A training-free, confidence-gated iterative in-context learning framework substantially improves out-of-distribution video understanding in QA, classification, and captioning.
What makes multimodal in-context learning work? In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pages 1539–1550, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding
A training-free, confidence-gated iterative in-context learning framework substantially improves out-of-distribution video understanding in QA, classification, and captioning.