Giters
microsoft
/
XPretrain
Multi-modality pre-training
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
465
Watchers:
14
Issues:
38
Forks:
36
microsoft/XPretrain Issues
Is there no classification in the HD-VILA dataset?
Updated
24 days ago
Comments count
1
about clipvip-vit-16 pretrained weights file
Updated
a month ago
Pretrained Checkpoints of CLIP-VIP
Updated
2 months ago
Code for transcript text processing
Closed
2 years ago
Comments count
26
About activitynet captions dataset in CLIP-ViP
Updated
2 months ago
Pretrained Checkpoints of LF-VILA
Closed
2 months ago
Comments count
1
Hi, how to understand the LF-hdvila-8m?
Updated
3 months ago
Comments count
1
Code for transcript text processing
Updated
4 months ago
Comments count
1
Dockerfile and requirements for Clip-ViP
Updated
5 months ago
About LF-VILA code in PatchEmbed3D of video encoder
Updated
5 months ago
Error on starting horovod
Updated
6 months ago
Asking for a simple script to get text and video features
Updated
7 months ago
Comments count
8
Model checkpoints
Updated
10 months ago
Error in finetuning
Updated
10 months ago
Comments count
1
video caption of HD-VILA-100M Dataset
Closed
10 months ago
Comments count
1
How long does CLIP-VIP pretraining takes?
Updated
a year ago
Comments count
1
About the zero-shot performance
Closed
a year ago
Comments count
1
About the zero-shot performance
Closed
a year ago
Comments count
2
where are the train9k.jsonl and test1ka.jsonl files in MSRVTT retrieval?
Closed
a year ago
Comments count
3
Where is the MSRVTT json file in CLIP-ViP?
Closed
a year ago
Comments count
2
CLIP-VIP OFA caption generate
Closed
a year ago
Comments count
1
MSR-VTT fine tune epochs number
Closed
a year ago
Comments count
2
Ways to open the .mdb caption files
Closed
a year ago
Comments count
2
Captions for HD-ViLA-100M
Closed
a year ago
Comments count
1
How to prepare pretrain data for LF-VILA?
Closed
a year ago
Comments count
2
How to use HD-VILA as multimodal TextEncoder?
Closed
a year ago
Comments count
3
Video compression/decoding methods of each dataset in CLIP-ViP
Closed
a year ago
Comments count
1
About OFA-Caption generated captions on HD-VILA-100M
Closed
a year ago
Comments count
1
Question regarding video proxy mechanism in CLIP-ViP
Closed
a year ago
Comments count
4
Reproducing the result of CLIP-ViP performance on MSRVTT
Closed
a year ago
Comments count
4
In CLIP-ViP, what is the results of OFA captions + HD-VILA-10M?
Closed
a year ago
Comments count
1
Questions about HD-VILA
Closed
2 years ago
Comments count
4
[CLS] token in CLIP-ViP
Closed
2 years ago
Comments count
2
releasing code and pretrain
Closed
2 years ago
Comments count
3
Long Video Processing in LF-VILA
Closed
2 years ago
Comments count
3
Where can i get the asr text
Closed
2 years ago
Comments count
1
where to download the ASR transcriptions?
Closed
2 years ago
Comments count
1
HD-VILA-100M dataset, where is the text corresponding to each video?
Closed
2 years ago
Comments count
2