[Colloquium] Talks at TTIC: Joseph J. Lim, MIT

[Dawn Ellis]

When:     Thursday, March 12th at 11am

Where:    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526

Who:       Joseph J. Lim, MIT

Title:       Toward understanding everyday objects

Abstract:
The computer vision community has made impressive progress on object
recognition and detection using large scale data. However, for any visual
system to interact with objects, it needs to understand much more than
simply recognizing where the objects are -- it needs to find their pose in
3D, understand their various states and transformations, and relate one to
another. In this talk, I will focus on 3D object pose estimation. Precise
pose estimation is a hard problem. One reason is that how an object appears
inside a photograph can vary a lot based on different conditions (e.g.
location, occlusions, and lighting). I address these issues by utilizing 3D
models directly. The goal is to develop a method that can exploit all
possible views provided by a 3D model – a single 3D model represents
infinitely many 2D views of the same object. I have developed a method that
uses the 3D geometry of an object for pose estimation. Despite providing
explicit geometric information, 3D models typically lack fine-details such
as texture, lighting, and exact shape, and any contextual information such
as common occlusions and part discriminativeness. I will talk about how to
learn these real world statistics (e.g. which parts are commonly occluded
or discriminative) from a small number of annotated photographs. These
methods are able to localize and estimate the exact pose of objects in
natural photographs. Finally, I will describe my other works and future
plans in fine-grained object understanding.

Bio:
Joseph Lim is a PhD student in the Department of Electrical Engineering and
Computer Science at Massachusetts Institute of Technology (MIT), where he
is advised by Professor Antonio Torralba. His research interests are in
computer vision and machine learning. He has been motivated by the goal of
building computer systems that automatically understand visual scenes in 2D
and 3D. Joseph graduated with BA in Computer Science from UC Berkeley,
where he worked under Professor Jitendra Malik. He was awarded the National
Science Foundation Graduate Research Fellowship in 2009.

Host:  Matthew Walter,  mwalter at ttic.edu


-- 
*Dawn Ellis*
Administrative Coordinator,
Bookkeeper
773-834-1757
dellis at ttic.edu

TTIC
6045 S. Kenwood Ave.
Chicago, IL. 60637
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20150305/85a330be/attachment-0001.htm