Enabling computers to understand natural human communication is a goal researchers
have been long aspired to in artificial intelligence. Since the concept demonstration of “Put …

Previous work on multimodality in interaction has mostly focussed on integrating models for
verbal utterances and embodied modalities like gestures. In this paper, we take a first step …

More recent multimodal systems have moved away from processing simple mouse or
touchpad pointing, and have begun designing systems based on two parallel input streams …

When giving descriptions, speakers often signify object shape or size with hand gestures.
Such so-called 'iconic'gestures represent their meaning through their relevance to referents …

Multimodal behavior has been studied for a long time and in many fields, eg, in psychology,
linguistics, communication studies, education, and ergonomics. One of the main motivations …

Imagine an intelligent system of the sort shown in Fig 1, that allowed humans to interact with
3D holographic display using a combination of modalities, including body pose, hand …

The demand for more sophisticated natural human-computer and human-robot interactions
is rapidly increasing as users become more accustomed to conversation-like interactions …

Humans perceive the world by combining acoustic, visual, and tactile stimuli from their
senses and interact with each other using different modalities of communication, such as …

Multimodal systems extract and convey meanings through different I/O interfaces, such as
voice, writing, gestures, gaze movements, and facial expressions. Increasing the …

During multimodal communication, we speak, shift eye gaze, gesture, and move in a
powerful flow of communication that bears little resemblance to the discrete keyboard and …