issues
search
facebookresearch
/
LaViLa
Code release for "Learning Video Representations from Large Language Models"
MIT License
478
stars
42
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
the output of sentence is not complete
#40
zhaishengfu
opened
2 weeks ago
0
the meaning of demo_narrator.py?
#39
zhaishengfu
opened
2 weeks ago
0
How to get text caption for each frame of video?
#38
zhaishengfu
opened
2 weeks ago
0
About Ego4d dataset
#37
lwpyh
closed
3 months ago
2
Checkpoint of the pre-trained dual-encoder.
#36
AlbertHuyb
opened
4 months ago
1
What is the source of WIT video dataset?
#35
rixejzvdl649
opened
4 months ago
3
val .pkl files for pre-training LAVILA Dual-Encoder
#34
AlbertHuyb
closed
4 months ago
2
Base narrator model
#33
sarisel
closed
6 months ago
0
May be repeatedly loade the checkpoints.
#32
yyvhang
closed
4 months ago
1
Cannot use Huggingface demo
#31
fgvfgfg564
opened
6 months ago
0
EGTEA reproduce
#30
jong980812
opened
8 months ago
1
Run locally on multiple GPUs
#29
maximotus
opened
8 months ago
3
if the model supports Chinese language prompts or narrations?
#28
ruifenggong
opened
10 months ago
1
Extracting spatial feature maps from LaViLa
#27
vineetparikh
opened
11 months ago
0
helper script to convert egovlp checkpoint
#26
zhaoyue-zephyrus
closed
11 months ago
0
add ego4d pre-processing script
#25
zhaoyue-zephyrus
closed
1 year ago
0
Preprocessing of Ego4D for pretraining
#24
chuyishang
closed
11 months ago
2
Training/fine-tuning the narrator
#23
tobyperrett
opened
1 year ago
2
LaViLa as feature extractor
#22
deepsurbhi8
opened
1 year ago
3
The pre-training weights of Dual-Encoder Baseline (with TSF-B/L)
#21
daiguangzhao
closed
1 year ago
1
The pre-training weights of Dual-Encoder Baseline (with TSF-B/L)
#20
daiguangzhao
closed
1 year ago
2
Currently unable to run the demo between Colab and Huggingface.
#19
kuangxiaoye
opened
1 year ago
3
The pretraining weights of TSF-B/L (visual only) on EPIC-KITCHENS-100 and EGTEA.
#18
daiguangzhao
closed
1 year ago
1
About the demo
#17
aa7784171
closed
1 year ago
1
Question about preprocessing Ego4D
#16
hyojinie
closed
1 year ago
2
Normalization values for CLIP models
#15
Jazzcharles
closed
1 year ago
1
Updated `transformers` version and updated import path
#14
gzhihongwei
closed
1 year ago
1
Pretrained weight of HowTo100M
#13
HYUNJS
opened
1 year ago
3
Narrator Training
#12
Flaick
closed
1 year ago
2
Reproducing zero-shot eval results on EK100-MIR
#11
melongua
opened
1 year ago
1
fix #4 potential seg. fault in demo
#10
zhaoyue-zephyrus
closed
1 year ago
0
Train LAVILA (L) to perform action recognition on the EPIC-100 dataset?
#9
daiguangzhao
opened
1 year ago
1
Thank you for contributing such excellent work!
#8
daiguangzhao
closed
1 year ago
1
Resized Version of EK100
#7
SJTUwxz
closed
1 year ago
3
Update PRETRAIN.md
#6
zhaoyue-zephyrus
closed
1 year ago
1
Training narrations for downloading
#5
melongua
closed
1 year ago
1
Segmentation fault when launching demo_narrator [was: Keys remapping seems not to work]
#4
amessina71
closed
1 year ago
9
Training Time
#3
mmaaz60
closed
1 year ago
2
Git clone failing in Colab
#2
nateraw
closed
1 year ago
1
Add models/demo to Hugging Face Hub
#1
nateraw
opened
1 year ago
4