muzairkhattak/ViFi-CLIP
[CVPR 2023] Official repository of paper titled "Fine-tuned CLIP models are efficient video learners".
PythonMIT
Issues
- 0
Fully Supervised Setting on Kinetics400
#22 opened by FYY799 - 0
The CUDA erros
#21 opened by caoql98 - 0
Confusion about zero-shot
#20 opened by overwhelmedxh - 0
Pretrained model Performance
#19 opened by ybbwcwaps - 2
LICENSE not Defined
#7 opened by rachmadionl - 4
Questions about model complexity calculation
#18 opened by byminji - 0
UCF-101 Base2novel performance
#17 opened by yjzst - 1
- 1
CUDA out of memory
#16 opened by W4ngH4o - 1
- 3
Inference code
#4 opened by LilyTheBear - 3
Pretrained ViFi-CLIP Model Weights
#13 opened by SHIBOYA - 3
t-SNE visualization code
#12 opened by minghu0830 - 5
Question about library version
#10 opened by byminji - 2
Seeds for Reproducing Results
#11 opened by fzohra - 3
Issue downloading pre-trained weights
#8 opened by ee2110 - 1
[Question] Hardware configuration
#5 opened by karelin - 1
Question about the results
#6 opened by Adeelyousaf - 2
Extracting Video Features
#3 opened by rayush7 - 1
Question about ssv2 data augmentations
#2 opened by tomchen-ctj - 2