Zero Shot Action Recognition On Activitynet

Top-1 Accuracy

Results

Performance results of various models on this benchmark

		Paper Title
BIKE	86.2	Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models
Text4Vis	84.6	Revisiting Classifier: Transferring Vision-Language Models for Video Recognition
LoCATe-GAT	73.8	LoCATe-GAT: Modeling Multi-Scale Local Context and Action Relationships for Zero-Shot Action Recognition
ResT	32.5	Cross-modal Representation Learning for Zero-shot Action Recognition
E2E	26.6	Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications

0 of 5 row(s) selected.