Host Institution : INRIA
Laboratory : LJK (CNRS/G INP/UJF/UPMF/INRIA)
Call to project : Advanced (PE6)
Project name: ALLEGRO – Active large-scale learning for visual recognitionAmount : 2,49 M€
A massive and ever growing amount of digital image and video content is available today, on sites such as Flickr and YouTube, in audiovisual archives such as those of BBC and INA, and in personal collections. In most cases, it comes with additional information, such as text, audio or other metadata, that forms a rather sparse and noisy, yet rich and diverse source of annotation, ideally suited to emerging weakly supervised and active machine learning technology. The ALLEGRO project will take visual recognition to the next level by using this largely untapped source of data to automatically learn visual models. The main research objective of our project is the development of new algorithms and computer software capable of autonomously exploring evolving data collections, selecting the relevant information, and determining the visual models most appropriate for different object, scene, and activity categories. An emphasis will be put on learning visual models from video, a particularly rich source of information, and on the representation of human activities, one of today’s most challenging problems in computer vision. Although this project addresses fundamental research issues, it is expected to result in significant advances in high-impact applications that range from visual mining of the Web and automated annotation and organization of family photo and video albums to large-scale information retrieval in television archives.