25 citations · 40 across the 24 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
cs.CV2019
MMTM: Multimodal Transfer Module for CNN Fusion
Hamid Reza Vaezi Joze, Amirreza Shaban, Michael L. Iuzzolino +1
In late fusion, each modality is processed in a separate unimodal Convolutional Neural Network (CNN) stream and the scores of each modality are fused at the end. Due to its simplic…
eess.AS2019★ 2 cited
Sound Event Detection in Multichannel Audio using Convolutional Time-Frequency-Channel Squeeze and Excitation
Wei Xia, Kazuhito Koishida
In this study, we introduce a convolutional time-frequency-channel "Squeeze and Excitation" (tfc-SE) module to explicitly model inter-dependencies between the time-frequency domain…