anas2908

Sumotosima

A novel framework and dataset for classifying and generating summaries for otoscopic images of the middle ear, with the objective of developing summaries that are both well-defined and patient-friendly, addressing the challenge of insufficient explanations from medical professionals due to their hectic schedules and limited time per patient.

clip-encoder--t5-decoder-

here I have implemented a transformer by using clip as encoder and t5 as decoder

CLIP_prefix_caption

Simple image captioning model

cv

E-Drone

ImageBind

ImageBind One Embedding Space to Bind Them All

MetaTransformer

Meta-Transformer for Unified Multimodal Learning

Movie-DB

mython

my own programming language which required a good knowledge in compiler designing and TOC one of the core subject of computer science engineering

solidity

solidity from basic to intermediate