Scenes from Video (SFV) IV is the latest in a series of an invitation-only workshops, which this year will be held in Spain.
SFV aims to bring together experts in the field to focus on the problem of recovering high-level information from images and video. In doing so, we aim to progress the field towards asking, and eventually answering questions that involve a deeper level of understanding of image content.
There is a long history of extracting physical information from video including: camera motion, structure, flow, scene flow, etc. Similarly there is a long history of extracting information from static images including shading, illumination, albedo, shape, object recognition, and scene layout. When SFV started, there was little work drawing these lines of research together to extract rich scene descriptions from video. With new tools like deep learning, research in the area is expanding quickly. The latest SFV will collect the top researchers in the field to describe and discuss the current state and the future.
SFV is structured to allow plenty of time for informal discussion. In addition to the invited technical talks by leaders in the field, there will be an engaging program. To foster communication and community, we ask that invited speakers attend the entire meeting.
The workshop will be held at Castilla Termal Monasterio Valbuena in the beautiful region of San Bernado. The area is full of history and culture, spectacular food and wine, and charming hiking and walking trails. Partners are encouraged to attend.