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

Latest Google Feature Provides Shortcut to Video Highlights

Google introduced Key Moments, a feature that enables users to find shortcuts to video highlights. A search for a how-to video, for example, will bring up links that creators have time-stamped. According to Google, the feature will also make video easier to find for people using screen-reading software to navigate the Internet. Key Moments will first appear in English for YouTube videos time-stamped by the creators. It is limited to a small number of creators but those interested can sign up for early access. Continue reading Latest Google Feature Provides Shortcut to Video Highlights

Facebook’s VideoStory Relies on AI to Automate Storytelling

Facebook’s video clips get over 8 billion views a day on average, but people with bad Internet connections or disabilities often don’t have access to them. That led Facebook to create VideoStory, which the company described in a research paper as “A Dataset for Telling the Stories of Social Media Videos.” The paper, to be delivered at the Conference on Empirical Methods in Natural Language Processing, noted that, “automatically telling the stories using multi-sentence descriptions of videos would allow bridging this gap.” Continue reading Facebook’s VideoStory Relies on AI to Automate Storytelling