Research map / Video / Video-language understanding
Self-supervised Pre-training and Contrastive Representation Learning for Multiple-choice Video QA
Seonhoon Kim, Seohyeong Jeong, Eunbyul Kim, Inho Kang, Nojun Kwak
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 locally aligned attention instead of globally aligned attention (ablation) | Video QA model · TVQA+ validation | QA accuracy: 71.62 $\pm$ 0.45 -> 72.29 $\pm$ 0.31 | Improved |
| add temporal localization span loss (ablation) | Video QA model with globally aligned attention · TVQA+ validation | QA accuracy: 71.62 $\pm$ 0.45 -> 73.45 $\pm$ 0.31 | Improved |
| add temporal localization span loss (ablation) | Video QA model with locally aligned attention · TVQA+ validation | QA accuracy: 72.29 $\pm$ 0.31 -> 73.53 $\pm$ 0.29 | Improved |
| add multiple token type embeddings (ablation) | Video QA model with global attention and temporal localization · TVQA+ validation | QA accuracy: 73.45 $\pm$ 0.31 -> 73.98 $\pm$ 0.27 | Improved |
| add multiple token type embeddings (ablation) | Video QA model with local attention and temporal localization · TVQA+ validation | QA accuracy: 73.53 $\pm$ 0.29 -> 74.54 $\pm$ 0.21 | Improved |
| add supervised contrastive loss using a masked ground-truth answer as anchor (ablation) | Video QA model with locally aligned attention, TL, and MT · TVQA+ validation | QA accuracy: 74.54\% to 75.16\% | Improved |
| add self-supervised question-prediction pre-training (ablation) | Video QA model with TL, MT, and contrastive loss · TVQA+ validation | QA accuracy: 75.16 $\pm$ 0.18 -> 75.83 $\pm$ 0.06 | Improved |
Closest papers by meaning
- Leveraging Video Descriptions to Learn Video Question Answering (AAAI 2017 · similarity 0.92)
- Contrastive Video Question Answering via Video Graph Transformer (TPAMI 2023 · 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)
- Learning to Answer Visual Questions From Web Videos (TPAMI 2022 · similarity 0.90)
- MoReVQA: Exploring Modular Reasoning Models for Video Question Answering (CVPR 2024 · similarity 0.88)
- Video-Context Aligned Transformer for Video Question Answering (AAAI 2024 · 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.
