SDGAN improves temporal video grounding by jointly using static and dynamic graphs with query-clip contrastive learning and easy-to-hard progressive training.
Revi- sionLLM: Recursive vision–language model for temporal grounding in hour-long videos,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Static and Dynamic Graph Alignment Network for Temporal Video Grounding
SDGAN improves temporal video grounding by jointly using static and dynamic graphs with query-clip contrastive learning and easy-to-hard progressive training.