Sibling Neural Estimators: Improving Iterative Image Decoding with Gradient Communication. (arXiv:1911.08478v1 [cs.CV])

For lossy image compression, we develop a neural-based system which learns a nonlinear estimator for decoding from quantized representations. The system links two recurrent networks that \help” each other reconstruct same target image patches using complementary portions of spatial context that communicate via gradient signals. This dual agent system builds upon prior work that proposed…

Nanoimprinting and Tapering of Chalcogenide Photonic Crystal Fibers for Cascaded Supercontinuum Generation. (arXiv:1911.08481v1 [physics.optics])

Improved long-wavelength transmission and supercontinuum (SC) generation is demonstrated by anti-reflective (AR) nanoimprinting and tapering of chalcogenide photonic crystal fibers (PCF). Using a SC source input spanning from 1-4.2 {\mu}m, the total transmission of a 15 {\mu}m core diameter PCF was improved from ~53 % to ~74 % by nanoimprinting of AR structures on both…

Modern Antennas and Microwave Circuits — A complete master-level course. (arXiv:1911.08484v1 [eess.SP])

Modern antenna systems include passive antenna structures, passive microwave circuits and interconnections to electronics. Therefore, the antenna engineer should have a deep understanding of antenna theory and should be able to apply microwave engineering concepts. This textbook provides all relevant material for Master-level courses in the domain of antenna systems. The book includes comprehensive material…

Modal-aware Features for Multimodal Hashing. (arXiv:1911.08479v1 [cs.CV])

Many retrieval applications can benefit from multiple modalities, e.g., text that contains images on Wikipedia, for which how to represent multimodal data is the critical component. Most deep multimodal learning methods typically involve two steps to construct the joint representations: 1) learning of multiple intermediate features, with each intermediate feature corresponding to a modality, using…

The Future Time Traveller Project: Career Guidance on Future Skills, Jobs and Career Prospects of Generation Z through a Game-Based Virtual World Environment. (arXiv:1911.08480v1 [cs.HC])

Future Time Traveller is a European project that aims at transforming career guidance of generation Z through an innovative, games-based scenario approach and to prepare the next generation for the jobs of the future. The pro-ject objective is to foster innovative thinking and future-oriented mindset of young people, through an innovative game-based virtual world environment.…

Automatic Brain Tumour Segmentation and Biophysics-Guided Survival Prediction. (arXiv:1911.08483v1 [eess.IV])

Gliomas are the most common malignant brain tumourswith intrinsic heterogeneity. Accurate segmentation of gliomas and theirsub-regions on multi-parametric magnetic resonance images (mpMRI)is of great clinical importance, which defines tumour size, shape andappearance and provides abundant information for preoperative diag-nosis, treatment planning and survival prediction. Recent developmentson deep learning have significantly improved the performance of auto-mated…

Parameters Estimation for the Cosmic Microwave Background with Bayesian Neural Networks. (arXiv:1911.08508v1 [astro-ph.IM])

In this paper, we present the first study that compares different models of Bayesian Neural Networks (BNNs) to predict the posterior distribution of the cosmological parameters directly from the Cosmic Microwave Background (CMB) map. We focus our analysis on four different methods to sample the weights of the network during training: Dropout, DropConnect, Reparameterization Trick…

Optimal Complexity and Certification of Bregman First-Order Methods. (arXiv:1911.08510v1 [math.OC])

We provide a lower bound showing that the $O(1/k)$ convergence rate of the NoLips method (a.k.a. Bregman Gradient) is optimal for the class of functions satisfying the $h$-smoothness assumption. This assumption, also known as relative smoothness, appeared in the recent developments around the Bregman Gradient method, where acceleration remained an open issue. On the way,…

Action Recognition Using Volumetric Motion Representations. (arXiv:1911.08511v1 [cs.CV])

Traditional action recognition models are constructed around the paradigm of 2D perspective imagery. Though sophisticated time-series models have pushed the field forward, much of the information is still not exploited by confining the domain to 2D. In this work, we introduce a novel representation of motion as a voxelized 3D vector field and demonstrate how…

Towards Reducing Bias in Gender Classification. (arXiv:1911.08556v1 [cs.LG])

Societal bias towards certain communities is a big problem that affects a lot of machine learning systems. This work aims at addressing the racial bias present in many modern gender recognition systems. We learn race invariant representations of human faces with an adversarially trained autoencoder model. We show that such representations help us achieve less…