マルチモーダル行動予測のための先読み特徴融合トランスフォーマ
Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation
複数モーダルのデータを早期に統合するトランスフォーマベースの手法を提案し、行動予測タスクで最先端性能を達成した。
著者: Zeyun Zhong, David Schneider, Michael Voit, Rainer Stiefelhagen, Jürgen Beyerer
分類: cs.CV, cs.RO
原文アブストラクト
Although human action anticipation is a task which is inherently multi-modal, state-of-the-art methods on well known action anticipation datasets leverage this data by applying ensemble methods and averaging scores of unimodal anticipation networks. In this work we introduce transformer based modality fusion techniques, which unify multi-modal data at an early stage. Our Anticipative Feature Fusion Transformer (AFFT) proves to be superior to popular score fusion approaches and presents state-of-the-art results outperforming previous methods on EpicKitchens-100 and EGTEA Gaze+. Our model is easily extensible and allows for adding new modalities without architectural changes. Consequently, we extracted audio features on EpicKitchens-100 which we add to the set of commonly used features in the community.
