Video-GCD: a new benchmark and a consistency-aware contrastive learning method for discovering known and novel categories in videos.
Visionzip: Longer is better but not necessary in vision language models
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
-
Video-based Generalized Category Discovery via Memory-Guided Consistency-Aware Contrastive Learning
Video-GCD: a new benchmark and a consistency-aware contrastive learning method for discovering known and novel categories in videos.