IEEE ICASSP 2022

2022 IEEE International Conference on Acoustics, Speech and Signal Processing

7-13 May 2022
  • Virtual (all paper presentations)
22-27 May 2022
  • Main Venue: Marina Bay Sands Expo & Convention Center, Singapore
27-28 October 2022
  • Satellite Venue: Crowne Plaza Shenzhen Longgang City Centre, Shenzhen, China

ICASSP 2022
MLSP-L1: Deep Learning Techniques
Tue, 24 May, 13:00 - 15:30 China Time (UTC +8)
Tue, 24 May, 05:00 - 07:30 UTC
Location: Roselle Junior Ballroom 4611-3
Session Co-Chairs: Hak Gu Kim, Chung-Ang University and Savitha Ramasamy, Institute for Infocomm Research, A*STAR
Track: Machine Learning for Signal Processing

MLSP-L1.1: GRADIENT VARIANCE LOSS FOR STRUCTURE-ENHANCED IMAGE SUPER-RESOLUTION
Lusine Abrahamyan, Nikos Deligiannis, Vrije Universiteit Brussel, Belgium; Anh Minh Truong, Wilfried Philips, Ghent University, Belgium

MLSP-L1.2: ADVERSARIAL ROBUSTNESS BY DESIGN THROUGH ANALOG COMPUTING AND SYNTHETIC GRADIENTS
Alessandro Cappelli, Iacopo Poli, LightOn, France; Ruben Ohana, Julien Launay, LightOn/ Ecole Normale Superieure, France; Laurent Meunier, Université Dauphine/ Facebook AI Research, France; Florent Krzakala, LightOn/ EPFL, France

MLSP-L1.3: DEMON: IMPROVED NEURAL NETWORK TRAINING WITH MOMENTUM DECAY
John Chen, Cameron Wolfe, Anastasios Kyrillidis, Rice University, United States of America; Zhao Li, UT Health, United States of America

MLSP-L1.4: BAYESIAN CONTINUAL IMPUTATION AND PREDICTION FOR IRREGULARLY SAMPLED TIME SERIES DATA
Yang Guo, Cheryl Sze Yin Wong, Savitha Ramasamy, Institute for Infocomm Research, A*STAR, Singapore; Jeanette Wen Jun Poh, Nanyang Technological University Singapore, Singapore

MLSP-L1.5: LABEL-AWARE RANKED LOSS FOR ROBUST PEOPLE COUNTING USING AUTOMOTIVE IN-CABIN RADAR
Lorenzo Servadei, Huawei Sun, Julius Ott, Daniela Sanchéz Lopera, Infineon Technologies AG / Technical University of Munich, Germany; Michael Stephan, Thomas Stadelmayer, Infineon Technologies AG / Friedrich-Alexander-University of Erlangen Nuremberg, Germany; Souvik Hazra, Avik Santra, Infineon Technologies AG, Germany; Robert Wille, Johannes Kepler University Linz, Germany

MLSP-L1.6: TRAINING STABLE GRAPH NEURAL NETWORKS THROUGH CONSTRAINED LEARNING
Juan Cervino, Luana Ruiz, Alejandro Ribeiro, University of Pennsylvania, United States of America

MLSP-L1.7: JOINT LEARNING OF FEATURE EXTRACTION AND COST AGGREGATION FOR SEMANTIC CORRESPONDENCE
Jiwon Kim, Youngjo Min, Mira Kim, Seungryong Kim, Korea University, Korea, Republic of

MLSP-L1.8: ON DATA AUGMENTATION FOR GAN TRAINING
Ngoc-Trung Tran, Viet-Hung Tran, Ngoc-Bao Nguyen, Trung-Kien Nguyen, Ngai-Man (Man) Cheung, Singapore University of Technology and Design (SUTD), Singapore

MLSP-L1.9: Natural-looking Adversarial Examples from Freehand Sketches
Hak Gu Kim, Chung-Ang University, Korea, Republic of; Davide Nanni, Sabine Süsstrunk, École Polytechnique Fédérale de Lausanne, Switzerland

MLSP-L1.10: T-NGA: TEMPORAL NETWORK GRAFTING ALGORITHM FOR LEARNING TO PROCESS SPIKING AUDIO SENSOR EVENTS
Shu Wang, Yuhuang Hu, Shih-Chii Liu, Institute of Neuroinformatics, University of Zürich and ETH Zürich, Switzerland