Here’s another great Two Minute Papers video on DeepMind’s venture into computer vision.
In this age of PhotoShop and Instagram filters, detecting a real image from an altered one is getting more difficult.
Naturally, there’s an AI research paper for that. Watch this video by Two Minute Papers to learn more.
Content moderation is the process of monitoring for possible offensive, undesirable, and risque content.
Content Moderator, a Cognitive Services product, combines machine-assisted content moderation APIs and human review tool for images, text, and videos into a complete content moderation solution. In this episode, we will get an overview of Content Moderator and learn about its video moderation capabilities.
In this video, learn about the API and the human review capabilities in Content Moderator.
Here is a primer to introduce the concepts of deep learning with a specific focus on computer vision. It covers concepts including CNN’s (Convolutional Neural Networks), deep learning and transfer learning. It was created as an introduction for people getting started with machine learning and specifically deep learning to explain some of the commonly used terms and introduce some of the popular approaches to solving computer vision challenges.
Siraj Raval demonstrates how to use TensorFlow to track people’s facial expressions and body positions with a regular webcam.
Ruth shows how to use Azure Custom Vision to train a model to recognize a modern Mercedes-Benz car keys since the design does not look like a traditional key. Then shows to how to call the generated REST API from the trained model in a Java application that displays tags and description of uploaded images.
In this video, Seth and Noel take a lap through Microsoft Cognitive Services and cover the updates and enhancements made public at the BUILD 2018 conference.
In this video from the Ignite conference last September, watch the latest additions to the Cognitive Toolkit, which offer a Python API, as well as a GUI to have a non‐disruptive experience from data load through operationalization with all the steps in between.
The goal is to support classification, object detection and image similarity use case. This is a work in progress. In this session, they demonstrate only a classification pipeline.
This video demonstrates how to use the CNTK libraries to build out a simple image classifier using a neural network.