Core Technologies

Based on the foundation of proprietary technologies and a core “brain” built on a deep learning platform, SenseTime has rapidly opened up AI application in multiple vertical scenarios.

High Volume Video Comprehension and Mining

High Volume Video Comprehension and Mining

Technical Capabilities

Video Content Review
Video Labelling
Video Content Structuring
Video Summarization
2D-to-3D Video Conversion
Ultra HD Video Super-Resolution

Video Content Review

Combining video classification, small sample size learning, OCR, video fingerprinting and other algorithms, our technology accurately identifies advertisements and illegal content including pornography, violence, and horror, significantly improving the efficiency of video content review and enabling a better and healthier Internet.

Video Labelling

Using industry-leading large-scale multi-label tagging algorithm, our technology automatically comprehends video content, and automatically generates text labels to help improve the performance of video search and video recommendation. With a comprehensive labelling system, the technology has been successfully applied to various industries including mobile Internet, television, advertising, etc.

Video Content Structuring

By automatically analyzing and extracting key elements from the video (such as stars and celebrities, human behaviors, fashion and apparel, certain scenes, logos and merchandises), our technology provides rich, structured information for efficient video materials management and targeted marketing.

Video Summarization

Based on self-developed deep learning algorithm, our technology analyzes the content and style of each shot in a long video, discovering the intrinsic relations among scenes, people and activities in each shot, and extracts the key information for a short video summary. This technology has been applied to the industry of television, mobile Internet and more.

2D-to-3D Video Conversion

By imitating the 3D cognition abilities of human eyes, our technology automatically converts 2D videos into 3D ones, which enhances the stereoscopic effect of the video and saves labor costs significantly. Our technology can be used in industries including but not limited to movie, television, advertising, live streaming and so forth.

Ultra HD Video Super-Resolution

Ultra HD video super-resolution converts videos to any resolution and size. Using deep learning algorithm, our technology converts transmitted low-resolution video to high-definition video for a clearer picture quality and a better viewing experience.