Peixi Peng

Shanghai Jiao Tong University — China

Computer Science · Physical Sciences

18h-index2.0kcitations81works2.22yr 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(24), Advanced Neural Network Applications(14), Domain Adaptation and Few-Shot Learning(14), Human Pose and Action Recognition(10), Multimodal Machine Learning Applications(10)

Publications81 total

SERF: Spatiotemporal-Aware Event-RGB Fusion for Steering Angle Prediction
IEEE Transactions on Intelligent Transportation Systems·2025
Multi-faceted Complementary Learning for Incomplete Multi-view Multi-label Classification
2025
CASA: Class-Agnostic Shared Attributes in Vision-Language Models for Efficient Incremental Object Detection
2025
VLMs-Guided Representation Distillation for Efficient Vision-Based Reinforcement Learning
2025
LongDWM: Cross-Granularity Distillation for Building a Long-Term Driving World Model
arXiv (Cornell University)·2025Open Access
A Global Visual Information Intervention Model for Medical Visual Question Answering
Computers in Biology and Medicine·2025
Visual Reinforcement Learning with Residual Action
Proceedings of the AAAI Conference on Artificial Intelligence·2025Open Access
Exploiting Continuous Motion Clues for Vision-Based Occupancy Prediction
Proceedings of the AAAI Conference on Artificial Intelligence·2025· 1 citedOpen Access
Towards Building Human-like Smart Agents in Modern 3D Video Games (Student Abstract)
Proceedings of the AAAI Conference on Artificial Intelligence·2025Open Access
Delta-Triplane Transformers as Occupancy World Models
arXiv (Cornell University)·2025Open Access
Parallel Multi-Attention and Gated Fusion for Visual Question Localized Answering in Surgical Scenes
IEEE Journal of Biomedical and Health Informatics·2025
A fuzzy logic constrained particle swarm optimization algorithm for industrial design problems
Applied Soft Computing·2024· 8 cited
CASA: Class-Agnostic Shared Attributes in Vision-Language Models for Efficient Incremental Object Detection
arXiv (Cornell University)·2024Open Access
Gelatin Methacryloyl (GelMA) - 45S5 Bioactive Glass (BG) Composites for Bone Tissue Engineering: 3D Extrusion Printability and Cytocompatibility Assessment Using Human Osteoblasts
ACS Biomaterials Science & Engineering·2024· 11 cited
Eye Gaze Guided Cross-Modal Alignment Network for Radiology Report Generation
IEEE Journal of Biomedical and Health Informatics·2024· 4 cited
Prior-Posterior Knowledge Prompting-and-Reasoning for Surgical Visual Question Localized-Answering
2024· 1 cited
DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning
2024· 3 cited
Density-Adaptive Model Based on Motif Matrix for Multi-Agent Trajectory Prediction
2024· 5 cited
Sensitivity Decouple Learning for Image Compression Artifacts Reduction
arXiv (Cornell University)·2024Open Access
Dual modality prompt learning for visual question-grounded answering in robotic surgery
Visual Computing for Industry Biomedicine and Art·2024· 3 citedOpen Access
page 1 of 5Next →

Frequent Co-authors

Yonghong Tian(35), Tiejun Huang(14), Yaowei Wang(9), Junliang Xing(7), Yangru Huang(6), Guangyao Chen(5), Xiangqian Wang(5), Li Ma(4), Yidong Li(4), Zongqing Lu(4), Tao Xiang(3), Mengyue Geng(3), Yi Jin(3), Yunpeng Zhai(3), Yifan Zhao(3), Guang Tan(3), Haoran Xu(3), Peiyin Xing(3), Massimiliano Pontil(2), Jia Li(2)