Yui010206 / SeViLA

[NeurIPS 2023] Self-Chained Image-Language Model for Video Localization and Question Answering

https://arxiv.org/abs/2305.06988

Yui010206/SeViLA Issues

finetuning result is so bad when using my pretrained checkpoints on QVhighlights.
Closed a year ago3
How to load the parameters of vit and t5?
Closed 7 months ago1
Problem on NextQA Inference
Closed 8 months ago2
About Localizer
Closed 7 months ago1
Performance gets worse when using Localizer that has been self-refined on the QA dataset
Updated 7 months ago
Problem during inference with VLEP
Updated 7 months ago
HF Spaces demo not working ?
Closed 7 months ago1
AttributeError:'NoneType' object has no attribute 'storage'
Updated 7 months ago
The warning of missing keys
Closed 8 months ago2
Problems encountered when running the inference script
Closed 8 months ago1
what is the meaning of frame_num and answer_num?
Closed a year ago6
Can you provide the file qformer_loc.pth？
Closed 9 months ago1
FileNotFoundError: [Errno 2] No such file or directory: '/nas-hdd/shoubin/pretrained_model/hub/checkpoints/qformer_loc.pth
Closed 9 months ago
Can the model infer on open-ended questions?
Closed 9 months ago1
How to fintune on my own data?
Updated 10 months ago
the results on STAR is lower than paper
Updated 10 months ago1
How to define answer_id?
Closed a year ago1
BLIP2 run scripts
Closed a year ago
The result of inference cannot be found in the paper
Closed a year ago5
Could you please provide a sample to show annotation files after processing?
Closed a year ago1
How many GPUs are required for inference?
Closed a year ago1
There is a writing error in the paper
Closed a year ago2