Weifeng Ou

Dongguan University of Technology — China

Computer Science · Physical Sciences

10h-index309citations24works1.52yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Biometric Identification and Security(7), Face recognition and analysis(6), Advanced Image and Video Retrieval Techniques(4), Generative Adversarial Networks and Image Synthesis(4), Domain Adaptation and Few-Shot Learning(4)

Publications24 total

LLaVA-SpaceSGG: Visual Instruct Tuning for Open-Vocabulary Scene Graph Generation with Enhanced Spatial Relations
2025· 2 cited
Motion Transfer-Driven intra-class data augmentation for Finger Vein Recognition
arXiv (Cornell University)·2024Open Access
LLaVA-SpaceSGG: Visual Instruct Tuning for Open-vocabulary Scene Graph Generation with Enhanced Spatial Relations
arXiv (Cornell University)·2024Open Access
Joint Learning of Identity and Vein Features for Enhanced Representations in Vascular Biometrics
2024· 2 cited
Motion Transfer-Driven Intra-Class Data Augmentation for Finger Vein Recognition
2024· 2 cited
GSCL: Generative Self-Supervised Contrastive Learning for Vein-Based Biometric Verification
IEEE Transactions on Biometrics Behavior and Identity Science·2024· 3 cited
CSRNet: Cascaded Selective Resolution Network for real-time semantic segmentation
Expert Systems with Applications·2022· 32 cited
Contrastive Spatio-Temporal Pretext Learning for Self-Supervised Video Representation
Proceedings of the AAAI Conference on Artificial Intelligence·2022· 12 citedOpen Access
ChildPredictor: A Child Face Prediction Framework With Disentangled Learning
IEEE Transactions on Multimedia·2022· 9 citedOpen Access
VCGAN: Video Colorization With Hybrid Generative Adversarial Network
IEEE Transactions on Multimedia·2022· 38 citedOpen Access
GAN-Based Inter-Class Sample Generation for Contrastive Learning of Vein Image Representations
IEEE Transactions on Biometrics Behavior and Identity Science·2022· 14 cited
Pixel Voting Decoder: A novel decoder that regresses pixel relationships for segmentation
Expert Systems with Applications·2021· 2 cited
Contrastive Spatio-Temporal Pretext Learning for Self-supervised Video Representation
arXiv (Cornell University)·2021Open Access
Deep triplet residual quantization
Expert Systems with Applications·2021· 7 cited
CSRNet: Cascaded Selective Resolution Network for Real-time Semantic Segmentation
arXiv (Cornell University)·2021Open Access
Fusion loss and inter-class data augmentation for deep finger vein feature learning
Expert Systems with Applications·2021· 38 cited
Angular Deep Supervised Vector Quantization for Image Retrieval
IEEE Transactions on Neural Networks and Learning Systems·2020· 10 cited
Data-level information enhancement: Motion-patch-based Siamese Convolutional Neural Networks for human activity recognition in videos
Expert Systems with Applications·2020· 21 cited
LinCos-Softmax: Learning Angle-Discriminative Face Representations With Linearity-Enhanced Cosine Logits
IEEE Access·2020· 7 citedOpen Access
Saliency Map-Aided Generative Adversarial Network for RAW to RGB Mapping
2019· 9 cited
page 1 of 2Next →

Frequent Co-authors

Lai-Man Po(21), Yuzhi Zhao(13), Wing-Yin Yu(10), Yujia Zhang(9), Chang Zhou(9), Pengfei Xian(7), Jingjing Xiong(6), Yasar Abbas Ur Rehman(6), Mengyang Liu(5), Xiu‐Feng Huang(4), Zongbang Liao(2), Xiang Shi(2), Zijie Zou(2), Xuyuan Xu(2), Yexin Wang(2), Mingjie Xu(2), Mengyang Wu(2), Jason Chun Lok Li(2), Andrey Ignatov(1), Radu Timofte(1)