2026 Dengxin Dai: Computer Science Researcher – H-Index, Publications & Awards

Discipline name	D-Index	World Ranking	Current World Ranking	National Ranking	Current National Ranking	Publications	Citations
Computer Science	49	5787	5621	120	120	219	13007

Overview

Dengxin Dai is affiliated with ETH Zurich in Switzerland and has a focus on research within the field of Computer Science, particularly in Computer Vision and Pattern Recognition. Their work spans multiple subfields including Artificial Intelligence, Aerospace Engineering, Automotive Engineering, and Media Technology.

The scientist's research covers several main topics, such as:

Advanced Neural Network Applications
Domain Adaptation and Few-Shot Learning
Multimodal Machine Learning Applications
Advanced Vision and Imaging
Robotics and Sensor-Based Localization
Video Surveillance and Tracking Methods
Image Enhancement Techniques

Dengxin Dai has contributed extensively to the academic literature, with significant publications in key venues including:

arXiv (Cornell University)
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IEEE Transactions on Pattern Analysis and Machine Intelligence
International Journal of Computer Vision
2021 IEEE/CVF International Conference on Computer Vision (ICCV)

Notable recent papers include:

"Multi-Task Learning for Dense Prediction Tasks: A Survey" (2021), published in IEEE Transactions on Pattern Analysis and Machine Intelligence
"DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation" (2022), presented at the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
"Continual Test-Time Domain Adaptation" (2022), also published at the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
"Decoupling Zero-Shot Semantic Segmentation" (2022), presented at the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
"Deep Gradient Learning for Efficient Camouflaged Object Detection" (2023), published in Machine Intelligence Research

Frequent co-authors in Dengxin Dai's research include:

Luc Van Gool
Lukas Hoyer
Bernt Schiele
Alexander Liniger
Christos Sakaridis

Best Publications

Domain Adaptive Faster R-CNN for Object Detection in the Wild

Yuhua Chen;Wen Li;Christos Sakaridis;Dengxin Dai

1542
Citations
Semantic Foggy Scene Understanding with Synthetic Data

Christos Sakaridis;Dengxin Dai;Luc Van Gool;Luc Van Gool

840
Citations
Multi-Task Learning for Dense Prediction Tasks: A Survey.

Simon Vandenhende;Stamatios Georgoulis;Wouter Van Gansbeke;Marc Proesmans

706
Citations
DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation

Lukas Hoyer;Dengxin Dai;Luc Van Gool

532
Citations
Continual Test-Time Domain Adaptation

Unknown

504
Citations
Semantic Foggy Scene Understanding with Synthetic Data

Christos Sakaridis;Dengxin Dai;Luc Van Gool;Luc Van Gool

397
Citations
Fast Optical Flow Using Dense Inverse Search

Till Kroeger;Radu Timofte;Dengxin Dai;Luc J. Van Gool;Luc J. Van Gool

393
Citations
Satellite Image Classification via Two-Layer Sparse Coding With Biased Image Representation

Dengxin Dai;Wen Yang

363
Citations
MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation

Unknown

324
Citations
Decoupling Zero-Shot Semantic Segmentation

Unknown

312
Citations
ACDC: The Adverse Conditions Dataset With Correspondences for Semantic Driving Scene Understanding

Christos Sakaridis;Dengxin Dai;Luc Van Gool

266
Citations
Deep Gradient Learning for Efficient Camouflaged Object Detection

Unknown

264
Citations
Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding

Christos Sakaridis;Dengxin Dai;Simon Hecker;Luc Van Gool

247
Citations
End-to-End Learning of Driving Models with Surround-View Cameras and Route Planners

Simon Hecker;Dengxin Dai;Luc Van Gool

239
Citations
Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime

Dengxin Dai;Luc Van Gool

232
Citations
HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation

Unknown

231
Citations
Jointly Optimized Regressors for Image Super-resolution

D. Dai;R. Timofte;L. Van Gool

209
Citations
Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation

Christos Sakaridis;Dengxin Dai;Luc Van Gool

192
Citations
LiDAR Snowfall Simulation for Robust 3D Object Detection

Unknown

184
Citations
Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather

Martin Hahner;Christos Sakaridis;Dengxin Dai;Luc Van Gool

171
Citations
Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather

Martin Hahner;Christos Sakaridis;Dengxin Dai;Luc Van Gool

171
Citations
End-to-End Urban Driving by Imitating a Reinforcement Learning Coach

Zhejun Zhang;Alexander Liniger;Dengxin Dai;Fisher Yu

168
Citations
Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime

Dengxin Dai;Luc Van Gool

152
Citations
Latent Dictionary Learning for Sparse Representation Based Classification

Meng Yang;Dengxin Dai;Lilin Shen;Luc Van Gool

140
Citations
Is image super-resolution helpful for other vision tasks?

Dengxin Dai;Yujian Wang;Yuhua Chen;Luc Van Gool

138
Citations
Domain Generalization and Adaptation Using Low Rank Exemplar SVMs

Wen Li;Zheng Xu;Dong Xu;Dengxin Dai

128
Citations
Curriculum Model Adaptation with Synthetic and Real Data for Semantic Foggy Scene Understanding

Dengxin Dai;Christos Sakaridis;Simon Hecker;Luc Van Gool;Luc Van Gool

124
Citations
Ensemble Projection for Semi-supervised Image Classification

Dengxin Dai;Luc Van Gool

121
Citations
Don’t Forget The Past: Recurrent Depth Estimation from Monocular Video

Vaishakh Patil;Wouter Van Gansbeke;Dengxin Dai;Luc Van Gool

115
Citations
Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation

Christos Sakaridis;Dengxin Dai;Luc Van Gool

102
Citations
Polarimetric SAR image classification using multifeatures combination and extremely randomized clustering forests

Tongyuan Zou;Wen Yang;Dengxin Dai;Hong Sun

101
Citations

Frequent Co-Authors

Luc Van Gool Institute for Computer Science, Artificial Intelligence and Technology (INSAIT)

Gui-Song Xia Wuhan University

Wen Li University of Electronic Science and Technology of China

Radu Timofte University of Wurzburg

Bill Triggs Laboratoire Jean Kuntzmann

Jianbing Shen University of Macau

Liangpei Zhang Wuhan University

Fisher Yu ETH Zurich

Jiri Matas Czech Technical University in Prague

Martin Danelljan ETH Zurich

External Links

Personal website of Dengxin Dai

If you think any of the details on this page are incorrect, let us know.

Related Online Degrees & Career Pathways

Pursuing Computer Science in the USA opens many diverse and flexible learning opportunities. For students concerned about past academic performance, several online graduate programs that accept 2.0 gpa are available. These options make it easier for learners to earn a reputable degree and advance their careers even with a lower undergraduate GPA.

Many choose an accelerated computer science degree online to graduate quicker and enter the tech workforce faster. Program length and flexibility can be ideal for working professionals or those looking to change careers rapidly.

If you’re interested in interdisciplinary paths, environmental fields also offer growth. Earning an environmental engineer degree online equips students with skills in both engineering and sustainability. Graduates can explore roles in renewable energy, policy, or design.

Curious about options outside of computer science? Find out what can you get with an environmental science degree and unlock a range of career possibilities—from research to environmental consulting.