Dengxin Dai

Huawei Technologies (China) — China

Computer Science · Physical Sciences

46h-index11.5kcitations233works8.92yr 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(68), Domain Adaptation and Few-Shot Learning(59), Multimodal Machine Learning Applications(45), Advanced Image and Video Retrieval Techniques(39), Advanced Vision and Imaging(35)

Publications233 total

Reflection Removal through Efficient Adaptation of Diffusion Transformers
arXiv (Cornell University)·2025Open Access
ACDC: The Adverse Conditions Dataset With Correspondences for Robust Semantic Driving Scene Perception
IEEE Transactions on Pattern Analysis and Machine Intelligence·2025· 1 cited
GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering
2025Open Access
ECCV 2024 W-CODA: 1st Workshop on Multimodal Perception and Comprehension of Corner Cases in Autonomous Driving
arXiv (Cornell University)·2025Open Access
Robust Object Detection with Domain-Invariant Training and Continual Test-Time Adaptation
International Journal of Computer Vision·2025
RealDriveSim: A Realistic Multi-Modal Multi-Task Synthetic Dataset for Autonomous Driving
2025· 1 cited
Beyond Calibration: Physically Informed Learning for Raw-to-Raw Mapping
arXiv (Cornell University)·2025Open Access
Status, Challenges and Countermeasures of Inclusive Infrastructure
Lecture notes in civil engineering·2025
U-BEV: Height-aware Bird’s-Eye-View Segmentation and Neural Map-based Relocalization
2024· 7 cited
Research on Intelligent Diagnosis Integrating Disease Subgraph and Large Language Model
2024
MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentation
Lecture notes in computer science·2024· 8 cited
Test-Time Training for Hyperspectral Image Super-Resolution
IEEE Transactions on Pattern Analysis and Machine Intelligence·2024· 1 cited
Test-time Training for Hyperspectral Image Super-resolution
arXiv (Cornell University)·2024Open Access
MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentation
arXiv (Cornell University)·2024Open Access
FreePoint: Unsupervised Point Cloud Instance Segmentation
2024· 12 cited
Object-centric Cross-modal Feature Distillation for Event-based Object Detection
2024· 6 cited
Benchmarking the Robustness of LiDAR Semantic Segmentation Models
International Journal of Computer Vision·2024· 19 cited
Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities
arXiv (Cornell University)·2024· 3 citedOpen Access
MTR++: Multi-Agent Motion Prediction With Symmetric Scene Modeling and Guided Intention Querying
IEEE Transactions on Pattern Analysis and Machine Intelligence·2024· 115 cited
2D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentation
2024· 5 cited
page 1 of 12Next →

Frequent Co-authors

Luc Van Gool(37), Christos Sakaridis(9), Lukas Hoyer(4), Simon Hecker(4), Wen Li(4), Stamatios Georgoulis(3), Olga Fink(3), Wen Yang(3), Yuhua Chen(2), Simon Vandenhende(2), Marc Proesmans(2), Radu Timofte(2), Haoran Wang(2), Alexander Liniger(2), Martin Hahner(2), Fisher Yu(2), Li Jiang(2), Bernt Schiele(2), Hong Sun(2), Anton Obukhov(2)