No description available.

No description available.

Recent years, we have witnessed significant progress in the quality enhancement of compressed video by deep learning methods. In this paper, we propose an effective method for Video Quality Enhancement(VQE) task. Our method is realized via \textbf{A Parallel Network for Compressed Video Enhancement(PEN)}. To tackle optical flow estimates and complicated motion, PEN has two branches which are \textbf{Offset Deformable Fusion Network(ODFN)} and \textbf{Complex Motion Solution Network(CMSN)}. During the alignment stage, existing methods typically estimate optical flow for temporal motion compensation. However, because the compressed video may be severely distorted as a result of various compression artifacts, the estimated optical flow is typically inaccurate and unreliable. Therefore in ODFN we use deformable convolution to align frames in a fast and efficient way. At the same time, we adopt pyramidal processing and cascading refinement in CMSN which can address complex motions and large parallax problems in alignment. Furthermore, we use the target frame's neighbor Peak Quality frames(PQFs) as reference frames, which adjusts for video quality variations. Extensive experiments show that our method has improved the average video quality by 0.7 decibel. / Thesis / Master of Applied Science (MASc) / The quality of video is improving as cameras improve, but the size of the video is also increasing. As a result, we will need to compress the video. Video compression, on the other hand, is always accompanied with a loss of video quality. Deep learning approaches have made tremendous progress in improving the quality of compressed video in recent years. In this paper, we propose an effective method PEN for Video Quality Enhancement(VQE) task by parallel processing of multiple frames.

Recent developments in social neuroscience have stirred up increased interest within the bioethical debate (for a review see: Specker et al. 2014). Moral enhancement is a concept that directly embodies the idea of making brain science work for the social and moral good. In recent ethical discussions about biomedical means of moral enhancement, scholars have focused on so called ‘direct means of moral enhancement,’ discussing the ethical permissibility of modifying the emotional underpinnings of moral behaviour (Douglas, 2008; 2013; Persson and Savulescu, 2008; Savulescu and Persson, 2012). However, critics have argued that such modification only seems like moral enhancement, that behavioural modification is not ‘true’ moral enhancement, for the reason that it changes behaviours without making agents better moral agents. Critics have also noted that it can undermine freedom (e.g. Harris, 2011; see also: Douglas, 2014). This thesis addresses the ethical issues relating to enhancement. In the first part of this work I consider conceptual issues surrounding the concept of moral enhancement and argue that moral enhancement is plausible if we adjust our expectations to match those we have of cognitive enhancement. I examine the difference between pro-sociality and morality, and argue that an increase in empathy and reduction in anger cannot be seen as straightforward moral enhancements. The second part examines the objections related to moral disagreement, medicalization and narrative identity. The third part of this work focuses of the issues related to freedom and agency. I argue that voluntary direct emotion modulation, if embedded in appropriate reflection, is a prima facie desirable way of moral enhancement.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.