Partnership with Arvato Bertelsmann and VidiNet

vidispine und deepva kooperation

AI is becoming more and more prevalent in our everyday lives, but less than 6% of companies in the media and entertainment industry are using AI in the form of computer vision, voice recognition, or natural language processing. Often, the current AI offering does not provide the added value that was hoped for. Thus, it […]

Visual Concepts Recognition Screencast

DeepVA Recognition of objects and scenes

For media companies and broadcasters, it’s not only essential to recognize people in their content. It’s equally important to get a general understanding of what is happening in their videos and when. With DeepVA’s Visual Concepts Recognition it’s possible to detect and identify different objects and scenes to gain even more meaningful metadata! Find out […]

Face Dataset Creation Screencast

Create training data in seconds

Although we already provide tools that make the creation of your own AI models super easy and intuitive, we still have found ways to further reduce the effort needed. With DeepVA’s Face Dataset Creation, we detect people in videos, extract high-quality images of them and store them in a labeled dataset. This way, the user […]

DeepVA Custom Model Training Screencast

Custom ai model training with deepva

The biggest challenge for media industries when it comes to using AI efficiently, is the necessity of training their own AI model to guarantee promising results. Out-of-the-box recognition services are often not practicable for media companies with high quality standards regarding the creation of visual content. Therefore, we have developed DeepVA, an AI platform to […]

Landmark Recognition Screencast

Landmark recognition screencast

Some content might require the integration of certain landmarks or architectural structures, for example for showcasing a city. Also tourists may like to gather additional information on buildings they have taken pictures of. DeepVA’s Landmark Recognition is very useful to retrieve pictures or videos of a certain building by keyword search and get an abundance […]

Face Recognition Screencast

Face recognition screencast

With the growing amount of video and images available to consumers, the importance of structuring and managing media content increases. To help to achieve this goal, we developed DeepVA’s Face Recognition, which helps our users to instantly locate specific people in any form of visual content by simply providing a name. Face Recognition can be […]

Diversity Analysis Screencast

Diversity analysis

Nowadays, the media has a great responsibility to make sure that their produced content meets the requirements of the audience. This includes conveying true and appropriate information and ensuring the correct representation of different genders, age or demographic information. To support this endeavor, we developed the Diversity Analysis which helps our customers to meet the […]

Dataset Management Screencast

How to simplify dataset management

A dataset is a collection of images that can be used as training data for your custom AI model. Without proper tools, creating and managing a dataset can be complicated for the client. Thus, we developed functionalities that help our users to build the optimal dataset for training an AI, including automated suggestions on how to improve your dataset and the easy and intuitive handling of images. With DeepVA’s Dataset Evaluation, you will make the most of your […]