Experimental results on three public datasets demonstrate that MDSTA-Net achieves favorable recognition performance compared with several representative methods, indicating that multi-scale spatial feature enhancement and key spatiotemporal information aggregation can effectively improve action recognition performance.
Abstract
Video action recognition requires the joint modeling of spatial appearance information and temporal dynamics. However, existing efficient action recognition methods based on two-dimensional convolution still have limitations in representing multi-scale spatial cues and aggregating key spatiotemporal information. To address these issues, this paper proposes an action recognition network based on Multi-Scale Dilated Feature Fusion and Decoupled Spatiotemporal Attention Pooling, termed MDSTA-Net. The proposed method adopts TSM as the basic temporal modeling framework and ResNet-50 as the backbone network. First, a Multi-Scale Dilated Feature Fusion module (MSDF) is designed to construct continuous multi-scale receptive fields through parallel convolutional branches with different dilation rates. An adaptive branch aggregation mechanism is further introduced to dynamically fuse responses at different scales, thereby enhancing the representation of both local details and broader contextual information. Second, a Decoupled Spatiotemporal Attention Pooling module (DSTAP) is proposed to model key action frames along the temporal dimension and salient discriminative regions along the spatial dimension. A residual pooling path is also incorporated to preserve global semantic information, improving the discriminative capability of video-level action representations. Experimental results on three public datasets, namely Something-Something V2, Kinetics-400, and HMDB51, demonstrate that MDSTA-Net achieves favorable recognition performance compared with several representative methods. Ablation studies further verify the effectiveness of MSDF and DSTAP, indicating that multi-scale spatial feature enhancement and key spatiotemporal information aggregation can effectively improve action recognition performance.
A Multi-Scale Convolutional Neural Network integrated with a Long Short-Term Memory network for sports video action recognition is proposed, demonstrating the potential of the proposed framework to combine spatial and temporal information for sports video action recognition.
Hai-Ming Yang, H. Sarim, Xiao-Juan Ma et al.· Journal of Visualized Experi...· 0 citations
A semantic-guided multi-scale feature pyramid learning method that significantly outperforms existing methods in scenarios requiring fine-grained local feature recognition, especially in topics such as "laboratory," "medical surgery," and "cooking process".
Jin-Yao Zhang· Poster Volume 0007 The 2026...· 0 citations
This article proposes ActNet, a novel deep convolutional neural network architecture that combines multi-scale feature learning with a focus-aware attention mechanism to address the problem of recognizing human actions from still images.
YOWOFormer is presented, which replaces the 3D CNN with VideoMAE and adopts YOLOv11 as the 2D backbone, introducing two bridging modules: a Spatial Query Adapter (SQA) that converts transformer tokens into spatial feature maps via learnable queries and cross-attention and a Bidirectional Spatio-Temporal Fusion (BSTF) m...
Soft sensors are vital for industrial monitoring but face severe challenges arising from complex spatiotemporal multi-scale dynamics and prevalent information redundancy. Existing deep learning methods often struggle to capture multi-scale dependencies and suffer from weak or redundant interactions introduced by fully...
Xiao Li, Shi-Wei Gao, Meng-Yi Chen et al.· Measurement science and tech...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.