论文标题
多模式特征融合，并注意Vatex字幕挑战2020
Multi-modal Feature Fusion with Feature Attention for VATEX Captioning Challenge 2020
论文作者
论文摘要
该报告描述了我们的Vatex字幕挑战2020的模型。首先，要从多个域中收集信息，我们提取运动，外观，语义和音频功能。然后，我们设计一个功能注意模块，以在解码时参与不同的功能。我们应用两种类型的解码器，自上而下和X-Lan，并将这些模型集成以获得最终结果。提出的方法的表现优于正式基线，其差距很大。我们在英语和中文私人测试套件上实现了76.0苹果酒和50.0苹果酒。我们在英语和中文私人测试排行榜上排名第二。
This report describes our model for VATEX Captioning Challenge 2020. First, to gather information from multiple domains, we extract motion, appearance, semantic and audio features. Then we design a feature attention module to attend on different feature when decoding. We apply two types of decoders, top-down and X-LAN and ensemble these models to get the final result. The proposed method outperforms official baseline with a significant gap. We achieve 76.0 CIDEr and 50.0 CIDEr on English and Chinese private test set. We rank 2nd on both English and Chinese private test leaderboard.
