FlashVTG improves moment retrieval and highlight detection by replacing the DETR decoder with a temporal feature pyramid and adaptively refining confidence scores from intra- and inter-scale features.
Slowfast networks for video recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding
FlashVTG improves moment retrieval and highlight detection by replacing the DETR decoder with a temporal feature pyramid and adaptively refining confidence scores from intra- and inter-scale features.