[ICCV19] AdaptIS: Adaptive Instance Selection Network, https://arxiv.org/abs/1909.07829

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

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

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

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

Fast and accurate Human Pose Estimation using ShelfNet with PyTorch

Code for the paper "Semantic Object Accuracy for Generative Text-to-Image Synthesis"

Helper for dealing with MS-COCO annotations

Object Detection for Video with MXNet and GluonCV using YOLOv3

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.

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

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

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

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

Computer Vision with Microsoft CNTK

Used deep learning to train a CNN + RNN/LSTM on the MS-COCO dataset to automatically generate captions.

A system to process visual input on timed frames to produce sensible audio aid in accordance with human information processing limits, using image captioning, semantic text comparison and text-to-speech modules.

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

A collection of semantic segmentation approaches

labeling tool that allows easy plugin of detection networks that can assist in the labeling process

Side projects and Hands-on projects from the Technion's course

MS-COCO-ES is a dataset created from the original MS-COCO dataset. This project aims to provide a small subset of the original image captions translated into Spanish by humans annotators. This subset is composed by 20,000 captions of 4,000 images.