virtual conference icassp 2021

Disentanglement For Audio-Visual Emotion Recognition Using Multitask Setup

Frame Rate Up-Conversion Using Key Point Agnostic Frequency-Selective Mesh-To-Grid Resampling

Learning A Sparse Generative Non-Parametric Supervised Autoencoder

Near-Optimal Algorithms For Piecewise-Stationary Cascading Bandits

Compressing Local Descriptor Models For Mobile Applications

Self-Training For Sound Event Detection In Audio Mixtures

Detecting Signal Corruptions In Voice Recordings For Speech Therapy

Waveform Design For The Joint Mimo Radar And Communications With Low Integrated Sidelobe Levels And Accurate Information Embedding

Self-Convolution: A Highly-Efficient Operator For Non-Local Image Restoration

Heterogeneous Two-Stream Network With Hierarchical Feature Prefusion For Multispectral Pan-Sharpening

Data Augmentation With Signal Companding For Detection Of Logical Access Attacks

Efficient Real-Time Video Stabilization With A Novel Least Squares Formulation