Research map / Video / Video-language understanding
ActivityNet-QA: A Dataset for Understanding Complex Web Videos via 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 |
|---|---|---|---|
| Replace fixed-stepsize sampling with dynamic-stepsize sampling based on action proposals (ablation) | VideoQA baselines · ActivityNet-QA | Accuracy: at least 1% | Helped |
| Increase sampling frequency to T=60 (ablation) | E-SA · ActivityNet-QA | Accuracy | Hurt |
| Use mean-pooling fusion instead of concatenation or elementwise product (ablation) | E-SA with FS sampling · ActivityNet-QA | Accuracy | Helped |
| Use E-SA instead of E-VQA | VideoQA baseline · ActivityNet-QA test | Accuracy: 25.1 -> 31.8 | Helped |
| Use E-SA instead of E-MN | VideoQA baseline · ActivityNet-QA test | Accuracy: 27.1 -> 31.8 | Helped |
Closest papers by meaning
- MoReVQA: Exploring Modular Reasoning Models for Video Question Answering (CVPR 2024 · similarity 0.90)
- VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection (CVPR 2025 · similarity 0.89)
- Commonsense Video Question Answering through Video-Grounded Entailment Tree Reasoning (CVPR 2025 · similarity 0.89)
- LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding (NeurIPS 2024 · similarity 0.88)
- ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition (NeurIPS 2024 · similarity 0.88)
- Understanding Complexity in VideoQA via Visual Program Generation (ICML 2025 · similarity 0.88)
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.