ACSF-ED: Adaptive Cross-Scale Fusion Encoder-Decoder for Spatio-Temporal Action Detection  

作　　者：Wenju Wang Zehua Gu Bang Tang Sen Wang Jianfei Hao 

机构地区：[1]College of Publishing,University of Shanghai for Science and Technology,Shanghai,200093,China [2]Institute of Information Technology,Shanghai Baosight Software Co.,Ltd.,Shanghai,200940,China

出　　处：《Computers, Materials & Continua》2025年第2期2389-2414,共26页计算机、材料和连续体(英文)

基　　金：support for this work was supported by Key Lab of Intelligent and Green Flexographic Printing under Grant ZBKT202301.

摘　　要：Current spatio-temporal action detection methods lack sufficient capabilities in extracting and comprehending spatio-temporal information. This paper introduces an end-to-end Adaptive Cross-Scale Fusion Encoder-Decoder (ACSF-ED) network to predict the action and locate the object efficiently. In the Adaptive Cross-Scale Fusion Spatio-Temporal Encoder (ACSF ST-Encoder), the Asymptotic Cross-scale Feature-fusion Module (ACCFM) is designed to address the issue of information degradation caused by the propagation of high-level semantic information, thereby extracting high-quality multi-scale features to provide superior features for subsequent spatio-temporal information modeling. Within the Shared-Head Decoder structure, a shared classification and regression detection head is constructed. A multi-constraint loss function composed of one-to-one, one-to-many, and contrastive denoising losses is designed to address the problem of insufficient constraint force in predicting results with traditional methods. This loss function enhances the accuracy of model classification predictions and improves the proximity of regression position predictions to ground truth objects. The proposed method model is evaluated on the popular dataset UCF101-24 and JHMDB-21. Experimental results demonstrate that the proposed method achieves an accuracy of 81.52% on the Frame-mAP metric, surpassing current existing methods.

关 键 词：Spatio-temporal action detection encoder-decoder cross-scale fusion multi-constraint loss function 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]