Research map / Vision-language and multimodal / Visual question answering
Leveraging Video Descriptions to Learn Video Question Answering
Kuo-Hao Zeng, Tseng-Hung Chen, Ching-Yao Chuang, Yuan-Hong Liao, Juan Carlos Niebles, Min Sun
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 self-paced learning to mask training pairs flagged by the ratio test (ablation) | E-SS · Video-QA test, Avg. | accuracy: 28.4 -> 31.0; 2.6% improvement | Improved |
| Use self-paced learning to mask training pairs flagged by the ratio test (ablation) | E-MN · Video-QA test, Avg. | accuracy: 26.2 -> 27.5 | Improved |
| Use self-paced learning to mask training pairs flagged by the ratio test (ablation) | E-VQA · Video-QA test, Avg. | accuracy: 25.9 -> 26.4 | Improved |
| Use self-paced learning to mask training pairs flagged by the ratio test (ablation) | E-SA · Video-QA test, Avg. | accuracy: 30.4 -> 30.5 | Improved |
| Replace video observations with dummy observations (ablation) | E-SS · Video-QA test, Avg. | accuracy: 31.0 -> 27.2 | Hurt |
| Replace video observations with dummy observations (ablation) | E-MN · Video-QA test, Avg. | accuracy: 27.5 -> 25.9 | Hurt |
| Replace video observations with dummy observations (ablation) | E-VQA · Video-QA test, Avg. | accuracy: 26.4 -> 25.2 | Hurt |
| Replace video observations with dummy observations (ablation) | E-SA · Video-QA test, Avg. | accuracy: 30.5 -> 28.2 | Hurt |
| Encode video and question sequentially, then decode the answer | Video-QA extended models · Video-QA test, Avg. | accuracy: 31.0 vs. 30.5, 27.5, and 26.4 | Improved |
| Combine video and question representations with element-wise multiplication | E-VQA · Video-QA test, Avg. | accuracy: 26.4 | Hurt |
Closest papers by meaning
- Self-supervised Pre-training and Contrastive Representation Learning for Multiple-choice Video QA (AAAI 2021 · similarity 0.92)
- Just Ask: Learning To Answer Questions From Millions of Narrated Videos (ICCV 2021 · similarity 0.92)
- Learning to Answer Visual Questions From Web Videos (TPAMI 2022 · similarity 0.91)
- Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models (ICCV 2023 · similarity 0.90)
- Commonsense Video Question Answering through Video-Grounded Entailment Tree Reasoning (CVPR 2025 · similarity 0.89)
- MoReVQA: Exploring Modular Reasoning Models for Video Question Answering (CVPR 2024 · similarity 0.89)
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.
