VIBE selects task-relevant video summaries by combining a grounding score (video-text alignment) and a utility score (task informativeness), improving human accuracy by up to 61% in user studies.
AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DR
VIBE selects task-relevant video summaries by combining a grounding score (video-text alignment) and a utility score (task informativeness), improving human accuracy by up to 61% in user studies.