The Visual Computing Database: A Platform for Visual Data Processing and Analysis at Internet Scale

There is strong evidence that a fundamental requirement of the next generation of visual and experiential computing (VEC) applications will be the efficient analysis and manipulation of large repositories of visual data (images, videos, RGBD, point clouds, etc.). For example, highly publicized recent advances in image understanding [24] stem not only from improved deep-learning techniques, but also from the ability to execute these techniques on internet-scale, human-annotated image collections [11, 28, 1, 45]. Analysis of visual data collections is also a major component of other advanced VEC applications such as computational photography, high-level image and video manipulation [19, 26, 25], and 3D scene reconstruction [36] and understanding [14]. Further, with image sensors rapidly becoming ubiquitous in all environments (in public spaces, on vehicles, the body, etc.), we anticipate the emergence of entirely new ecosystems of applications made possible by large-scale mining of streams of visual sensor data. These applications may range from consumer-centric personal assistants, to management of critical infrastructure for transportation and smart cities, and even include data-analysis for fundamental science.