In single image deblurring, the "coarse-to-fine" scheme, i.e. gradually restoring the sharp image on different resolutions in a pyramid, is very successful in both traditional optimization-based methods and recent neural-networkbased approaches. In this paper, we investigate this strategy and propose a Scale-recurrent Network (SRN-DeblurNet) for this deblurring task. Compared with the many recent learning-based approaches in [25], it has a simpler network structure, a smaller number of parameters and is easier to train. We evaluate our method on large-scale deblurring datasets with complex motion. Results show that our method can produce better quality results than state-of-thearts, both quantitatively and qualitatively.
Previous CNN-based video super-resolution approaches need to align multiple frames to the reference. In this paper, we show that proper frame alignment and motion compensation is crucial for achieving high quality results. We accordingly propose a "sub-pixel motion compensation" (SPMC) layer in a CNN framework. Analysis and experiments show the suitability of this layer in video SR. The final end-to-end, scalable CNN framework effectively incorporates the SPMC layer and fuses multiple frames to reveal image details. Our implementation can generate visually and quantitatively high-quality results, superior to current state-of-the-arts, without the need of parameter tuning.
The purpose of this study was to examine parents’ perceived social change and its relations with adolescents’ reports of childrearing attitudes in urban and rural China. The participants were high school students and their parents in a Northern region of China. Parents completed a measure of perceived social change, and the adolescents completed a measure of childrearing attitudes including parental warmth, control, and encouragement of independence. The results indicated that urban parents had higher scores than rural parents on major dimensions of perceived social change including work-related opportunities, self-improvement in work, and high-tech experiences. Urban adolescents reported lower parental control and higher parental encouragement of independence than rural adolescents. In addition, parents’ reports of opportunities and prospects were positively associated with adolescents’ reports of parental warmth and encouragement of independence in childrearing across the urban and rural groups, suggesting that parents who perceived more challenges and opportunities to pursue self-advancement and personal career goals were more likely to support the use of warm and sensitive parenting and to encourage their children to develop independent behaviors. The results indicated the implications of social change for socialization and adolescent development in Chinese context.
We develop a latent variable selection method for multidimensional item response theory models. The proposed method identifies latent traits probed by items of a multidimensional test. Its basic strategy is to impose an [Formula: see text] penalty term to the log-likelihood. The computation is carried out by the expectation-maximization algorithm combined with the coordinate descent algorithm. Simulation studies show that the resulting estimator provides an effective way in correctly identifying the latent structures. The method is applied to a real dataset involving the Eysenck Personality Questionnaire.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.