ICASSP 2020

Secure Symbol-Level Miso Precoding

Dgan: Disentangled Representation Learning For Anisotropic Brdf Reconstruction

Steganography And Its Detection In Jpeg Images Obtained With The Trunc Quantizer

Enhancing The Labelling Of Audio Samples For Automatic Instrument Classification Based On Neural Networks

Vamp With Vector-Valued Diagonalization

Learning Diverse Sub-Policies Via A Task-Agnostic Regularization On Action Distributions.

Fully Convolutional Recurrent Networks For Speech Enhancement

Multi-Resolution Multi-Head Attention In Deep Speaker Embedding

Fourier Phase Retrieval With Arbitrary Reference Signal

Effective Pipeline For Compressing Deep Object Detectors

Ava Active Speaker: An Audio-Visual Dataset For Active Speaker Detection

Spatial Attentional Bilinear 3D Convolutional Network For Video-Based Autism Spectrum Disorder Detection