Slow-Fast Auditory Streams For Audio Recognition

5 Mar 2021  ·  Evangelos Kazakos, Arsha Nagrani, Andrew Zisserman, Dima Damen ·

We propose a two-stream convolutional network for audio recognition, that operates on time-frequency spectrogram inputs. Following similar success in visual recognition, we learn Slow-Fast auditory streams with separable convolutions and multi-level lateral connections. The Slow pathway has high channel capacity while the Fast pathway operates at a fine-grained temporal resolution. We showcase the importance of our two-stream proposal on two diverse datasets: VGG-Sound and EPIC-KITCHENS-100, and achieve state-of-the-art results on both.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Human Interaction Recognition EPIC-SOUNDS Slow-Fast(Finetune by Fivewin team) Top-1 accuracy % 55.11 # 1

Methods


No methods listed for this paper. Add relevant methods here