| | |
Summary: Unsupervised Learning of Human Action Categories
Juan Carlos Niebles1,2, Hongcheng Wang1, Li Fei-Fei1
1
University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA
2
Universidad del Norte, Barranquilla, Colombia
Email: {jnieble2,hwang13,feifeili}@uiuc.edu
DESCRIPTION
Imagine a video taken on a sunny beach, can a computer au-
tomatically tell what is happening in the scene? Can it identify
different human activities in the video, such as water surfing,
people walking and lying on the beach? To automatically
classify or localize different actions in video sequences is very
useful for a variety of tasks, such as video surveillance, object-
level video summarization, video indexing, digital library
organization, etc. However, it remains a challenging task for
computers to achieve robust action recognition due to cluttered
background, camera motion, occlusion, and geometric and
photometric variances of objects. For example, in a live video
of a skating competition, the skater moves rapidly across
|
