6 citations · 8 across the 13 of their papers we have counts for
17 papers
EXE: Egocentric Cross-Embodiment Pretraining via Factorized Latent Actions for VLA Models
Qingyuan Cai, Bo Zhang, Yongzhen Huang +1
Vision-Language-Action (VLA) models are bottlenecked by the scarcity of robot data. Egocentric human manipulation videos offer an abundant, diverse, and semantically-rich alternati…
Are Multimodal Benchmarks Really Useful? Item-Level Multimodal Benchmark Diagnosis via Structure-Response Co-Calibration
Shiqi Zhang, Weixin Zeng, Ziheng Zhang +2
Multimodal benchmarks are central to evaluating whether models can reason over information from multiple modalities. However, existing literature has revealed that some benchmarks…
MMGait: Benchmarking and Unifying Gait Recognition across Heterogeneous Modalities
Saihui Hou, Chenye Wang, Qingyuan Cai +2
Gait recognition is commonly studied using RGB videos or their derived silhouettes and poses. Yet human walking produces heterogeneous photometric, geometric, and motion cues that…
MMGait: Towards Multi-Modal Gait Recognition
Chenye Wang, Qingyuan Cai, Saihui Hou +2
Gait recognition has emerged as a powerful biometric technique for identifying individuals at a distance without requiring user cooperation. Most existing methods focus primarily o…
BarbieGait: An Identity-Consistent Synthetic Human Dataset with Versatile Cloth-Changing for Gait Recognition
Qingyuan Cai, Saihui Hou, Xuecai Hu +1
Gait recognition, as a reliable biometric technology, has seen rapid development in recent years while it faces significant challenges caused by diverse clothing styles in the real…
Learning Geometric Invariance for Gait Recognition
Zengbin Wang, Junjie Li, Saihui Hou +6
The goal of gait recognition is to extract identity-invariant features of an individual under various gait conditions, e.g., cross-view and cross-clothing. Most gait models strive…
FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimation
Qingyuan Cai, Linxin Zhang, Xuecai Hu +2
Recent approaches for monocular 3D human pose estimation (3D HPE) have achieved leading performance by directly regressing 3D poses from 2D keypoint sequences. Despite the rapid pr…
GaitSnippet: Gait Recognition Beyond Unordered Sets and Ordered Sequences
Saihui Hou, Chenye Wang, Wenpeng Lang +2
Recent advancements in gait recognition have significantly enhanced performance by treating silhouettes as either an unordered set or an ordered sequence. However, both set-based a…
OmniDiff: A Comprehensive Benchmark for Fine-grained Image Difference Captioning
Yuan Liu, Saihui Hou, Saijie Hou +3
Image Difference Captioning (IDC) aims to generate natural language descriptions of subtle differences between image pairs, requiring both precise visual change localization and co…
OpenAnimals: Revisiting Person Re-Identification for Animals Towards Better Generalization
Saihui Hou, Panjian Huang, Zengbin Wang +4
This paper addresses the challenge of animal re-identification, an emerging field that shares similarities with person re-identification but presents unique complexities due to the…
Artificial Immune System of Secure Face Recognition Against Adversarial Attacks
Min Ren, Yunlong Wang, Yuhao Zhu +4
Insect production for food and feed presents a promising supplement to ensure food safety and address the adverse impacts of agriculture on climate and environment in the future. H…
OpenGait: A Comprehensive Benchmark Study for Gait Recognition towards Better Practicality
Chao Fan, Saihui Hou, Junhao Liang +5
Gait recognition, a rapidly advancing vision technology for person identification from a distance, has made significant strides in indoor settings. However, evidence suggests that…
POPDG: Popular 3D Dance Generation with PopDanceSet
Zhenye Luo, Min Ren, Xuecai Hu +2
Generating dances that are both lifelike and well-aligned with music continues to be a challenging task in the cross-modal domain. This paper introduces PopDanceSet, the first data…
Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoiser
Qingyuan Cai, Xuecai Hu, Saihui Hou +2
Recently, diffusion-based methods for monocular 3D human pose estimation have achieved state-of-the-art (SOTA) performance by directly regressing the 3D joint coordinates from the…
QAGait: Revisit Gait Recognition from a Quality Perspective
Zengbin Wang, Saihui Hou, Man Zhang +5
Gait recognition is a promising biometric method that aims to identify pedestrians from their unique walking patterns. Silhouette modality, renowned for its easy acquisition, simpl…
Towards More Efficient Depression Risk Recognition via Gait
Min Ren, Muchan Tao, Xuecai Hu +3
Depression, a highly prevalent mental illness, affects over 280 million individuals worldwide. Early detection and timely intervention are crucial for promoting remission, preventi…
FastPoseGait: A Toolbox and Benchmark for Efficient Pose-based Gait Recognition
Shibei Meng, Yang Fu, Saihui Hou +3
We present FastPoseGait, an open-source toolbox for pose-based gait recognition based on PyTorch. Our toolbox supports a set of cutting-edge pose-based gait recognition algorithms…