论文标题
UNICON+：ICTCAS-UCAS在Avistnet挑战赛上提交AVA-ACTIVESPEAKER任务2022
UniCon+: ICTCAS-UCAS Submission to the AVA-ActiveSpeaker Task at ActivityNet Challenge 2022
论文作者
论文摘要
本报告简要描述了我们对AVA主动扬声器检测（ASD）任务的获胜解决方案，该任务在2022年。我们的基础模型Unicon+继续基于我们先前的工作，统一的上下文网络（UNICON）和扩展的Unicon，旨在为可靠的场景级别ASD设计。我们使用一个简单的基于GRU的模块来增强体系结构，该模块允许重复身份的信息通过阅读和更新操作在场景中流动。我们报告了Ava-Activespeaker测试集94.47％地图的最佳结果，该测试套装在今年的挑战排行榜上继续排名第一，并大大推动了最新的攻击。
This report presents a brief description of our winning solution to the AVA Active Speaker Detection (ASD) task at ActivityNet Challenge 2022. Our underlying model UniCon+ continues to build on our previous work, the Unified Context Network (UniCon) and Extended UniCon which are designed for robust scene-level ASD. We augment the architecture with a simple GRU-based module that allows information of recurring identities to flow across scenes through read and update operations. We report a best result of 94.47% mAP on the AVA-ActiveSpeaker test set, which continues to rank first on this year's challenge leaderboard and significantly pushes the state-of-the-art.
