wachman.sm.gif
Joshua Wachman


Alumnus: Masters in Media Arts and Sciences

Research interests:
Getting a handle on the content of humorous video sequences by analyzing mutliple features.

Advisor: Prof. Rosalind 'Roz' Picard

Education:
S.M. Arts and Media Technology , 1996
Perceptual Computing Section, Vision and Modeling Group
Massachusetts Institute of Technology

Self-directed curriculum in Media Technology,
(currently offered as The Program in Media Arts and Sciences)
S.B. Department of Architecture
Massachusetts Institute of Technology , 1990

Publications:
1) A Video Browser that Learns by Example , MIT Masters Thesis, 1996
(aka: Understanding Seinfeld )
See MIT Media Laboratory Technical Report #383 to download full PostScript version

2) Unsupervised Cross-Modal Characterization of Expressive Gesture in Professional Monologue Discourse
(aka: Understanding Jay Leno's ) Joke Detector
by Michael Casey and Joshua Wachman
To appear at WIGLS, October 1996
See MIT Media Laboratory Technical Report #392 to download full PostScript version


Experience:
Research Assistant
MIT Media Laboratory, Perceptual Computing Group, 1995 - 1996
Consultant
Sony Coroporation of America , Sony Development, Entertainment Technology Group, 1994
Technical Staff
Walt Disney Imagineering , Research & Development, 1990-1994

Research Description

wachman.research.sm.gif

What the heck is that?

This is an image from our final class project in Machine Understanding of Video (spring 95). The boxes bound the area in which Jay moves his head and hands while giving his monologue. The dots represent his head and hand positions during the performance.

In this group project, we measured four features of Jay Leno's monologue on "The Tonight Show with Jay Leno" . Our goal was to see what speech and gesture reveal about what someone is saying.

In the audio domain, we measured the distribution of pauses in the monologue and tracked the pitch of the voice. In the visual domain, we tracked the hand positions and measured their velocities.

We used the isodata clustering method to characterize our feature space. This method plots each feature as a vector in a space and simply finds clusters. The scattering of the clusters is a measure of the salience of the features.

We were able to automatically find portions of Jay's monologue in which he makes large gestures at long pauses in his speech. In practice, this usually corresponds to a point of emphasis and occurs at the conclusion of a joke.

We think we built the first computer joke detector!

Contributers to this work were Mike Casey, and Chris Wren.
Interests
Cinema, Photography, Swimming, Cooking

Birthplace
Bahston, MA.

But I grew up in

Lexington, MA.

Favorite book
Les Miserable, Victor Hugo

Most wishes to have dinner with
dessert


The Vismod Home Page