Tianzhu Zhang

University of Science and Technology of China — China

Computer Science · Physical Sciences

4h-index41citations26works1.62yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Video Surveillance and Tracking Methods(5), Human Pose and Action Recognition(5), 3D Shape Modeling and Analysis(4), 3D Surveying and Cultural Heritage(3), Gaze Tracking and Assistive Technology(3)

Publications27 total

SMTrack: State-Aware Mamba for Efficient Temporal Modeling in Visual Tracking
ArXiv.org·2026Open Access
SMTrack: State-Aware Mamba for Efficient Temporal Modeling in Visual Tracking
arXiv (Cornell University)·2026Open Access
ScaleDepth: Decomposing Metric Depth Estimation into Semantic-aware Scale Prediction and Adaptive Relative Depth Estimation
IEEE Transactions on Circuits and Systems for Video Technology·2026
SMTrack: State-Aware Mamba for Efficient Temporal Modeling in Visual Tracking
IEEE Transactions on Image Processing·2026
WildSplatting: Unposed Incremental 3D Gaussian Splatting Reconstruction in the Wild
2025· 1 cited
UniSOT: A Unified Framework for Multi-Modality Single Object Tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence·2025Open Access
ER-Depth: Enhancing the Robustness of Self-Supervised Monocular Depth Estimation in Challenging Scenes
ACM Transactions on Multimedia Computing Communications and Applications·2025· 1 cited
CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selection
arXiv (Cornell University)·2025Open Access
Rethinking Noisy Video-Text Retrieval via Relation-aware Alignment
2025· 1 cited
Rethinking Correspondence-based Category-Level Object Pose Estimation
2025
B2-3D++: Uncertainty-aware Hierarchical Registration Network with Domain Alignment
2025Open Access
Bridge 2D-3D: Uncertainty-aware Hierarchical Registration Network with Domain Alignment
Proceedings of the AAAI Conference on Artificial Intelligence·2025· 2 citedOpen Access
SAS: Segment Any 3D Scene with Integrated 2D Priors
arXiv (Cornell University)·2025Open Access
SAM-Glomeruli: Enhanced Segment Anything Model for Precise Glomeruli Segmentation
Lecture notes in computer science·2025
Learning Discriminative Features for Visual Tracking via Scenario Decoupling
International Journal of Computer Vision·2024
Towards Unsupervised Domain Bridging via Image Degradation in Semantic Segmentation
arXiv (Cornell University)·2024Open Access
DN-4DGS: Denoised Deformable Network with Temporal-Spatial Aggregation for Dynamic Scene Rendering
arXiv (Cornell University)·2024· 1 citedOpen Access
MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting
arXiv (Cornell University)·2024· 1 citedOpen Access
Localization and Expansion: A Decoupled Framework for Point Cloud Few-shot Semantic Segmentation
arXiv (Cornell University)·2024Open Access
Towards Anytime Retrieval: A Benchmark for Anytime Person Re-Identification
2024· 3 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Wenfei Yang(12), Jiacheng Deng(8), Yongdong Zhang(5), Yanzhe Liang(5), Jiahao Lu(5), Ruijie Zhu(5), Yinchao Ma(5), Xinjun Li(4), Wangkai Li(4), Hanzhi Chang(3), Zhixin Cheng(3), Baoqun Yin(3), Dewei Yang(3), Zhangyu He(3), Zhaoyang Li(2), Huayu Mai(2), Zhiwei Xiong(2), Guoxin Xiong(2), Yuan Wang(2), Zhaoyang Li(2)