Second Workshop on Human Computation for Image and Video Analysis @ HCOMP 2017
Keynote speakers have been announced! Please see the Program for details.
What would be possible if we could accelerate the analysis of images and videos, especially at scale? This question is inspiring widespread interest across communities as diverse as computer vision, human computer interaction, computer graphics, and multimedia. Some researchers are designing algorithms to automatically analyze visual content, yet many tasks remain too difficult for state-of-the-art algorithms. Other researchers are investigating ways to leverage crowdsourced human computation to power the analysis of visual content, however this is a more costly and less scalable alternative. And, at the intersection, lies an emerging research field for how to actively decide when and how to engage humans to cooperate with computers for visual analysis.
We are pleased to announce the second annual GroupSight workshop, building on the successful first edition at last year's AAAI Conference on Human Computation and Crowdsourcing (HCOMP). This year, HCOMP is co-located with UIST 2017, the premiere forum for innovations in human-computer interfaces. This promises an exciting mix of people and papers at the intersection of HCI, crowdsourcing, and computer vision.
The aim of this workshop is to promote greater interaction between the diversity of researchers and practitioners who examine how to mix human and computer efforts to convert visual data into discoveries and innovations that benefit society at large. It will foster in-depth discussion of technical and application issues for how to engage humans with computers to optimize cost/quality trade-offs. It will also serve as an introduction to researchers and students curious about this important, emerging field at the intersection of crowdsourced human computation and image/video analysis.
August 14, 2017August 23, 2017 (5:59 pm EDT): Deadline for paper submission (extended!)
- August 25, 2017: Notification of decision
- October 24, 2017: Workshop (full-day)