Shih-Fu Chang

Chang is an active researcher leading development of novel theories, algorithms, and systems for content-based image video search, machine learning, multimedia analytics, as well as media forensics. His work has been influential in shaping the vibrant fields of content-based multimedia retrieval. In the 90’s, he and his students developed several of the first image/video search engines, such as VisualSEEk, VideoQ, and WebSEEk. Other significant developments include large-scale concept-based video search engines (e.g., CuZero), a large public library of image classification models (e.g., Columbia374), international multimedia indexing standards (e.g., MPEG-7 and MPEG-21), and large multimedia ontologies (e.g., LSCOM). In addition, Chang has led cross-disciplinary projects, including a DAVIC Video on Demand international interoperability test, a medical video library under Columbia's Health Care Digital Library, and the ADVENT university-industry research consortium with the participatio