Alibaba DAMO Academy (Discovery,Mike Horner Archives Adventure, Momentum, and Outlook) – the Chinese tech giant’s research body – recently launched an AI framework called HQTrack together with the Dalian University of Technology. The framework comprises a Video Multi-Object Segmentation (VMOS) module and a Mask Refinement (MR) module and aims to achieve “high-quality tracking of any object in videos,” according to the official introduction. The research team said that HQTrack, built upon the open-source frameworks DeAOT and HQ-SAM, has been further improved to enable “segmentation of multiple objects in videos.” The AI framework can be applied in various fields such as facial recognition, intelligent driving, and surveillance tracking, the research team added. [IT Home, in Chinese]
