YuanGongND/cav-mae
Code and Pretrained Models for ICLR 2023 Paper "Contrastive Audio-Visual Masked Autoencoder".
PythonBSD-2-Clause
Issues
- 2
- 1
traintest_ft.py 中缺少 calculate_stats 函数
#31 opened by yt605155624 - 2
- 0
Eval data not used in evaluation stage?
#28 opened by ben2002chou - 1
some problem about finetuning
#27 opened by thirteen-bears - 3
- 2
- 2
Where is contrastive loss implemented? How are the positive and negative samples defined?
#23 opened by ben2002chou - 4
- 1
- 6
what is the validation set for finetuning?
#19 opened by thirteen-bears - 3
- 3
retrieval evaluation
#15 opened by sukun1045 - 0
installation
#18 opened by chandlerbing65nm - 2
- 1
Some confuse about this paper and implement
#17 opened by skyzjsx - 6
- 5
- 1
- 6
- 4
How to download MSR-VTT datatset?
#11 opened by KyeonghaRho - 6
Finetune CAVMAE on ESC50
#8 opened by kaiw7 - 18
Pretraining cav-mae on K400
#5 opened by kaiw7 - 2
- 4
Multi-gpu pre-training
#6 opened by mtran14 - 5
- 2
Zero-shot Code
#3 opened by zongzi3zz - 3
Video Only results on AudioSet-20K
#2 opened by GenjiB - 2
Error when loading the CAV-MAE model
#1 opened by pelegshilo