activity
20222026
most citedOn the Design Fundamentals of Diffusion Models: A Survey

47 citations · 52 across the 12 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2026

Quality-Preserving Imperceptible Adversarial Attack on Skeleton-based Human Action Recognition

Ziyi Chang, Kanglei Zhou, Xiaohui Liang +1

Adversarial attacks on skeletal human action recognition have received significant attention. However, existing methods typically introduce noise-like perturbations that degrade mo…

cs.CV2026

ART: Adaptive Relational Transformer for Pedestrian Trajectory Prediction with Temporal-Aware Relations

Ruochen Li, Ziyi Chang, Junyan Hu +3

Accurate prediction of real-world pedestrian trajectories is crucial for a wide range of robot-related applications. Recent approaches typically adopt graph-based or transformer-ba…

cs.CV2023

Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradient

Zhengzhi Lu, He Wang, Ziyi Chang +2

Recently, methods for skeleton-based human activity recognition have been shown to be vulnerable to adversarial attacks. However, these attack methods require either the full knowl…

cs.CV2022

Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models

Ziyi Chang, Edmund J. C. Findlay, Haozheng Zhang +1

Generating realistic motions for digital humans is a core but challenging part of computer animations and games, as human motions are both diverse in content and rich in styles. Wh…

cs.CV2022★ 1 cited

3D Reconstruction of Sculptures from Single Images via Unsupervised Domain Adaptation on Implicit Models

Ziyi Chang, George Alex Koulieris, Hubert P. H. Shum

Acquiring the virtual equivalent of exhibits, such as sculptures, in virtual reality (VR) museums, can be labour-intensive and sometimes infeasible. Deep learning based 3D reconstr…

cs.CV2022★ 3 cited

Denoising Diffusion Probabilistic Models for Styled Walking Synthesis

Edmund J. C. Findlay, Haozheng Zhang, Ziyi Chang +1

Generating realistic motions for digital humans is time-consuming for many graphics applications. Data-driven motion synthesis approaches have seen solid progress in recent years t…