Md Mohaiminul Islam

icon indicating a website link https://md-mohaiminul.github.io/

icon company PhD Student, UNC Chapel Hill icon location Computer Vision, Multi-modal deep learning

Results 3 issues of Md Mohaiminul Islam

How to download narrations?

Setup for BBC and OVSD datasets.

Hi, Thanks for this wonderful work. Can you please release the setup and instruction for how to run on the BBC and the OVSD datasets?

LLaVA-Video-7B performance on NExt-QA

In the LLaVA-Video paper, the reported performance of LLaVA-Video-7B on NExt-QA is **83.2**. However, I used lmms-eval and the following command; I got **80.46**% Accuracy. Why this is a mismatch?...