2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

Click on the icon to view the manuscript on IEEE XPlore in the IEEE ICASSP 2021 Open Preview.

MLSP-46: Theory and Applications

Session Type: Poster
Time: Friday, 11 June, 13:00 - 13:45
Location: Gather.Town
Virtual Session: View on Virtual Platform
Session Chair: Iván López-Espejo, Aalborg University
 
 MLSP-46.1: SAPAUGMENT: LEARNING A SAMPLE ADAPTIVE POLICY FOR DATA AUGMENTATION
         Ting-Yao Hu; Carnegie Mellon University
         Ashish Shrivastava; Apple
         Rick Chang; Apple
         Hema Koppula; Apple
         Stefan Braun; Apple
         Kyuyeon Hwang; Apple
         Ozlem Kalinli; Apple
         Oncel Tuzel; Apple
 
 MLSP-46.2: HIERARCHICAL CODED ELASTIC COMPUTING
         Shahrzad Kianidehkordi; University of Toronto
         Tharindu Adikari; University of Toronto
         Stark Draper; University of Toronto
 
 MLSP-46.3: SYNTHESIZE & LEARN: JOINTLY OPTIMIZING GENERATIVE AND CLASSIFIER NETWORKS FOR IMPROVED DROWSINESS DETECTION
         Sandipan Banerjee; Affectiva
         Ajjen Joshi; Affectiva
         Ahmed Ghoneim; Affectiva
         Survi Kyal; Affectiva
         Taniya Mishra; SureStart
 
 MLSP-46.4: A JOINT CONVOLUTIONAL AND SPATIAL QUAD-DIRECTIONAL LSTM NETWORK FOR PHASE UNWRAPPING
         Malsha V. Perera; University of Moratuwa
         Ashwin De Silva; University of Moratuwa
 
MLSP-46.5: IMPROVING THE HARMONY OF THE COMPOSITE IMAGE BY SPATIAL-SEPARATED ATTENTION MODULE
         Xiaodong Cun; University of Macau
         Chi-Man Pun; University of Macau
 
MLSP-46.6: A MNEMONIC KALMAN FILTER FOR NON-LINEAR SYSTEMS WITH EXTENSIVE TEMPORAL DEPENDENCIES
         Steffen Jung; Fraunhofer FKIE
         Isabel Schlangen; Fraunhofer FKIE
         Alexander Charlish; Fraunhofer FKIE