PerceptCLIP
/

PerceptCLIP_Memorability

computer_vision

perceptual_tasks

Model card Files Files and versions Community

Amitz244 commited on Mar 19

Commit

ee2b3f4

·

verified ·

1 Parent(s): d953bd7

Update README.md

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -35,8 +35,7 @@ Our approach leverages *CLIP* as a prior for perceptual tasks, inspired by cogni
 ## Performance
 The model was trained on the *LaMem dataset* and exhibits *state-of-the-art generalization* to the *THINGS memorability dataset*.
-For more models and results on the *five common splits* of LaMem, please refer to our paper.
 ## Usage
 To use the model for inference:

 ## Performance
 The model was trained on the *LaMem dataset* and exhibits *state-of-the-art generalization* to the *THINGS memorability dataset*.
+For more models and results on the five common splits of LaMem, please refer to our paper. *We achieve state-of-the-art (SOTA) performance on the LaMem dataset based on both Spearman correlation and MSE metrics*.
 ## Usage
 To use the model for inference: