issues
search
UARK-AICV
/
VLTinT
[AAAI 2023 Oral] VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning
https://uark-aicv.github.io/VLTinT/
65
stars
6
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Could you release pretrained checkpoint for evaluation?
#17
Raaaandy
opened
5 months ago
0
Regarding dependency issues.
#16
Hzzzy31
opened
9 months ago
2
What should be placed inside the folder 'video_feature/anet_trainval'?
#15
shaohuaJK
closed
10 months ago
1
The Cider score for YouCookII are different
#14
yangxingrui
opened
10 months ago
2
YouCook2
#13
mrzhang66
opened
11 months ago
4
about YouCook2 dataset
#12
myccver
closed
11 months ago
1
Open the permissions of the features extracted from rescaled videos of ActivityNet-1.3
#11
Minniemu
closed
9 months ago
4
Update README.md
#10
Kashu7100
closed
1 year ago
1
Generating captions for other videos
#9
shamanthak-hegde
closed
9 months ago
6
Update README.md
#8
Kashu7100
closed
1 year ago
0
share the captions generated by your model
#7
wanghao14
closed
1 year ago
5
Extract bbox bug for multi gpu processing
#6
fake-warrior8
closed
1 year ago
1
Could you release the trained checkpoint?
#5
fake-warrior8
opened
1 year ago
1
FileNotFoundError: [Errno 2] No such file or directory: 'path/to/video/dir'
#4
NCU-MC
closed
1 year ago
1
The scores for YouCookII are different.
#3
yueyue0401
closed
1 year ago
2
demo.py is missing
#2
yueyue0401
closed
1 year ago
1
bbox_extract.py for Detectron2
#1
yueyue0401
closed
1 year ago
1