issues
search
rowanz
/
merlot
MERLOT: Multimodal Neural Script Knowledge Models
MIT License
223
stars
25
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Access to Video Data
#18
Legen927
opened
7 months ago
0
Got `UnicodeDecodeError` whening load file `yttemporal180m_050of100.jsonl.gz`.
#17
SCZwangxiao
closed
1 year ago
1
Question on fair comparison with Conceptual ∪ COCO
#16
SCZwangxiao
opened
1 year ago
0
Issue on the model scalablity due to segment-level positional embeddings
#15
SCZwangxiao
opened
1 year ago
0
Question on the definition of visually "ungrounded" categories
#14
SCZwangxiao
opened
1 year ago
0
Code for preprocessing raw video data
#13
TZWwww
opened
2 years ago
0
[Question] Est. disk space to hold the pretraining dataset
#12
dxli94
closed
2 years ago
2
Is finetuned checkpoint on VCR available?
#11
yrf1
opened
2 years ago
0
Running funetuning on GPU
#10
insundaycathy
opened
2 years ago
2
YT-Temporal-180M video dataset
#9
MrZihan
closed
2 years ago
1
Access to Video Dataset
#8
dneirfi
closed
2 years ago
0
Fine-tuning on VCR dataset
#7
yanan1989
closed
2 years ago
3
Access to Video Dataset
#6
HellwayXue
closed
2 years ago
0
How to access the video dataset
#5
Minji-Seo
closed
3 years ago
2
Question about merlot model
#4
ZihaoZheng98
closed
3 years ago
4
Access to video dataset?
#3
aleSuglia
closed
3 years ago
2
Fine-tune on TVQA dataset
#2
Curry-AI
opened
3 years ago
5
How to download pre training model
#1
Curry-AI
closed
3 years ago
1