YuanGongND cav-mae issues

YuanGongND / cav-mae

Code and Pretrained Models for ICLR 2023 Paper "Contrastive Audio-Visual Masked Autoencoder".

BSD 2-Clause "Simplified" License

214 stars 22 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

traintest_ft.py 中缺少 calculate_stats 函数

#31 yt605155624 opened 1 month ago
1
About the video part, could you release the experimental code?

#30 Cb1ock opened 2 months ago
2
extract mono wav in ffmpeg

#29 yt605155624 opened 3 months ago
0
Eval data not used in evaluation stage?

#28 ben2002chou opened 4 months ago
0
some problem about finetuning

#27 thirteen-bears opened 4 months ago
1
General code refactoring/cleanup done to prepare adding CAV-MAE to HuggingFace

#26 rationalism opened 6 months ago
0
BOM Considerations When Extracting Your Video frames & Audio

#25 fujitte opened 6 months ago
2
Question Regarding stat calculation of dataset

#24 ben2002chou closed 5 months ago
3
Where is contrastive loss implemented? How are the positive and negative samples defined?

#23 ben2002chou closed 7 months ago
2
Not found the sample_video_extract_list.csv

#22 JackieWang9811 closed 8 months ago
4
Could you release the checkpoints pretrained on Kinetics 400

#21 qiyue-liang opened 8 months ago
1
Question for contrastive loss weight in the paper

#20 sukun1045 opened 8 months ago
3
what is the validation set for finetuning?

#19 thirteen-bears opened 8 months ago
6
installation

#18 chandlerbing65nm closed 8 months ago
0
Some confuse about this paper and implement

#17 skyzjsx opened 8 months ago
1
Just suggesting a small change to Loading model for Finetuning Example

#16 ben2002chou opened 8 months ago
2
retrieval evaluation

#15 sukun1045 closed 8 months ago
3
Audio Event Classification resulting tensor has all negative values

#14 rehana-mahfuz closed 10 months ago
5
Acquiring checkpoints of VGGSound (audio), VGGSound (video)

#13 mouxingyang opened 11 months ago
1
Task/cav mae on event dataset

#12 ChunTao1999 closed 11 months ago
0
How to download MSR-VTT datatset?

#11 KyeonghaRho closed 11 months ago
4
How can i get the video and audio pairs of audioset?

#10 SteveTanggithub opened 11 months ago
6
Question about some irregular videos in AudioSet-20k

#9 mouxingyang closed 11 months ago
6
Finetune CAVMAE on ESC50

#8 kaiw7 opened 1 year ago
6
Usage of audio-modality components for visual embeddings

#7 gchochla closed 1 year ago
2
Multi-gpu pre-training

#6 mtran14 closed 1 year ago
4
Pretraining cav-mae on K400

#5 kaiw7 closed 1 year ago
18
Which epoch of pre-trained models should I use?

#4 GenjiB closed 1 year ago
5
Zero-shot Code

#3 zongzi3zz closed 1 year ago
2
Video Only results on AudioSet-20K

#2 GenjiB closed 1 year ago
3
Error when loading the CAV-MAE model

#1 pelegshilo opened 1 year ago
2