Structural vibration-based gait recognition aims to identify pedestrians through their unique vibration patterns and has gained significant attention for its non-invasive nature. However, existing methods primarily rely on manually crafted features and convolutional neural networks (CNNs) to extract local details, without considering global gait features in vibration signals. To address this limitation, we propose CSCA, a novel framework designed to capture discriminative global gait features through collaborative spatial and channel attention. Specifically, CSCA consists of two key components: Mamba-inspired Linear Channel Attention (MLCA) and Strip Pooling-guided Spatial Attention (SPSA). MLCA integrates Mamba with linear attention to enhance discriminative attention in the channel dimension by capturing global gait features. Additionally, SPSA integrates axial strip pooling with multikernel depth-wise convolutions to extract multi-level spatial semantic features. Experimental results on the VIBEID dataset demonstrate that CSCA achieves state-of-the-art performance across diverse environmental conditions, with identity recognition accuracy exceeding 96%. Code is available at https://github.com/xiaomush/CSCA.

Human identification at a distance (HID) faces challenges due to the difficulty of acquiring traditional biometric modalities like face and fingerprints. Gait recognition offers a viable solution since it can be captured at a distance. To promote progress in gait recognition and provide a fair evaluation platform, the International Competition on Human Identification at a Distance (HID) has been organized annually since 2020. Since 2023, the competition has adopted the challenging SUSTech-Competition dataset, which includes significant variations in clothing, carried objects, and view angles. No training data is provided, requiring participants to train their models using external datasets. Each year, the competition applies a different random seed to generate distinct evaluation splits, reducing the risk of overfitting and ensuring fair evaluation of cross-domain generalization. Although the previous two competitions (HID 2023 and HID 2024) already utilized this dataset, HID 2025 aimed explicitly to explore whether algorithmic improvements could surpass the accuracy limits observed previously. Despite these heightened challenges, participants again demonstrated significant advancements, with the highest accuracy reaching 94.2%, setting a new benchmark for this dataset. We also analyze key technical trends and outline potential directions for future research on gait recognition.

Skeleton-based gait emotion recognition has received significant attention due to its wide-ranging applications. However, existing methods primarily focus on extracting spatial and local temporal motion information, failing to capture long-range temporal representations. In this paper, we propose CGTGait, a novel framework that collaboratively integrates graph convolution and transformers to extract discriminative spatiotemporal features for gait emotion recognition. Specifically, CGTGait consists of multiple CGT blocks, where each block employs graph convolution to capture frame-level spatial topology and the transformer to model global temporal dependencies. Additionally, we introduce a Bidirectional Cross-Stream Fusion (BCSF) module to effectively aggregate posture and motion spatiotemporal features, facilitating the exchange of complementary information between the two streams. We evaluate our method on two widely used datasets, Emotion-Gait and ELMD, demonstrating that our CGTGait achieves state-of-the-art or at least competitive performance while reducing computational complexity by approximately 82.2% (only requiring 0.34G FLOPs) during testing. Code is available at https://github.com/githubzjj1/CGTGait.

Ruichu Cai, Junhao Lu, Zhongjie Chen, Boyan Xu, Zhifeng Hao. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.