Researchers Create AI Technique to Generate Video Captions

Researchers at Microsoft Research Asia and the Harbin Institute of Technology have come up with a new technique to use artificial intelligence to generate live video captions. In the past, technologists have used encoder-decoder models, but didn’t model the interaction between videos and comments, resulting in mainly irrelevant comments. The new technique — based on a model that iteratively learns to capture the representations of audio, video and comments — outperforms current methods, according to the research team. Continue reading Researchers Create AI Technique to Generate Video Captions

Onscreen Text Messages Appear in Chinese Movie Theaters

Select movie theaters in Chinese cities have begun experimenting with “bullet screens” (or “danmu”) — a new model in which audience members can comment on the film via text messages and have their impressions projected directly onto the screen. The experience is targeting young viewers who often have difficulty being away from their tablets and mobile phones. The experiment currently involves theaters in major cities including Beijing and Shanghai, in addition to smaller cities such as Hangzhou. Continue reading Onscreen Text Messages Appear in Chinese Movie Theaters