Richard Russell - MIT

Richard Russell - MIT

Richard Russell Graduate Student [email protected] The Problems: Which computational image similarity metrics correspond most closely to human impres...

2MB Sizes 0 Downloads 5 Views

Recommend Documents

Richard Russell - Advisor Perspectives
Richard Russell. December 2, 2015 by Jeffrey Saut of Raymond James. A couple of weeks ago I wrote a strategy report titl

CV - Richard Russell
Richard Russell CV page 2 of 9. Russell, R., Kramer, S.S., & Jones, A.L. (In press) Facial contrast declines with age bu

Stock Guide - Richard Russell
SIZE CONVERSIONS. Metric (mm). Feet. Inches. 915 X 610. 3 X 2. 36 X 24. 915 X 915. 3 X 3. 36 X 36. 1220 X 610. 4 X 2. 48

Richard Russell -
Richard Russell. 2114 Lear Ln. Austin, TX 78745 (512) 299-1261. Relevant. Experience. 5 years of experience managing e-c

Richard A. Russell
Richard A. Russell is a former Senior National Intelligence Service. Executive who served in progressively responsible p

richard russell - University of Miami
RICHARD RUSSELL. HEIGHT: 6'2”. Cell (630)605‐3818. WEIGHT: 200 LBS. [email protected] Theater. Almos

RICHARD RUSSELL. Defender. Pursuer: Crosbie, Solicitor. Defender: Party Litigant. Glasgow, 4 October 2017. The sheriff h

Rich Man, Poor Man – Richard Russell
By Richard Russell. The most popular piece I've published in 40 years of writing these Letters was entitled, "Rich Man,

14h15 Richard Russell Green Development - Green Building
KUALA LUMPUR, MALAYSIA. 1985-2016. 1,427,000 – 6,837,000. Page 4. CHONGQING, CHINA. 1985-2016. 3,000,000 – 14,200,00

Richard Russell, Bishop of Glasgow and Galloway's
Jun 14, 2011 - Richard Russell, Bishop of Glasgow and Galloway's. 1292. Sculptor: Unknown. Town or Village. Parish. Loca

Richard Russell Graduate Student [email protected]

The Problems: Which computational image similarity metrics correspond most closely to human impressions of image similarity? How can image compression be optimized? What makes images look similar or dissimilar? How do humans perform comparisons of images?

Comparisons of different image similarity metrics L1 match Σ | xi-yi |

Original Image

L2 match Σ (xi-yi)2

Vector quantization style image compression using different similarity metrics L1 Metric


L2 Metric

What I like most about MIT/Cambridge: - ‘All under one roof’ - living in Boston - free espresso

What I like least about MIT/Cambridge: - expensive - winter - can’t buy booze on Sunday

Yuri Ostrovsky Graduate Student [email protected]

The Problems: What is the role of 3D in image processing? Does 3D scene information facilitate object search? How are different 3D scene attributes, such as illumination, represented by the visual system? Does object recognition influence 3D form perception?

Exploring the influence of 3D scene layout on visual search

Instant Good3D advantage


How fast do people find objects in Good3D vs. Bad3D?


Good 3D

2800 2600

Bad 3D

Reaction Time (ms)

2400 2200 2000 1800 1600 1400 1200 1000 1


3 4 5 Trial Number for a Given Word


Amount of training Bad3D


Exploring the representation of 3D scene attributes such as illumination

What I like most about MIT/Cambridge: - The inexhaustible supply of nerdy rhetoric - Those charming long-time residents that scream at you for riding your bike on the sidewalk - Parades, parades, parades

What I like least about MIT/Cambridge: - Too much sunshine

Javid Q. Sadr Graduate Student [email protected]

The Problems: Can we develop a unified experimental paradigm for exploring different issues in object perception? What are the neural correlates of conscious object percepts? Can we develop novel, quantitative measures of object agnosias, development, and priming? How are object concepts learned, especially in the absence of supervision and image normalization?

The RISE Paradigm for Exploring Issues in Object Perception Idea of Object-Image Space and Random Image Structure Evolution....

... Phase RISE

... Bit-Flip RISE

manipulate phase

A sample RISE sequence

What I like most about MIT/Cambridge: - the Rev. Sayan Mukherjee, Ph.D. - Top-Notch Local Weather Coverage - Dirty Deeds, Done Dirt Cheap - The Cambridgeport Saloon - Community-Based Policing

What I like least about MIT/Cambridge: - WHAT ! - SOMEONE SET UP US THE BOMB !

Jodi Davenport Graduate Student [email protected]

The Problems: How do we recognize faces? What aspects of a face do caricaturists capture to make super-recognizable portraits? What features are important for recognizing faces that are blurred or far away? How are objects represented in the brain?

Caricaturists have an intuitive sense of what features make a face recognizable as a unique individual. By creating a database of caricatures and real faces and developing computational schemes for extracting consistencies across the images of specific individuals, we hope to determine what aspects of a face define its recognizability.

Even when faces are far away or blurred and individual features (such as eyes, nose, lips) are difficult to discern, people are still able to recognize specific individuals. One goal is to define the heuristics used by human observers by determining the capabilities and limitations in face recognition with degraded images.

What I like most about MIT/Cambridge: • Students and Faculty with diverse interests. • Academic resources and talks. • Art loan program.

What I like least about MIT/Cambridge: • Tow trucks. • Lack of late night coffee-shops. • Slush.

Keith Thoresz Graduate Student [email protected]

The Problems: How can one extract automatically the invariant features of an arbitrary class of objects? Can a reliable object invariant be learned from a handful of examples? What kind of object model could be used to encode low resolution images to facilitate detection at a distance?

A qualitative invariant object representation. The ratio template is a compact object representation, robust to changes in illumination, noise and image degradation. Emphasizes lowfrequency (low-res) spectral components.

Detection results on faces. Note the range of spatial resolution and illumination differences.

What I like most about MIT/Cambridge: - New England sports (SCUBA, snowboarding) - Student-sponsored activities - Variety of lectures and talks institute-wide - Academic freedom and resources

What I like least about MIT/Cambridge: - No late-night food options - Classes

Antonio Torralba Postdoctoral Associate [email protected]

The Problems: What is the role of contextual information in object recognition? How can we efficiently represent context structure? How can we computationally model contextual influences on object recognition? What are the neural correlates of contextual processing?

Contextual influences in object recognition Object intrinsic features

Object recognition performances %

Object background features



32 c/i



32 c/i



32 c/i


Object in context %

A statistical framework for modeling contextual influences on object recognition Object priming:

1 0

Context driven focus of attention

Outdoor scene. Urban environment. Street. 50-100 meters.

Context driven scale selection

Car Person Traffic signs Furniture … categories

Location of Pedestrian area derived by context-based processing.

Likely pedestrian size derived via contextual cues

What I like most about MIT/Cambridge:

What I like least about MIT/Cambridge: - this guy