SOTAVerified

Open Vocabulary Action Recognition

Open Vocabulary Action Recognition (OVAR) aims to generalize beyond the predefined set of actions seen during training. The actions (verbs or verb-object pairs) are provided as textual queries during inference and no prior knowledge about them is assumed to be known during training.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–5 of 5 papers

TitleStatusHype
FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action RecognitionCode2
Rethinking CLIP-based Video Learners in Cross-Domain Open-Vocabulary Action RecognitionCode1
Learning to Generalize without Bias for Open-Vocabulary Action Recognition—0
DENOISER: Rethinking the Robustness for Open-Vocabulary Action Recognition—0
Opening the Vocabulary of Egocentric ActionsCode0
Show:102550

No leaderboard results yet.