Naver at ActivityNet Challenge 2019 -- Task B Active Speaker Detection (AVA)

06/25/2019

∙

by   Joon Son Chung, et al.

∙

2

∙

share

This report describes our submission to the ActivityNet Challenge at CVPR 2019. We use a 3D convolutional neural network (CNN) based front-end and an ensemble of temporal convolution and LSTM classifiers to predict whether a visible person is speaking or not. Our results show significant improvements over the baseline on the AVA-ActiveSpeaker dataset.