Superpoint Implemented in PyTorch: https://arxiv.org/abs/1712.07629

[ICCV '21] In this repository you find the code to our paper "Keypoint Communities".

[CVPR 2022] Official Pytorch code for OW-DETR: Open-world Detection Transformer

Convert segmentation RGB mask images to COCO JSON format

Code, data and benchmark from the paper "Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming" (NeurIPS 2019 ML4AD)

A PyTorch implementation of the paper: Specifying Object Attributes and Relations in Interactive Scene Generation

Fast and accurate Human Pose Estimation using ShelfNet with PyTorch

Implementation for "Generating Multiple Objects at Spatially Distinct Locations" (ICLR 2019)

Code for "Semantic Object Accuracy for Generative Text-to-Image Synthesis" (TPAMI 2020)

Helper for dealing with MS-COCO annotations

[IJCAI 2022] Official Pytorch code for paper “S2 Transformer for Image Captioning”

Mask R-CNN Model to detect the area of damage on a car. The rationale for such a model is that it can be used by insurance companies for faster processing of claims if users can upload pics and they can assess damage from them. This model can also be used by lenders if they are underwriting a car loan especially for a used car.

[TIP] Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition

This Repo covers all formats of annotations for Object Detection and can easily convert from one form to another using attached scripts

Object Detection for Video with MXNet and GluonCV using YOLOv3

NeuSyRE: A Neuro-Symbolic Visual Understanding and Reasoning Framework based on Scene Graph Enrichment

This repository contains code for YOLO v3 Object detection, and is capable of fast object detection. Input can be given through images, videos and webcam input feed.

[AAAI 2024] Official code for "Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection"

Implementation of Darknet with You Only Look Once (YOLO) in Pytorch

Side projects and hands-on work

Ladder Loss for Coherent Visual-Semantic Embedding, AAAI, 2020

A deep learning based application which is entitled to help the visually impaired people. The application automatically generates the textual description of what's happening in front of the camera and conveys it to person through audio. It is capable of recognising faces and tell user whether a known person is standing in front of him or not.

Civic Issue Detection Dataset from Adversarial Adaptation of Scene Graph Models for Understanding Civic Issues

Drawing and visualizing bounding boxes and key points.

A tool to download and format MS COCO dataset for multilabel classification

Using Image Segmentation for identifying free car parking slots

Intelligent Advertisement Generation for e-commerce websites using deep learning.

Deep learning project that generates natural-language captions for images using CNN for visual feature extraction and LSTM for text generation. Built with TensorFlow/Keras and trained on the MS COCO dataset for AI-powered image understanding.

PyTorch implementation of Conditional Generative Adversarial Networks (cGAN) for image colorization of the MS COCO dataset

Compact Image Captioning (CoCA) is an open source image captioning project to promote Green Computer Vision, as well as to make image captioning research accessible to universities, research labs and individual practitioners with limited financial resources.