Xiatian Zhu

Computer Science · Physical Sciences

51h-index15.9kcitations292works2.02yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Video Surveillance and Tracking Methods(73), Domain Adaptation and Few-Shot Learning(73), Human Pose and Action Recognition(66), Multimodal Machine Learning Applications(66), Advanced Neural Network Applications(49)

Publications293 total

Adaptive Diffusion-based Augmentation for Recommendation
arXiv (Cornell University)·2026Open Access
Adaptive Diffusion-based Augmentation for Recommendation
ArXiv.org·2026Open Access
Efficient4D: Fast Dynamic 3D Object Generation from a Single-view Video
International Journal of Computer Vision·2025
Efficient4D: Fast Dynamic 3D Object Generation from a Single-view Video
International Journal of Computer Vision·2025· 2 citedOpen Access
Reconstructing 3D Scenes in Native High Dynamic Range
arXiv (Cornell University)·2025Open Access
More Than A Shortcut: A Hyperbolic Approach To Early-Exit Networks
arXiv (Cornell University)·2025Open Access
Bayesian Test-time Adaptation for Object Recognition and Detection with Vision-language Models
arXiv (Cornell University)·2025Open Access
Unified Unsupervised Anomaly Detection via Matching Cost Filtering
arXiv (Cornell University)·2025Open Access
Dynamic Novel View Synthesis in High Dynamic Range
arXiv (Cornell University)·2025Open Access
Optimizing Deep Learning for Edge Deployment via Weight Statistics Aware Network Pruning
2025
DeMo++: Motion Decoupling for Autonomous Driving
arXiv (Cornell University)·2025Open Access
Robust Low-light Scene Restoration via Illumination Transition
arXiv (Cornell University)·2025Open Access
Deep learning techniques for DDoS attack detection: Concepts, analyses, challenges, and future directions
Expert Systems with Applications·2025· 2 citedOpen Access
Improving Gaussian Splatting with Localized Points Management
2025· 3 cited
Bayesian Test-Time Adaptation for Vision-Language Models
2025· 1 cited
TensoFlow: Tensorial Flow-Based Sampler for Inverse Rendering
2025
FAM Diffusion: Frequency and Attention Modulation for High-Resolution Image Generation with Stable Diffusion
2025
DreamPet: Text Driven Controllable 3D Animal Generation using Gaussian Splatting
SPIRE - Sciences Po Institutional REpository·2025
High Dynamic Range Novel View Synthesis with Single Exposure
arXiv (Cornell University)·2025Open Access
CostFilter-AD: Enhancing Anomaly Detection through Matching Cost Filtering
arXiv (Cornell University)·2025Open Access
page 1 of 15Next →

Frequent Co-authors

Shaogang Gong(33), Tao Xiang(7), Yanbei Chen(5), Qi Dong(5), Jiachen Lu(4), Li Zhang(4), Li Zhang(3), Wei Li(3), Mao Ye(3), Wei‐Shi Zheng(3), Zhiyi Cheng(3), Hanxiao Wang(3), Sixiao Zheng(2), Hengshuang Zhao(2), Zekun Luo(2), Yabiao Wang(2), Yanwei Fu(2), Jianfeng Feng(2), Philip H. S. Torr(2), Taiqing Wang(2)