2 citations · 2 across the 8 of their papers we have counts for
10 papers
Unlocking Multi-Site Clinical Data: A Federated Approach to Privacy-First Child Autism Behavior Analysis
Guangyu Sun, Wenhan Wu, Zhishuai Guo +3
Automated recognition of autistic behaviors in children is essential for early intervention and objective clinical assessment. However, the development of robust models is severely…
Monocular Models are Strong Learners for Multi-View Human Mesh Recovery
Haoyu Xie, Shengkai Xu, Cheng Guo +6
Multi-view human mesh recovery (HMR) is broadly deployed in diverse domains where high accuracy and strong generalization are essential. Existing approaches can be broadly grouped…
KHMP: Frequency-Domain Kalman Refinement for High-Fidelity Human Motion Prediction
Wenhan Wu, Zhishuai Guo, Chen Chen +4
Stochastic human motion prediction aims to generate diverse, plausible futures from observed sequences. Despite advances in generative modeling, existing methods often produce pred…
Communication-Efficient Federated AUC Maximization with Cyclic Client Participation
Umesh Vangapally, Wenhan Wu, Chen Chen +1
Federated AUC maximization is a powerful approach for learning from imbalanced data in federated learning (FL). However, existing methods typically assume full client availability,…
UniSTFormer: Unified Spatio-Temporal Lightweight Transformer for Efficient Skeleton-Based Action Recognition
Wenhan Wu, Zhishuai Guo, Chen Chen +1
Skeleton-based action recognition (SAR) has achieved impressive progress with transformer architectures. However, existing methods often rely on complex module compositions and hea…
Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognition
Wenhan Wu, Zhishuai Guo, Chen Chen +2
Zero-shot skeleton-based action recognition aims to develop models capable of identifying actions beyond the categories encountered during training. Previous approaches have primar…
FreqMixFormerV2: Lightweight Frequency-aware Mixed Transformer for Human Skeleton Action Recognition
Wenhan Wu, Pengfei Wang, Chen Chen +1
Transformer-based human skeleton action recognition has been developed for years. However, the complexity and high parameter count demands of these models hinder their practical ap…
Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer
Wenhan Wu, Ce Zheng, Zihao Yang +3
Recently, transformers have demonstrated great potential for modeling long-term dependencies from skeleton sequences and thereby gained ever-increasing attention in skeleton action…
Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language Models
Zheng Ma, Mianzhi Pan, Wenhan Wu +4
Vision-language models (VLMs) have shown impressive performance in substantial downstream multi-modal tasks. However, only comparing the fine-tuned performance on downstream tasks…
Part Aware Contrastive Learning for Self-Supervised Action Recognition
Yilei Hua, Wenhan Wu, Ce Zheng +4
In recent years, remarkable results have been achieved in self-supervised action recognition using skeleton sequences with contrastive learning. It has been observed that the seman…