Gist of a Gest: Can Machines Recognize ?Almost? Spontaneous Gestures?

Speaker:  Juan Pablo Wachs – West Lafayette, IN, United States
Topic(s):  Architecture, Embedded Systems and Electronics, Robotics

Abstract

Humans are able to understand meaning intuitively and generalize from a single observation, as opposed to machines which require several examples to learn and recognize a new physical expression. This trait is one of the main roadblocks in natural human- machine interaction. Particularly, in the area of gestures which are an intrinsic part of human communication. In the aim of natural interaction with machines, a framework must be developed to include the adaptability humans portray to understand gestures from a single observation. This problem is known as one-shot gesture recognition, and it has been researched previously. Nevertheless, most approaches rely heavily on purely numerical solutions, and leave aside the mechanisms humans use to perceive and execute gestures. This gap leads to suboptimal solutions. A framework is discussed to incorporate the processes of cognition, perception and execution related to gesturing to the paradigm of one-shot gesture recognition. The performance of the method is evaluated in terms of independence from the classifying method, efficiency in terms of comparing to traditional N-shot learning approaches, and coherence in recognition among machines (robots) and humans.

About this Lecture

Number of Slides:  51
Duration:  45 minutes
Languages Available:  English
Last Updated: 

Request this Lecture

To request this particular lecture, please complete this online form.

Request a Tour

To request a tour with this speaker, please complete this online form.

All requests will be sent to ACM headquarters for review.