FOR-LQ 2018 - 2018 IEEE FG Workshop on Real-World Face and Object Recognition from Low-Quality Images (FOR-LQ)

Description: While the visual recognition research has made tremendous progress in recent years, most models are trained, applied, and evaluated on high-quality (HQ) visual data, such as the LFW and ImageNet benchmarks. However, in many emerging applications such as video surveillance, robotics and autonomous driving, the performances of visual sensing and analytics are largely jeopardized by low-quality (LQ) visual data acquired from complex unconstrained environments, suffering from various types of degradations such as low resolution, noise, occlusion and motion blur. While some mild degradations may be compromised by sophisticated visual recognition models, their impacts will turn much notable as the level of degradations passes some empirical threshold. This Half-Day workshop (FOR-LQ 2018) will provide an integrated forum for researchers to review the recent progress of robust face and object recognition from LQ visual data. We embrace the most advanced deep learning systems, meanwhile being open to classical physically grounded models and feature engineering, as well as any well-motivated combination of the two streams. The workshop will consist of 1-2 invited keynote talks, together with peer-reviewed regular papers (oral and poster).
Organizers:
Dong Liu, dongeliu-AT-ustc.edu.cn
Weisheng Dong, wsdong-AT-mail.xidian.edu.cn
Zhangyang Wang, atlaswang-AT-tamu.edu
Ding Liu: dingliu2-AT-illinois.edu