ICASSP 2022

Deep Markov Clustering For Panoptic Segmentation

MFA: TDNN WITH MULTI-SCALE FREQUENCY-CHANNEL ATTENTION FOR TEXT-INDEPENDENT SPEAKER VERIFICATION WITH SHORT UTTERANCES

Temporal Early Exiting for Streaming Speech Commands Recognition

MEMORY-BASED MESSAGE PASSING: DECOUPLING THE MESSAGE FOR PROPAGATION FROM DISCRIMINATION

DYNAMIC RESOURCE OPTIMIZATION FOR ADAPTIVE FEDERATED LEARNING EMPOWERED BY RECONFIGURABLE INTELLIGENT SURFACES

A Global to Local Guiding Network for Missing Data Imputation

DEPTH REMOVAL DISTILLATION FOR RGB-D SEMANTIC SEGMENTATION

AERIAL BASE STATION PLACEMENT LEVERAGING RADIO TOMOGRAPHIC MAPS

USER SCHEDULING USING GRAPH NEURAL NETWORKS FOR RECONFIGURABLE INTELLIGENT SURFACE ASSISTED MULTIUSER DOWNLINK COMMUNICATIONS

UNSUPERVISED WORD-LEVEL PROSODY TAGGING FOR CONTROLLABLE SPEECH SYNTHESIS

Gradient-weighted Class Activation Mapping for spatio temporal graph convolutional network

MULTI-TASK LEARNING IMPROVES THE BRAIN STOKE LESION SEGMENTATION