object-recognition

A curated list of action recognition and related area resources

SSD: Single Shot MultiBox Detector | a PyTorch Tutorial to Object Detection

The collection of pre-trained, state-of-the-art AI models for ailia SDK

Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness" (ICLR 2019 Oral)

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection, NeurIPS2020

Deep Learning Computer Vision Algorithms for Real-World Use

JavaScript object detection lightweight library for augmented reality (WebXR demos included). It uses convolutional neural networks running on the GPU with WebGL.

Simple project to recognize hands in realtime. 👋 Serves as an Example for building your own object recognizer.

Face mask detection system using Deep learning.

🟣 Object detection of abstract shapes with neural networks

💎 "Marker-less Augmented Reality" with OpenCV and OpenGL.

HAKE: Human Activity Knowledge Engine (CVPR'18/19/20, NeurIPS'20, TPAMI'21)

An example of using Tensorflow with Unity for image classification and object detection.

A curated list of visual relationship detection and related area resources

👁 👂 Smart media tagging for Nextcloud: recognizes faces, objects, landscapes, music genres

A Box detection algorithm for any image containing boxes.

Object-recognition using multiple templates in python

SURF - Speeded Up Robust Features - source code

An example of using Tensorflow and ONNX models with Unity Barracuda inference engine for image classification and object detection.

CORe50: a new Dataset and Benchmark for Continual Learning

Data, code & materials from the paper "Generalisation in humans and deep neural networks" (NeurIPS 2018)

Object Recognition using TensorFlow and Java

A collection of SOTA Image Classification Models in PyTorch

Vehicle make and model classification in Tensorflow by fine-tuning VGG16

High level python script that looks at a folder of video files and tells you which files contain people.

This is the python implementation of openvino models.

The ORBIT dataset is a collection of videos of objects in clean and cluttered scenes recorded by people who are blind/low-vision on a mobile phone. The dataset is presented with a teachable object recognition benchmark task which aims to drive few-shot learning on challenging real-world data.

As a part of the HAKE project (HAKE-Object), code for SymNet (CVPR'20 and TPAMI'21).

Deep Co-occurrence Feature Learning for Visual Object Recognition (CVPR 2017)