Multi-modal Feature Fusion with Feature Attention for VATEX Captioning Challenge 2020
This is an incremental improvement for video captioning, specifically for the VATEX challenge.
The authors tackled the VATEX Captioning Challenge 2020 by extracting multi-modal features (motion, appearance, semantic, audio) and using a feature attention module with ensemble decoders, achieving 76.0 CIDEr on English and 50.0 CIDEr on Chinese private test sets and ranking 2nd in both.
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.