AI Paper Atlas

Research map / Video / Video-language understanding

IntentQA: Intent Question Answering in Videos by Cognitive Context Reasoning

J H Li, Ping Wei, Wenjuan Han, Song Chun Zhu, Lifeng Fan

TPAMI 2026 · Video › Video-language understanding · approach: Video question answering · 0 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
add Video Query Language (VQL) (ablation)Base Model · IntentQA testaccuracy (%): 51.36 -> 52.34 (+0.98)Improved
add triplet loader (ablation)Base + VQL · IntentQA testaccuracy (%): 52.34 -> 53.80 (+1.46)Improved
add triplet margin loss (ablation)Base + VQL + loader · IntentQA testaccuracy (%): 53.80 -> 54.50 (+0.70)Improved
add LLM commonsense with confidence prompting (ablation)visual model · IntentQA testaccuracy (%): 54.50 -> 58.48 (+3.98)Improved
use confidence prompting instead of late fusion (ablation)InstructGPT · IntentQA testaccuracy (%): 57.64 -> 58.48Improved
add caption information (ablation)X-CaVIR (InstructGPT) · IntentQA testaccuracy (%): 58.48 -> 60.73 (+2.25)Improved
add caption information (ablation)X-CaVIR (GPT-4) · IntentQA testaccuracy (%): 62.65 -> 64.81Improved
add the visual model on top of caption + LLM (ablation)InstructGPT · IntentQA testaccuracy (%): 54.03 -> 60.73Improved
use GPT-4 instead of InstructGPTX-CaVIR full · IntentQA testaccuracy (%): 60.73 -> 64.81Improved
use random masking instead of attention-based masking in contrastive learning (ablation)contrastive learning · IntentQA testaccuracy (%): 54.50 -> 51.50Hurt
mask lowest-attention tokens instead of selected action (ablation)contrastive learning · IntentQA testaccuracy (%): 54.50 -> 54.05Hurt
compare to the strongest prior VideoQA modelX-CaVIR vs VGT · IntentQA testaccuracy (%): 51.27 -> 60.73Improved

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