Guanglei Yang

Harbin Institute of Technology — China

Computer Science · Physical Sciences

14h-index1.2kcitations57works1.62yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Domain Adaptation and Few-Shot Learning(19), Advanced Neural Network Applications(15), Multimodal Machine Learning Applications(14), Human Pose and Action Recognition(5), Advanced Vision and Imaging(4)

Publications57 total

MR-GDINO: Memory and Retrieval for Efficient Open-World Continual Object Detection
SSRN Electronic Journal·2026Open Access
Parameter-efficient multimodal adaptation for adverse condition depth estimation
Expert Systems with Applications·2025
Deep learning-based multi-parameter coupling compensation algorithm for clamp-on gas metering systems
Scientific Reports·2025Open Access
Segmenting Objectiveness and Task-awareness Unknown Region for Autonomous Driving
2025Open Access
DualAug: Exploiting additional heavy augmentation with OOD data rejection
Neurocomputing·2025· 1 cited
FILP-3D: Enhancing 3D few-shot class-incremental learning with pre-trained vision-language models
Pattern Recognition·2025· 2 cited
ProGBA: Prompt Guided Bayesian Augmentation for Zero-Shot Domain Adaptation
Lecture notes in computer science·2025· 1 cited
Consept: Continual Semantic Segmentation Via Adapter-Based Vision Transformer
SSRN Electronic Journal·2025· 1 citedOpen Access
MetricDepth: Enhancing Monocular Depth Estimation with Deep Metric Learning
arXiv (Cornell University)·2024Open Access
Geo-ConvGRU: Geographically Masked Convolutional Gated Recurrent Unit for Bird-Eye View Segmentation
arXiv (Cornell University)·2024Open Access
Multi-Modality Driven LoRA for Adverse Condition Depth Estimation
arXiv (Cornell University)·2024Open Access
Unprejudiced Training Auxiliary Tasks Makes Primary Better: A Multi-Task Learning Perspective
arXiv (Cornell University)·2024Open Access
UniM$$^2$$AE: Multi-modal Masked Autoencoders with Unified 3D Representation for 3D Perception in Autonomous Driving
Lecture notes in computer science·2024· 9 cited
Unprejudiced Training Auxiliary Tasks Makes Primary Better: A Multitask Learning Perspective
IEEE Transactions on Neural Networks and Learning Systems·2024
Which decarbonization policy mixes are better for China's power sector? A simulation balancing aggregate abatement effects and economic impacts
Energy Economics·2024· 10 cited
Spatial Distribution Characteristics and Influencing Factors of Intangible Cultural Heritage in the Yunnan, Guangxi, and Guizhou Rocky Desertification Area
Sustainability·2024· 4 citedOpen Access
ConSept: Continual Semantic Segmentation via Adapter-based Vision Transformer
arXiv (Cornell University)·2024Open Access
Filp-3d: Enhancing 3d Few-Shot Class-Incremental Learning with Pre-Trained Vision-Language Models
SSRN Electronic Journal·2024· 1 citedOpen Access
FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models
arXiv (Cornell University)·2023· 1 citedOpen Access
DPDFormer: A Coarse-to-Fine Model for Monocular Depth Estimation
ACM Transactions on Multimedia Computing Communications and Applications·2023· 9 cited
page 1 of 3Next →

Frequent Co-authors

Mingli Ding(19), Elisa Ricci(14), Wangmeng Zuo(14), Hao Tang(8), Nicu Sebe(7), Paolo Rota(7), Xavier Alameda-Pineda(7), Jun Cui(6), Jun Meng(6), Yushi Luan(6), Xinxin Hou(5), Dan Xu(5), Yiwen Guo(5), Ning Jiang(4), Zhun Zhong(4), Xiaoxu Zhou(3), Enrico Fini(3), Liang Xie(3), Zhezheng Liu(3), Wan Xu(3)