Workshop on Computer Vision and Human Computation
Monday, June 23, 2014, Columbus, Ohio, CVPR 2014
C 114-115, Columbus Convention Center (getting here)

News · Schedule · Accepted Papers · Program Committee · Organizers

Human computation and crowdsourcing have emerged as exciting new frontiers for computer vision research. On one hand, engaging humans is crucial for advancing computer vision. We rely on humans for data collection, annotation, evaluation, and knowledge extraction in general. Important engineering insights often arise from studying humans visual systems. On the other hand, computer vision systems and humans can collaborate to break new grounds and accomplish challenging tasks.

This workshop aims to bring together researchers and practitioners interested in the intersection of computer vision, human computation and crowdsourcing. The workshop will feature invited talks and poster presentations. Topics include but are not limited to the following:

• Crowdsourcing issues, including UI design, resource optimization, quality control, etc.
• Interactive or semi-automatic systems for visual tasks
• Active and/or semi-supervised learning
• Never ending / continuous learning with human supervision
• Novel forms of interaction (gamification, attributes, human input beyond labels, etc.)
• Modeling and mining data generated by humans

Sponsored by

News

• Some talk slides posted.
• Room change Grand Ballroom 3 C 114-115, Columbus convention center.
• Schedule for the workshop is available.
• Google, Microsoft and Yahoo! are sponsoring our workshop. Thank you!
• Authors can upload their spotlight talk on CMT directly. Here is the link to the powerpoint template.
• Authors may optionally upload the final version of their paper on CMT. It will be posted at the workshop page.

Schedule

0920	Opening Remarks
0925	Invited Talk Larry Zitnick, Microsoft Research Building Large Datasets to Represent the World
1005	Morning Break
1030	Invited Talk Devi Parikh, Viginia Tech Beyond Mindless Labeling: *Really* Leveraging Humans to Build Intelligent Machines Talk slides
1105	Spotlights and Posters
1200	Lunch Break (Exhibit Hall C)
1330	Invited Talk Jeffrey Bigham, CMU Quickly Answering General Visual Questions
1405	Keynote Talk Sebastian Seung, Princeton University EyeWire, A Game to Map the Brain
1500	Afternoon Break
1530	Invited Talk James Hays, Brown University Crowd One Shot Learning
1605	Invited Talk Serge Belongie, Cornell Tech. Visipedia Tool Ecosystem for Dataset Curation and Annotation Talk slides

Accepted Papers

One author from each paper will be given 90 seconds during the spotlight session to present their work. This will be followed by the poster session extending into the lunch break. Below is the list of accepted papers:

	Similarity Comparisons for Interactive Fine-Grained Categorization Catherine Wah, Grant Van Horn, Steven Branson, Subhransu Maji, Pietro Perona, Serge Belongie abstract / poster / extended paper
	Visual Abstraction for Zero-Shot Learning Stanislaw Antol, Larry Zitnick, Devi Parikh abstract / poster
	Interactive Image Search with Attribute-based Guidance and Personalization Adriana Kovashka, Kristen Grauman abstract / poster
	Beyond Comparing Image Pairs: Setwise Active Learning for Relative Attributes Lucy Liang, Kristen Grauman abstract / poster / extended paper
	Using Human Knowledge to Judge Part Goodness: Interactive Part Selection Ejaz Ahmed, Subhransu Maji, Gregory Shakhnarovich, Larry Davis abstract / poster
	A User Friendly Crowdsourcing Task Manager Tomas Matera, Jan Jakes, Munan Cheng, Serge Belongie abstract / poster
	Cost-Effective HITs for Relative Similarity Comparisons Michael Wilber, Sam Kwak, Serge Belongie abstract / poster / extended paper
	Learning to Identify Local Flora with Human Feedback Stefan Lee, David Crandall abstract / poster
	JAABA: An interactive machine learning system for biologists Kristin Branson, Mayank Kabra, Alice A. Robie, Marta Rivera-Alba, Steven Branson and Adam Hantman abstract / poster / extended paper
	Generating Gold Questions for Difficult Visual Recognition Tasks Diane Larlus, Florent Perronnin, Pramod Kompalli, Vivek Mishra abstract / poster
	Predicting Sufficient Annotation Strength for Interactive Foreground Segmentation Suyog Jain, Kristen Grauman abstract / poster / extended paper
	Interactive Segmentation as Supervised Classification with Superpixels Han Sang Lee, Jiwhan Kim, Sun Jeong Park, Junmo Kim abstract / poster
	Acquiring Visual Classfiers from Human Imagination Carl Vondrick, Hamed Pirsiavash, Aude Oliva, Antonio Torralba abstract / poster

Program Committee

• Tamara Berg, UNC Chapel Hill
• David Crandall, Indiana University
• Ryan Farrell, Brigham Young University
• David Forsyth, University of Illinois Urbana-Champaign
• Derek Hoiem, University of Illinois Urbana-Champaign
• Ashish Kapoor, Microsoft Research
• Jia Li, Yahoo! Research
• Jiebo Luo, University of Rochester
• Jitendra Malik, UC Berkeley
• Bryan Russell, University of Washington
• Greg Shakhnarovich, TTI Chicago
• Sinisa Todorovic, Oregon State University
• Zhuowen Tu, UC San Diego
• Andrea Vedaldi, University of Oxford
• Larry Zitnick, Microsoft Research

Organizers

Jia Deng University of Michigan/Google	Subhransu Maji TTI Chicago/UMass Amherst	Pietro Perona California Institute of Technology