FOR-LQ 2018

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 visual data acquired from complex unconstrained environments, suffering from various types of degradations such as low resolution, noise, occlusion and motion blur.

This workshop (FOR-LQ 2018) will provide an integrated forum for researchers to review the recent progress of robust face and object recognition from low-quality 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.


TOPICS

- Face and object recognition, especially from low-resolution image/video, video with motion blurs, highly noisy image/video, and/or other unconstrained environment conditions
- Recognition-oriented image/video super-resolution, image/video denoising and deblurring, and/or restoration and enhancement of other degradations such as low-illumination, inclement weathers, etc.
- Applications that robustly handle computer vision tasks with low-quality inputs
- Evaluating methods and metrics for image restoration and enhancement, especially for recognition purpose


SUBMISSIONS

Short paper: 4 pages + 1 page for references
IEEE conference paper template (anonymous submission)
More information:
https://fg2018.cse.sc.edu/submissions.html