Rahul Somani

shot-type-classifier. Detecting cinema shot types using a ResNet-50

shot-boundary-detection. There's a good amount of literature on shot boundary detection, and there's a multitude of techniques that work successfully for hard-cuts, and more modern techniques like neural networks for fades/dissolves, wipes, etc. In this repository, I survey and implement/use tools to detect cuts with different kinds of content.

videoutils. Read videos using OpenCV with ease.

logseq-reference-manager. Reference manager for importing from Zotero locally and from the Web clipper

video-classification. Exploring and understanding existing open-source video-classification tools and models

jupyter-custom-theme. CSS

zed-markdown-fold. Rust

rsomani95.github.io. Personal Website

icevision. End-to-End Object Detection Framework - Pluggable to any Training Library: Fastai, Pytorch-Lightning with more to come

ClipShots_basline. This is our implementation of deepSBD for ClipShots dataset.

icevision-training-scripts. Jupyter Notebook

clipyard. A lightweight wrapper around `yt-dlp` that aims to make downloading large video datasets easier and faster through a simple CLI

logseq-web-clipper. A Logseq port of the Obsidian Web Clipper