DeepVA - The Media's AI

DeepVA is a audiovisual AI-platform that helps companies extract any kind of information from images, videos, and live streams. Gain valuable insights from videos, while minimizing complexity and costs. THE MEDIA'S AI-PLATFORM ----------------------- DeepVA offers you an evergrowing toolset of AI functionalities, easy to integrate into your existing workflows. No matter if it is on-Premises, hybrid or in the cloud, our RestAPI makes integration simple and many software partners already have a ready-to-use integration. * **Simplified - no experts needed, all done with your team.** * **Thrustfull - along European standards.** * **Future-Proof - use state of the art research algorithms, own developments or our services.** AI CUSTOMIZATION ---------------- DeepVA makes AI training predictable and easy to budget. Pre-trained face models quickly reach their limits and, in most cases, do not reflect the needs of the media industry. With the Custom Face Models, DeepVA guarantees the possibility to train individuals and especially region-specific personalities. With Few-Shot Learning, media companies are now able to build their own face models in just a few seconds. Recognizing buildings creates a huge editorial benefit for media companies in their press coverage. With DeepVAs Custom Landmark Model there is now the possibility to easily extend our Landmark Recognition. You are now able to recognize your most relevant landmarks with just a few clicks. Face Indexing is another great way to recognize faces. This state-of-the-art method of face fingerprinting allows media companies to analyze media data followed by assignment of unique IDs. Thus, unknown persons can be described retrospectively across all your media data without the need for further analysis. SPEECH-TO-TEXT -------------- Often the spoken word alone is not enough: transcription is needed. Our Speech to Text function automates this process. The speech recognition algorithms were developed in collaboration with the Fraunhofer Institute. These algorithms make it possible not only to analyse the visual content of the videos, but also to take the audio track into account. Speech-to-Text helps to extract even more detailed metadata from media. You can find out exactly what happens in the video, what it is about, and even what genre it is. The function is perfect for creating automated summaries of the material. And we can even use the voice data to identify speakers, extract trainingmaterial or use custom dictionaries. LIVE RECOGNITION ---------------- All our services are not only designed with file-based assets, but also with Live Broadcating in mind. Our hometurf is the television and media industry, therefore we are rolling out more and more services as live module. KNOWLEDGE GRAPH --------------- Enrich your video metadata with important background information through a powerful knowledge graph. Create more engaging content, better video recommendation engines, or significantly reduce editorial costs. Knowledge Graph recognizes the relationships between people or objects, represents them visually, and thus helps to stay one step ahead of the competition.