This paper investigates the problem of learning the visual semantics of keyword categories for automatic image annotation. Supervised learning algorithms which learn only a single ...
The CollabLogger is a visual tool that supports usability analyses of human-computer interaction in a team environment. Participants in our computer-mediated activity were engaged...
Many authors in the field of 3D human computer interaction have described the advantages of 3D user interfaces: Intuitive metaphors from daily life, immersive workspaces, virtual ...
In this paper, we present a novel multiple kernel method to learn the optimal classification function for visual concept. Although many carefully designed kernels have been propose...
Multi-stream hidden Markov models (HMMs) have recently been very successful in audio-visual speech recognition, where the audio and visual streams are fused at the final decision...