Newsbridge To Feature New MXT-1 Generative AI For Fast Video Indexing At NAB Show

Newsbridge AI tags to tennis image
(Image credit: Newsbridge)

NEW YORK—Newsbridge has introduced MXT-1, a generative AI indexing technology that generates human-like descriptions of video content and is capable of indexing more than 500 hours of video per minute.  The company will show the new technology at the 2023 NAB Show, April 15-19, in Las Vegas.

Particularly useful for those working with media and sports content, the MXT-1 makes searching large collections of video faster, easier and more intuitive, the company said.

“With MXT-1, Newsbridge has achieved an important breakthrough in content indexing and discovery,” said Frederic Petitpont, co-founder and CTO at Newsbridge. “Our new core technology combines multiple AI modalities, including computer vision and speech processing with natural language models. MXT-1 aligns video perception with the power of language models to accomplish incredible results.” 

MXT-1 is specifically trained on hundreds of thousands of hours of media, entertainment, and sports audiovisual content, leveraging AI transformers, making it particularly good at describing content for these industries to index and search for content. MXT-1 reduces to a minimum the time it takes to enhance, sharing and monetize archives, it said.

“Until now, broadcasters faced the tough question of what footage to fully index due to limited media logging resources to transcribe, describe and summarize content,” said Philippe Petitpont, co-founder and CEO at Newsbridge. “MXT-1 dramatically reduces the cost of using AI at scale, making mass indexing of media assets a business reality. With MXT-1, content owners know exactly what is in their files and can shine a light on the hidden gems in their archives.”

MXT-1, with its dramatically reduced energy consumption, makes AI indexing seven times more cost-efficient than mono or unimodal AI systems, the company said.

Newsbridge’s language model links raw modalities, such as detection of faces, text, logos, landmarks, objects, actions, shot types and transcription, to generate a semantic description for increased searchability, it said.

It improves upon the current state of AI indexing, which produces a jumble of tags that fail to give content owners the level of information they need. MXT-1 bundles all the latest evolutions of Newsbridge's multifaceted AI and can be trained and fine-tuned by an end user with multimodal rules and a custom thesaurus, it said.

MXT-1 is available in beta mode now and is being progressively deployed in all of Newsbridge’s cloud solutions, including Just Index, Media Hub, Media Marketplace and Live Asset Manager.

See Newsbridge at NAB Show booth W2073.

More information is available on the company’s website.

Phil Kurz

Phil Kurz is a contributing editor to TV Tech. He has written about TV and video technology for more than 30 years and served as editor of three leading industry magazines. He earned a Bachelor of Journalism and a Master’s Degree in Journalism from the University of Missouri-Columbia School of Journalism.