Posts Tagged ‘video data’

LUCI members get many papers accepted by CHI 2011 - January 27th, 2011

Moleskins and Pens

Photo courtesy of paulworthington

The LUCI lab has had several papers accepted to CHI 2011. The list of accepted works was just released and includes the following by students, researchers, and faculty:

Full Papers:

Situating the Concern for Information Privacy through an Empirical Study of Responses to Video Recording by David Nguyen (LUCI Ph.D.), Aurora Bedford and Alex Bretana (Informatics undergrads) and Gillian R. Hayes (LUCI faculty)

Unpacking Exam-Room Computing: Negotiating Computer-Use in Patient-Physician Interactions by Yunan Chen (LUCI faculty), Victor Ngo and Sidney Harrison (Informatics Masters students) and Victoria Duong (UCI undergrad).

Comparing Activity Theory with Distributed Cognition for Video Analysis: Beyond “Kicking the Tires.” by Eric Baumer (former LUCI post-doc) and Bill Tomlinson (LUCI faculty)

Infrastructures for low-cost laptop use in Mexican schools
Ruy Cervantes (Informatics Ph.D.), Mark Warschauer (Ed. Dept.), Bonnie Nardi (LUCI Faculty), and Nithya Sambasivan (Informatics Ph.D.)

Designing a Phone Broadcasting System for Urban Sex Workers in India
Nithya Sambasivan (Informatics Ph.D.) and Ed Cutrell (Microsoft)

Classroom-Based Assistive Technology: Collective Use of Interactive Visual Schedules by Students with Autism
Meg Cramer (LUCI Ph.D.), Sen Hirano (LUCI M.S.), Monica Tentori (UABC), Michael Yeganyan (LUCI M.S.), and Gillian R. Hayes (LUCI Faculty)

Homebrew Databases: Complexities of Everyday Information Management in Nonprofit Organizations
Amy Voida (Informatics PostDoc), Ellie Harmon (LUCI Ph.D.), Ban Al-Ani (Informatics Faculty)

Why Do I Keep Interrupting Myself?: Environment, Habit and Self-Interruption
Laura Dabbish (CMU), Gloria Mark (Informatics Faculty), Victor Gonzalez, (ITAM)

Refraining from Technological Intervention by by Eric Baumer (former LUCI post-doc) and Six Silberman (former LUCI Ph.D. Student)

Congratulations
Alex, Aurora, Bill, David, Eric, Gillian, Sidney, Six, Victor, Yunan, Ruy, Bonnie, Nithya, Meg, Sen, Monica, Michael, Amy, Ellie, Ban, and Gloria!

Tags: , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,
Posted: 1/27/11 7:36 pm UTC by Add Your Comment
GD Star Rating
loading...

Involuntary Gesture Recognition for Predicting Cerebral Palsy in High-Risk Infants - July 21st, 2010

Moleskins and Pens

Photo courtesy of paulworthington

Congratulations to former Informatics visiting scholar Mohan Singh and Informatics Faculty Member Donald J. Patterson on having their paper accepted to the IEEE International Symposium on Wearable Computers
‘Involuntary Gesture Recognition for Predicting Cerebral Palsy in High-Risk Infants’

Abstract:In this paper we describe a system that leverages accelerometers to recognize a particular involuntary gesture in babies that have been born preterm. These gestures, known as cramped-synchronized general movements, have been shown to be highly correlated with a diagnosis of Cerebral Palsy. In order to test our system we recorded data from 10 babies admitted to the newborn intensive care unit at the UCI Medical Center. We applied machine learning techniques to features based on their data and were able to obtain high accuracies on this cohort. Validated video observation annotations were utilized as ground truth. Finally, we conducted an analysis to understand the basis of the algorithmic predictions.

Congratulations Mohan, and Don!

Tags: , , , , , , , , , ,
Posted: 7/21/10 3:59 pm UTC by Make the First Comment
GD Star Rating
loading...

Efficiently Scaling Up Video Annotation with Crowdsourced Marketplaces - June 7th, 2010

Moleskins and Pens

Photo courtesy of paulworthington

Congratulations to Computer Science Undergraduate Carl Vondrick, Computer Science Faculty Member Deva Ramanan and Informatics Faculty Donald J. Patterson on having their paper,
‘Efficiently Scaling Up Video Annotation with Crowdsourced Marketplaces’ accepted to ECCV-2010.

Abstract: “Accurately annotating entities in video is labor intensive and expensive. As the quantity of online video grows, traditional solutions to this task are unable to scale to meet the needs of researchers with limited budgets. Current practice provides a temporary solution by paying dedicated workers to label a fraction of the total frames and otherwise settling for linear interpolation. As budgets and scale require sparser key frames, the assumption of linearity fails and labels become inaccurate. To address this problem we have created a public framework for dividing the work of labeling video data into micro-tasks that can be completed by huge labor pools available through crowdsourced marketplaces. By extracting pixel-based features from manually labeled entities, we are able to leverage more sophisticated interpolation between keyframes to maximize performance given a budget. Finally, by validating the power of our framework on difficult, real-world data sets we demonstrate an inherent trade-off between the mix of human and cloud computing used vs. the accuracy and cost of the labeling.

Congratulations Carl, Deva and Don!

Tags: , , , , , , , , ,
Posted: 6/7/10 4:59 pm UTC by Make the First Comment
GD Star Rating
loading...
Front Page