Kunyu Peng

Karlsruhe Institute of Technology — Germany

Computer Science · Physical Sciences

17h-index1.2kcitations115works2.92yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Advanced Neural Network Applications(30), Human Pose and Action Recognition(30), Advanced Image and Video Retrieval Techniques(23), Multimodal Machine Learning Applications(20), Video Surveillance and Tracking Methods(15)

Publications115 total

Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalization
International Journal of Computer Vision·2026
HybriDLA: Hybrid Generation for Document Layout Analysis
Underline Science Inc.·2026Open Access
771 - HybriDLA: Hybrid Generation for Document Layout Analysis
Underline Science Inc.·2026Open Access
OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedback
arXiv (Cornell University)·2025Open Access
VISO-Grasp: Vision-Language Informed Spatial Object-centric 6-DoF Active View Planning and Grasping in Clutter and Invisibility
2025
Dense Semantic Bird-Eye-View Map Generation from Sparse LiDAR Point Clouds via Distribution-aware Feature Fusion
2025
RefAtomNet++: Advancing Referring Atomic Video Action Recognition using Semantic Retrieval based Multi-Trajectory Mamba
arXiv (Cornell University)·2025Open Access
EReLiFM: Evidential Reliability-Aware Residual Flow Meta-Learning for Open-Set Domain Generalization under Noisy Labels
arXiv (Cornell University)·2025Open Access
Exploring Single Domain Generalization of LiDAR-based Semantic Segmentation under Imperfect Labels
arXiv (Cornell University)·2025Open Access
Snap, Segment, Deploy: A Visual Data and Detection Pipeline for Wearable Industrial Assistants
2025
Exploring Video-Based Driver Activity Recognition under Noisy Labels
2025
Segment-to-Act: Label-Noise-Robust Action-Prompted Video Segmentation Towards Embodied Intelligence
arXiv (Cornell University)·2025Open Access
RoHOI: Robustness Benchmark for Human-Object Interaction Detection
arXiv (Cornell University)·2025· 1 citedOpen Access
Hallucinating 360°: Panoramic Street-View Generation via Local Scenes Diffusion and Probabilistic Prompting
ArXiv.org·2025Open Access
Exploring Self-supervised Skeleton-based Action Recognition in Occluded Environments
2025
CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding
arXiv (Cornell University)·2025Open Access
Out-of-Distribution Semantic Occupancy Prediction
arXiv (Cornell University)·2025Open Access
HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarios
arXiv (Cornell University)·2025Open Access
DiffCAP: Diffusion-based Cumulative Adversarial Purification for Vision Language Models
arXiv (Cornell University)·2025Open Access
Go Beyond Earth: Understanding Human Actions and Scenes in Microgravity Environments
arXiv (Cornell University)·2025· 1 citedOpen Access
page 1 of 6Next →

Frequent Co-authors

Rainer Stiefelhagen(47), Kailun Yang(44), Alina Roitberg(25), Jiaming Zhang(13), Jiaming Zhang(11), Jiaming Zhang(10), Ruiping Liu(7), Hao Shi(6), Simon Reiß(6), Chaoxiang Ma(5), M. Saquib Sarfraz(5), Junwei Zheng(5), Yufan Chen(5), Haodong Fu(4), Huayao Liu(4), Ruiping Liu(4), Junwei Zheng(4), David Schneider(4), Ke Cao(4), Ruiping Liu(4)