I am a Final Year Electrical Engineering Student at the University of Engineering and Technology, Lahore. My expertise are in the field of backend development using Python/Django and applying ML Algorithms.
Built a Few Shot Video Captioning Framework leveraging SigLip pretrained vision language model. Implemented frame extraction and visual embeddings pipelines using Python and Pytorch. Proposed Temporal Scope Attention module to model temporal dependencies across different video frames. Fine tuned the model using prototypical contrastive learning for improved caption generation under few shot scenarios. Conducted experiments on MSVD and MSR-VTT datasets and evaluated model performance using BLEU, METEOR, And Cider metrics.
Final Year Student. Focusing on the intersection of hardware and software, with specific coursework in programming, signals and systems, and machine learning.