This is the official repository for the paper titled "Unlocking Visual Tool Reasoning in Language Models via Perception Programs" accepted to CVPR 2026.

The official implementation of "Panoptic Pairwise Distortion Graph" paper accepted at ICLR 2026

[ NeurIPS 2024 ] The official PyTorch implementation for Learning Truncated Causal History Model for Video Restoration.

My solutions to LeetCode Problems

A calorie monitor android application with automated food detection.

Analyzing and drawing insights from historical NYPD shooting incidents data.

This repository contains code for learning slum segmentation and localization using satellite imagery.

A tensorflow implementation of pair-wise and patch-wise self attention network for image recognition.

🕶 A curated list of Tiny Object Detection papers and related resources.

🔥 TensorFlow Code for technical report: "YOLOv3: An Incremental Improvement"

A whale sound detector using spectrograms

Drawing insights from COVID-19 data

Deep Learning Study Group

Machine learning glossary

TextBoxes: A Fast Text Detector with a Single Deep Neural Network

Detecting Text in Natural Image with Connectionist Text Proposal Network (ECCV'16)

Linux kernel source tree

Caffe2 is a lightweight, modular, and scalable deep learning framework.

Code for generating synthetic text images as described in "Synthetic Data for Text Localisation in Natural Images", Ankush Gupta, Andrea Vedaldi, Andrew Zisserman, CVPR 2016.

Vehicle Detection, Tracking and Counting