MikeWangWZHL / VidIL

Pytorch code for Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners

MikeWangWZHL/VidIL Issues

The linked files and paper descriptions contains different numbers of Object and Attribute Synset
Closed 10 months ago1
Questions about Pipeline for Frame Captioning and Visaul Tokenization
Updated a year ago
someting about datasets
Closed a year ago1
Code for Getting GPT-3 Response
Closed 2 years ago1
QA about the text-video retrieval result in the paper.
Closed 2 years ago1
Custom dataset preparation
Closed 2 years ago1
About VLEP TV
Closed 2 years ago2
Computing BLIP baseline for 4 metrics on MSRVTT caption
Closed 2 years ago2
Getting the VidIL output captions
Closed 2 years ago1
Dockerfile content
Closed 2 years ago1
Download dataset error
Closed 2 years ago3