In this paper we describe new methods to detect semantic concepts from digital video based on audible and visual content. Temporal Gradient Correlogram captures temporal correlatio...
This paper presents a multi-output regression model for crowd counting in public scenes. Existing counting by regression methods either learn a single model for global counting, or...
Ke Chen, Chen Change Loy, Shaogang Gong, Tao Xiang...
Abstract. We are exploring an application for a novel direction in humancomputer interaction named ‘cultural computing’, which aims to provide a new medium for cultural transla...
Intuitive 3D surface control and deformation are crucial to CAD/CAM. To do this in a virtual environment, however, the technique must be very efficient. A common method for shape ...
Lizhuang Ma, Rynson W. H. Lau, Jieqing Feng, Qunsh...
We present a novel framework for characterizing signals in images using techniques from computational algebraic topology. This technique is general enough for dealing with noisy mu...