracy: 41.15 -> 41.18No clear effect
Add high-frequency relationship words (ablation)HCRN · ANetQA testaccuracy: 41.15 -> 40.48Hurt
Add high-frequency attribute words (ablation)HCRN · ANetQA testaccuracy: 41.15 -> 43.75Improved
Add high-frequency object, relationship, and attribute words together (ablation)HCRN · ANetQA testaccuracy: 41.15 -> 45.45Improved
Inject oracle frames during training (ablation)All-in-one · ANetQA testaccuracy: 44.53 -> 45.40Improved
Inject oracle frames during testing (ablation)All-in-one · ANetQA testaccuracy: 44.53 -> 44.99Improved
Inject oracle frames during both training and testing (ablation)All-in-one · ANetQA testaccuracy: 44.53 -> 46.07Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy