No abstract

This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020. This challenge involves three tracks to super-resolve an input image for ×2, ×3 and ×4 scaling factors, respectively. The goal is to attract more attention to realistic image degradation for the SR task, which is much more complicated and challenging, and contributes to real-world image super-resolution applications. 452 participants were registered for three tracks in total, and 24 teams submitted their results. They gauge the state-of-the-art approaches for real image SR in terms of PSNR and SSIM.

In this paper we examine the model of crowdsourcing for translation and compare it with Machine Translation (MT). The large volume of material to be translated, the translation of this material into many languages combined with tight deadlines lead enterprises today to follow either crowdsourcing and/or MT. Crowdsourcing translation shares many characteristics with MT, as both can cope with high volume, perform at high speed, and reduce the translation cost. MT is an older technology, whereas crowdsourcing is a new phenomenon gaining much ground over time, mainly through Web 2.0. Examples and challenges of both models will be discussed and the paper is closed with future prospects regarding the combination of crowdsourcing and MT, so that they are not regarded as opponents. These prospects are partially based on the results of a survey we conducted. Based on our background, experience, and research, this paper covers aspects both from the point of view of translation studies and computational linguistics applications as well as of information sciences, and particularly the development of the Web regarding user-generated content.

No abstract

No abstract