Newsbridge announced MXT-1, an AI indexing technology designed to generate human-like descriptions of video content using natural language models. This technology allows him to index over 500 hours of video per minute.
Newsbridge co-founder and CTO Frederic Petitpont says MXT-1 is a significant breakthrough in content indexing and discovery. The technology combines multiple AI modalities, including computer vision, speech processing, and natural language models, to produce impressive results.
MXT-1 is specially trained on a wide range of media, entertainment and sports audiovisual content, making it highly effective for indexing and search purposes in these industries.
Newsbridge hopes MXT-1 will dramatically reduce the cost of using AI at scale, making mass indexing of media assets a business reality. The MXT-1’s reduced energy consumption makes AI indexing seven times more cost-effective than mono- or unimodal AI systems.
One of the main advantages of MXT-1 is the ability to describe scenes in natural language. The technology links raw modalities such as faces, text, logos, landmarks, objects, actions, shot type detection and transcription to generate semantic descriptions for enhanced searchability. MXT-1 is a significant improvement over existing AI indexing solutions that often produce disjointed collections of tags that fail to provide content owners with the information they need.
Currently in beta mode, MXT-1 is gradually being incorporated into all of Newsbridge’s cloud solutions, including Just Index, Media Hub, Media Marketplace and Live Asset Manager.
State-of-the-art design, manufacturing and engineering
Subscribe to NewscastStudio to get the latest news delivered straight to your inbox.
