A significant volume of analog information, i.e., documents and images, have been digitized in the form of scanned copies for storing, sharing, and/or analyzing in the digital world. However, the quality of such contents is severely degraded by various distortions caused by printing, storing, and scanning processes in the physical world. Although restoring high-quality content from scanned copies has become an indispensable task for many products, it has not been systematically explored, and to the best of our knowledge, no public datasets are available. In this paper, we define this problem as Descanning and introduce a new high-quality and large-scale dataset named DESCAN-18K. It contains 18K pairs of original and scanned images collected in the wild containing multiple complex degradations. In order to eliminate such complex degradations, we propose a new image restoration model called DescanDiffusion consisting of a color encoder that corrects the global color degradation and a conditional denoising diffusion probabilistic model (DDPM) that removes local degradations. To further improve the generalization ability of DescanDiffusion, we also design a synthetic data generation scheme by reproducing prominent degradations in scanned images. We demonstrate that our DescanDiffusion outperforms other baselines including commercial restoration products, objectively and subjectively, via comprehensive experiments and analyses.

Generative Adversarial Networks (GANs) are hindered from real-world applications due to their high computational cost and memory requirements. Model compression techniques, such as quantization, pruning, and knowledge distillation, can compress neural networks, lower memory requirements, and model size. However, quantizing generators often leads to a suboptimal solution. In this paper, we propose a novel method to stabilize GAN quantization by quantizing the generator and discriminator with different bit precision. Our method maximizes the quantization efficiency by jointly quantizing the generator and discriminator, which we found to be dependent on each other’s quantization. Specifically, quantizing the discriminator enhances the performance of the quantized generator, while the discriminator’s optimal quantization bit depends on the generator’s quantization bit and architectural type. We conducted extensive experiments on various GAN models, including BigGAN, SAGAN, and SNGAN, using different quantization methods, such as LSQ, PACT, and DoReFa, on benchmark dataset (CIFAR10). The experimental results demonstrate that our joint quantization method achieves higher compression rates while offering better performance in Frechet Inception Distance (FID) and Inception Score (IS).

Our preliminary study reveals that individuals use various management strategies for limiting smartphone use, ranging from keeping smartphones out of reach to removing apps. However, we also found that users often had difficulties in maintaining their chosen management strategies due to lack of self-regulation. In this paper, we present NUGU, a group-based intervention app for improving self-regulation of limiting smartphone use through leveraging social support: groups of people limit their use together by sharing their limiting information. NUGU is designed based on social cognitive theory, and it has been developed iteratively through two pilot tests. Our three-week user study (n = 62) demonstrated that compared with its non-social counterpart, the NUGU users' usage amount significantly decreased and their perceived level of managing disturbances improved. Furthermore, our exit interview confirmed that NUGU's design elements are effective for achieving limiting goals.

We consider participatory parental mediation in which children engage with their parents in activities that encourage both parents and children to participate in co-learning of digital media use. To this end, we developed FamiLync, a mobile service that treats use-limiting as a family activity and provides the family with a virtual public space to foster social awareness and improve self-regulation. A three-week user study conducted with twelve families in Korea (17 parents and 18 teenagers) showed that FamiLync improves mutual understanding of usage behavior, thereby providing common grounds for parental mediation. Further, parents actively participated in use-limiting with their children, which significantly increased the children's desire to participate. As a consequence, parental mediation methods and parent-child interaction in relation to smartphone usage changed appreciably, and the participants smartphone usage amount significantly decreased.

The negative aspects of smartphone overuse on young adults, such as sleep deprivation and attention deficits, are being increasingly recognized recently. This emerging issue motivated us to analyze the usage patterns related to smartphone overuse. We investigate smartphone usage for 95 college students using surveys, logged data, and interviews. We first divide the participants into risk and non-risk groups based on self-reported rating scale for smartphone overuse. We then analyze the usage data to identify between-group usage differences, which ranged from the overall usage patterns to app-specific usage patterns. Compared with the non-risk group, our results show that the risk group has longer usage time per day and different diurnal usage patterns. Also, the risk group users are more susceptible to push notifications, and tend to consume more online content. We characterize the overall relationship between usage features and smartphone overuse using analytic modeling and provide detailed illustrations of problematic usage behaviors based on interview data.