Evidence-Backed Video Question Answering
Current Video Large Language Models (Video LLMs) excel in question answering (QA) but largely operate as black boxes, providing textual answers without verifiable visual grounding. Existing explainability efforts rely on textual rationales or sparse bounding boxes, which struggle to capture complex video dynamics such as occlusions and non-rigid deformations. We propose Evidence-Backed Video Question Answering (E-VQA), a novel task requiring models to jointly output a semantic answer and precise spatio-temporal evidence: temporal segments and dense, tracked object segmentation masklets. To sup
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 55%VioletVision-3B →
- PossiblePossibly related (embedding) · 51%FennelFetish/qapyq →
- LinkedLinked via arxiv author · 85%Shijie Wang →
“Evidence-Backed Video Question Answering”
- LinkedLinked via arxiv author · 85%Honglu Zhou →
“Evidence-Backed Video Question Answering”
- LinkedLinked via arxiv author · 85%Ziyang Wang →
“Evidence-Backed Video Question Answering”
- LinkedLinked via arxiv author · 85%Ran Xu →
“Evidence-Backed Video Question Answering”
- LinkedLinked via arxiv author · 85%Caiming Xiong →
“Evidence-Backed Video Question Answering”
- LinkedLinked via arxiv author · 85%Silvio Savarese →
“Evidence-Backed Video Question Answering”