AI & Enterprise
TwelveLabs launches Pegasus 1.6 video understanding model, expands beyond media to physical AI
Multimodal video understanding AI company TwelveLabs said on Tuesday it has launched Pegasus 1.6, a vision-language model designed to understand egocentric data, or first-person video. The company said the model supports automating tasks needed to turn such footage into robot training data by segmenting scenes and analyzing actions and interactions. It supports five functions including action segmentation and labeling, dense caption labeling, quality scoring, search and curation, and consent and compliance flagging.
