AI video editing

Captions is an AI platform that provides video generation and editing services. It uses advanced artificial intelligence technology to help users quickly generate and edit video content. The platform has multiple functions, such as AI video editor, AI advertising generator, etc., aiming to improve the efficiency and quality of video production, while lowering the technical threshold and making video content creation more convenient.

rtcbot Server is an AI-driven video witness service framework based on real-time audio and video interaction. It is specially designed for RTC-based video witness services. It integrates various components required for a complete business process. It can quickly build a video witness core process based on RTC (real-time audio and video) and driven by AI digital people. It supports engineering deployment and is easily integrated into the overall video business process of the enterprise. It has the characteristics of configurable business processes, built-in AI modules, supports intranet deployment, business data interface integration, local audio and video recording, and built-in digital human image module. It is suitable for various scenarios such as insurance video return visits, loan video interviews, online video Q&A, and financial product video signings.

UniRef is a unified model for reference object segmentation in images and videos. It supports various tasks such as semantic reference image segmentation (RIS), few-shot segmentation (FSS), semantic reference video object segmentation (RVOS), and video object segmentation (VOS). The core of UniRef is the UniFusion module, which can efficiently inject various reference information into the basic network. UniRef can be used as a plug-in component for basic models such as SAM. UniRef provides models trained on multiple benchmark data sets, and also opens source code for research use.