ICTCAS-UCAS-TAL Submission to the AVA-ActiveSpeaker Task at ActivityNet Challenge 2021
Yuanhang Zhang, Susan Liang, Shuang Yang, Xiao Liu, Zhongqin Wu, Shiguang Shan
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
This report presents a brief description of our method for the AVA Active Speaker Detection (ASD) task at ActivityNet Challenge 2021. Our solution, the Extended Unified Context Network (Extended UniCon) is based on a novel Unified Context Network (UniCon) designed for robust ASD, which combines multiple types of contextual information to optimize all candidates jointly. We propose a few changes to the original UniCon in terms of audio features, temporal modeling architecture, and loss function design. Together, our best model ensemble sets a new state-of-the-art at 93.4% mAP on the AVA-ActiveSpeaker test set without any form of pretraining, and currently ranks first on the ActivityNet challenge leaderboard.