issues
search
Alibaba-MIIL
/
STAM
Official implementation of "An Image is Worth 16x16 Words, What is a Video Worth?" (2021 paper)
Apache License 2.0
219
stars
31
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
about temporal module
#30
yinruonan
closed
1 year ago
0
How to train?
#19
TianshengSun
opened
2 years ago
0
how to prepare a validation folder?
#18
Bobby-youngking
closed
2 years ago
1
Performance with low hyper parameters
#17
chenyangjamie
opened
2 years ago
0
train model
#16
yeboqxc
closed
1 year ago
0
Why did you use a pytorch built-in TransformerEncoder in TAggregate module?
#15
yojayc
opened
3 years ago
0
Pretrain weights from the ImageNet
#14
villawang
closed
3 years ago
2
时间聚合时维度如何对齐?
#13
unclebuff
closed
3 years ago
2
python -m infer 预测是上传任何视频都行吗
#12
lonngxiang
opened
3 years ago
1
是把16帧组成当成一张图片吗,另外预训练模型会公布吗
#11
lonngxiang
opened
3 years ago
0
when will you update? looking forward to your code !
#10
zpyi
closed
3 years ago
0
Could you please share training hyper-parameters?
#9
stevehuanghe
opened
3 years ago
1
Cannot access pretrained model link
#8
ducminhkhoi
closed
3 years ago
1
39.8% of the validation data is not used for performance test
#7
FaceAnalysis
closed
3 years ago
2
some training hyperparameters about kinetics400
#6
lwdoubles
closed
3 years ago
1
Linear Projection
#5
ShuvenduRoy
closed
3 years ago
2
Training code
#4
OValery16
closed
3 years ago
2
About TAggreagate
#3
TitaniumOne
closed
3 years ago
1
Training hyperparameters?
#2
jianghaojun
closed
3 years ago
1
from .layers.drop import DropPath
#1
zkx-sust
closed
3 years ago
2