5 papers
DiffCrossGait: Trajectory-Level Alignment for 2D-3D Cross-Modal Gait Recognition via Latent Diffusion
Zhiyang Lu, Ming Cheng
Cross-modal 2D-3D gait recognition is impeded by inherent domain discrepancies between 2D silhouette and 3D LiDAR range-view representations. While prior methods align only final e…
Text-guided Feature Disentanglement for Cross-modal Gait Recognition
Zhiyang Lu, Ming Cheng
Gait recognition is a biometric technique that identifies individuals based on their walking patterns, offering advantages in long-range, non-intrusive scenarios. However, real-wor…
Walking Further: Semantic-aware Multimodal Gait Recognition Under Long-Range Conditions
Zhiyang Lu, Wen Jiang, Tianren Wu +4
Gait recognition is an emerging biometric technology that enables non-intrusive and hard-to-spoof human identification. However, most existing methods are confined to short-range,…
STARFlow: Spatial Temporal Feature Re-embedding with Attentive Learning for Real-world Scene Flow
Zhiyang Lu, Qinghan Chen, Ming Cheng
Scene flow prediction is a crucial underlying task in understanding dynamic scenes as it offers fundamental motion information. However, contemporary scene flow methods encounter t…
SSRFlow: Semantic-aware Fusion with Spatial Temporal Re-embedding for Real-world Scene Flow
Zhiyang Lu, Qinghan Chen, Zhimin Yuan +1
Scene flow, which provides the 3D motion field of the first frame from two consecutive point clouds, is vital for dynamic scene perception. However, contemporary scene flow methods…