.png){kind=icon}
.png){kind=icon}
Return
Multi-stage query-based feature generating and encoding for robust early action recognition
.png){kind=icon}
PRE
AI
DOI：10.1007/s00371-025-03922-9.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper proposes a novel early action recognition (EAR) method based on multi-stage query-based feature generation and encoding. Existing EAR approaches often struggle with the similarity of initial action features, making it challenging to accurately extract discriminative information. To address this, our method divides the unobserved feature reconstruction process into multiple sub-stages, with each stage focusing on generating and restoring a small segment of action information. This segmentation strategy ensures that the reconstructed action information is more consistent with real-world scenarios. Furthermore, we introduce a query encoding network to model the relationships between sub-stage action features, effectively integrating them to enrich feature representations, enhance model generalization, and improve sequence coherence. Experimental results on public datasets HMDB51 and UCF101 demonstrate that our method significantly outperforms existing methods, achieving robust and accurate early action recognition. Specifically, its ability to handle action progression under different observation rates also specifically reflects the robustness of the proposed method. The code of this work is publicly available at https://github.com/Chenjie0921/Multiple-stage.
Keywords:
Early action recognition
Multi-stage query
Unobserved feature reconstruction
Query encoding