Sanyuan Zhao

Beijing Institute of Technology — China

Computer Science · Physical Sciences

13h-index1.5kcitations64works0.82yr 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(17), Advanced Image and Video Retrieval Techniques(17), Advanced Neural Network Applications(16), Visual Attention and Saliency Detection(15), Human Pose and Action Recognition(8)

Publications64 total

A Progressive Approach to Learn Global and Local Multi-view Features for 3D Visual Grounding
Lecture notes in computer science·2025
Modality Confusion Learning: A Versatile Framework for Visible-Infrared Re-identification
International Journal of Computer Vision·2025· 1 cited
Intermediate domain-based unsupervised domain adaptive visual-infrared cross-modal person re-identification
2025Open Access
World Knowledge-Enhanced Reasoning Using Instruction-Guided Interactor in Autonomous Driving
Proceedings of the AAAI Conference on Artificial Intelligence·2025Open Access
World knowledge-enhanced Reasoning Using Instruction-guided Interactor in Autonomous Driving
arXiv (Cornell University)·2024Open Access
GTMS: A Gradient-Driven Tree-Guided Mask-Free Referring Image Segmentation Method
Lecture notes in computer science·2024
RepVF: A Unified Vector Fields Representation for Multi-task 3D Perception
Lecture notes in computer science·2024· 1 cited
Graph convolution-based feature disentanglement for visible-infrared person re-identification
2024Open Access
A simple but effective vision transformer framework for visible–infrared person re-identification
Computer Vision and Image Understanding·2024· 2 cited
RepVF: A Unified Vector Fields Representation for Multi-task 3D Perception
arXiv (Cornell University)·2024Open Access
TextFormer: A Query-based End-to-end Text Spotter with Mixed Supervision
Machine Intelligence Research·2024· 6 cited
InteractiveVideo: User-Centric Controllable Video Generation with Synergistic Multimodal Instructions
arXiv (Cornell University)·2024Open Access
A Simple But Effective Vision Transformer Framework for Visible-Infrared Person Re-Identification
SSRN Electronic Journal·2024Open Access
Using Self-Supervised Dual Constraint Contrastive Learning for Cross-Modal Retrieval
Frontiers in artificial intelligence and applications·2023· 4 citedOpen Access
TextFormer: A Query-based End-to-End Text Spotter with Mixed Supervision
arXiv (Cornell University)·2023· 1 citedOpen Access
Spectrum-irrelevant fine-grained representation for visible–infrared person re-identification
Computer Vision and Image Understanding·2023· 12 citedOpen Access
A New Framework of Collaborative Learning for Adaptive Metric Distillation
IEEE Transactions on Neural Networks and Learning Systems·2023· 5 cited
Generalized Few-Shot 3D Object Detection of LiDAR Point Cloud for Autonomous Driving
arXiv (Cornell University)·2023· 3 citedOpen Access
Learning Fine-Grained Information with Capsule-Wise Attention for Salient Object Detection
IEEE Transactions on Multimedia·2023· 8 cited
Online Teaching of Computer Fundamentals Course During the Pandemic
Communications in computer and information science·2023
page 1 of 4Next →

Frequent Co-authors

Jianbing Shen(15), Jianbing Shen(12), Fengxia Li(8), Kin‐Man Lam(7), Zhengchao Lei(7), Hongmei Song(5), Xiameng Qin(5), Jiahao Gong(4), Mang Ye(3), Yiyuan Zhang(3), Qi Qi(3), Xingping Dong(3), Wenguan Wang(2), Yuhao Kang(2), Jianbing Shen(2), Zongji Zhao(2), Tao Li(2), Zhiyuan Liang(2), Zongzheng Wen(2), Yukun Zhai(2)