paper-with-me

Gait Recognition

2개 벤치마크 · 논문 258편 · 이 태스크의 논문 보기 →

Benchmarks

OUMVLP

결과 7개

Gait3D

결과 4개

Most implemented

Papers

Who Remains, What Changes: Identity Anchored Composed Gait Retrieval

2026-08-27 · Jingchen Fei, Zengbin Wang, Yukun Liu, Muyi Sun 외 arxiv

Gait recognition has achieved remarkable progress, yet existing methods remain confined to rigid visual matching and often overlook the potential of natural language instructions for interactive retrieval. In this paper,…

Gait Recognition

Text-guided Feature Disentanglement for Cross-modal Gait Recognition

2026-05-29 · Zhiyang Lu, Ming Cheng arxiv

Gait recognition is a biometric technique that identifies individuals based on their walking patterns, offering advantages in long-range, non-intrusive scenarios. However, real-world scenarios often involve heterogeneous…

Gait Recognition

DiffCrossGait: Trajectory-Level Alignment for 2D-3D Cross-Modal Gait Recognition via Latent Diffusion

2026-05-29 · Zhiyang Lu, Ming Cheng arxiv

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 embeddings, we propose DiffCrossGait, whi…

Gait Recognition

EventGait: Towards Robust Gait Recognition with Event Streams

2026-05-21 · Senyan Xu, Shuai Chen, Chuanfu Shen, Kean Liu 외 arxiv

Gait recognition enables non-intrusive, privacy-preserving identification but suffers in uncontrolled environments due to illumination and motion sensitivity of conventional cameras. In this work, we explore gait recogni…

Gait Recognition

Local Spatiotemporal Convolutional Network for Robust Gait Recognition

2026-05-14 · Xiaoyun Wang, Cunrong Li, Wu Wang arxiv

Gait recognition, as a promising biometric technology, identifies individuals through their unique walking patterns and offers distinctive advantages including non-invasiveness, long-range applicability, and resistance t…

Gait Recognition

GaitProtector: Impersonation-Driven Gait De-Identification via Training-Free Diffusion Latent Optimization

2026-05-12 · Huiran Duan, Qian Zhou, Zhongliang Guo, Junhao Dong 외 arxiv

Conventional gait de-identification methods often encounter an inherent trade-off: they either provide insufficient identity suppression or introduce spatiotemporal distortions that impede structure-sensitive downstream …

Gait Recognition

전체 258편 보기 →