Susumu Seki

Learn More
In this paper, we propose a response model for a multi-modal human interface, by inserting listener responses particular times by detecting keywords from the user's utterances and controlling the face direction of a human-like Computer Graphics (CG) character according to the direction of the user's attention which is determined by tracing user's face. Then(More)
Binocular vision has several advantages as compared with monocular vision. In this study, objective recordings of binocular functioning were studied with visual evoked potentials (VEP's). Lenses from plano through +1.50 D were added to reduce acuity monocularly and binocularly. Results indicate that the VEP, while sensitive to binocularly induced blur, does(More)
This research focuses on the relationship between turn-taking and intensity of motions (head, hand and upper body motions). We examine five spontaneous dialogues conducted in Japanese, which were collected using video and audio recording equipment, and optical motion sensing device. We show first that the motions appear more in speech duration than in(More)
In this paper, we describe a multimodal interface prototype system based on Dynamical Dialogue Model. This system not only integrates information of speech and gestures, but also controls the response timing in order to realize a smooth interaction between user and computer. Our approach consists of human-human dialogue analysis, and computational modeling(More)
We propose a new appearance-based feature for real-time gesture recognition from motion images. The feature is the shape of the trajectory caused by human gestures, in the "Pattern Space" defined by the inner-product between patterns on frame images. It has three advantages, 1) it is invariant in term of the target human's position, size and lie, 2) it(More)
  • 1