Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation
This work addresses the challenge of effectively integrating multi-modal data for action anticipation, offering a more unified approach compared to existing ensemble methods.
The paper tackled the problem of multi-modal action anticipation by introducing a transformer-based modality fusion technique that unifies data early, achieving state-of-the-art results on EpicKitchens-100 and EGTEA Gaze+ datasets.
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.