hicv 2011 - 1st IEEE Workshop on Human Interaction in Computer Vision

Social and industrial demands for Multimodal Interactive (MI) technologies and advanced man‐machine interfaces are increasing dramatically. Computer Vision (CV) plays a highly relevant role in the development of these MI technologies and interfaces. However, traditional CV technologies have mainly focused on full automation, even though full automation often proves elusive or unnatural in many applications, where technology is expected to assist rather than replace human agents.
In the framework of the ICCV conference, this workshop focuses on discussing the human interaction role in computer vision algorithms. HICV attempts to analyze how existing CV technologies can naturally take benefit from the development of advanced interactive systems.
The Interactive computer vision topic includes several research lines, ranging from efficient data annotation, image segmentation, applications to medical image analysis, semi‐supervised learning and other novel techniques involving Human‐in‐the‐Loop Computer Vision. Finally, this workshop pretends to identify the future challenges and opportunities entailed by the human‐interaction paradigm.

Topics

Topics include, but are not limited to:

The use of annotation tools applied to label Computer Vision and Datasets: Mechanical Turk, ImageNet, LabelMe, etc.
Interactive Image Segmentation.
Active and Semi‐supervised techniques applied to Large Scale Visual Recognition.
Study of benefits and limitations of involving human subjects in Computer Vision algorithms.
Applications of Interactive Computer Vision to Medical imaging, gaming, industry, etc.
Other novel and transgressive techniques involving Human‐in‐the‐Loop Computer Vision.