Vision Meeting, 13 Nov 2002
Time: 10:00 am
Place: CSB 632
Speaker: Chen Yu
Title: Understanding human behaviors in the context of embodied language learning
Abstract
Language is about symbols and those symbols must be learned during human development. Most recently, there has been an increased awareness of the essential role of the human body in grounding those symbols. The challenge ahead is to develop formal models of language acquisition that can shed light on the leverage provided by embodiment. In this presentation, I will firstly give an overview of the embodied language acquisition system that we are developing. Then I will focus on action recognition that has traditionally been addressed by processing fixed camera observations while ignoring non-visual information. In this work, we explore the dynamic properties of the movements of different body parts in natural tasks: eye, head and hand movements are quite tightly coupled with the ongoing task. In light of this, our method takes an agent-centered view and incorporates an extensive description of eye-head-hand coordination. With the ability to track the course of gaze and head movements, our approach uses gaze and head cues to detect agent-centered attention switches that can then be utilized to segment an action sequence into action units. Based on recognizing those action primitives, parallel hidden Markov models are applied to model and integrate the probabilistic sequences of the action units of different body parts.
Vision Meeting coordinator: Andrew Learn
Last modified: Thu Sep 26 13:16:23 EDT 2002