Research map / Video / Video-language understanding
IntentQA: Context-aware Video Intent Reasoning
Jiapeng Li, Ping Wei, Wenjuan Han, Lifeng Fan
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 |
|---|---|---|---|
| add GPT commonsense prior at test time (ablation) | CaVIR · IntentQA test (Total) | accuracy (%): 54.50 -> 57.64 | Improved |
| add triplet loader for contrastive samples (ablation) | CaVIR · IntentQA test (Total) | accuracy (%): 52.34 -> 53.80 | Improved |
| add VQL (video query language) (ablation) | Base Model · IntentQA test (Total) | accuracy (%): 51.36 -> 52.34 | Improved |
| add triplet margin loss (ablation) | CaVIR · IntentQA test (Total) | accuracy (%): 53.80 -> 54.50 | Improved |
| add VQL to full model (removing it) (ablation) | CaVIR · IntentQA test (Total) | accuracy (%): 57.08 -> 57.64 | Improved |
| add contrastive learning to full model (removing it) (ablation) | CaVIR · IntentQA test (Total) | accuracy (%): 55.72 -> 57.64 | Improved |
| randomly mask k nodes of cross-modal graph (ablation) | CaVIR w/o GPT · IntentQA test (Total) | accuracy (%): 54.5 -> 51.5 | Hurt |
| mask lowest-attention nodes of cross-modal graph (ablation) | CaVIR w/o GPT · IntentQA test (Total) | accuracy (%): 54.5 -> 54.05 | No clear effect |
| stricter contrastive sample criterion (t1 = 1 with exact action) versus looser (ablation) | contrastive learning · IntentQA test (Total) | accuracy (%): 52.67 -> 54.50 (best config) | Improved |
| add 'Let's think step by step' to GPT prompt (ablation) | GPT commonsense module · IntentQA test (Total) | accuracy (%): prompt 1: 57.64 -> 58.43; prompt 2: 57.31 -> 57.83; prompt 3: 57.17 -> 57.36 | Mixed |
| pretrain on IntentQA with triplet loss then finetune on MSRVTT-QA | VGT-based model · MSRVTT-QA test | accuracy (%): 39.00 -> 39.39 | Improved |
Closest papers by meaning
- IntentQA: Intent Question Answering in Videos by Cognitive Context Reasoning (TPAMI 2026 · similarity 0.92)
- BDIQA: A New Dataset for Video Question Answering to Explore Cognitive Reasoning through Theory of Mind (AAAI 2024 · similarity 0.86)
- Contextual Augmented Global Contrast for Multimodal Intent Recognition (CVPR 2024 · similarity 0.85)
- Video-R1: Reinforcing Video Reasoning in MLLMs (NeurIPS 2025 · similarity 0.84)
- MoReVQA: Exploring Modular Reasoning Models for Video Question Answering (CVPR 2024 · similarity 0.84)
- VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection (CVPR 2025 · similarity 0.84)
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.
