Area of research
Computer Vision and Pattern Recognition · Media Technology
Research interest
Research interests include Computer science, Artificial intelligence, Pattern recognition (psychology), Signature (topology), Scripting language, and Identification (biology).
DPA-MVSNet: Dynamic Context Perception Multi-view Stereo with transformers and data augmentation
A comprehensive review of non-Latin natural scene text detection and recognition techniques
Multi-scale CNN-CrossViT network for offline handwritten signature recognition and verification
Script identification in multilingual environment: a survey in recent years
Toward based on concentrated multi-scale linear attention real-time UAV tracking using joint natural language specification
Mamba meets tracker: exploiting token aggregation and diffusion for robust unmanned aerial vehicles tracking
HyperSegmenter: Reappraising the potential of large kernel CNN architecture in efficient semantic segmentation
A simple interpolation-based data augmentation method for implicit sentiment identification
MAFF-CrossNet: Multi-scale Attentional Feature Fusion and Cross-Writer Network for Offline Signature Verification
Multi-scale Convolution Combined with DTW for Online Signature Verification
Dynamic token sampling for efficient unmanned aerial vehicles transformer tracking
Multi-scale dense feature fusion method for offline handwritten signature recognition
A dynamic graph structural framework for implicit sentiment identification based on complementary semantic and structural information
Sig-RFPNet: multi-branch network and multi-classifier method for offline signature recognition
Script Identification in the Wild with FFT-Multi-grained Mix Attention Transformer
Oracle Bone Inscriptions Image Retrieval Based on Metric Learning
A New Bottom-Up Path Augmentation Attention Network for Script Identification in Scene Images
Multi-Task Interaction Network Based on a Cross-Attention Fusion Mechanism for Offline Signature Verification
DDCTrack： Dynamic Token Sampling for Efficient UAV Transformer Tracking
Oracle Bone Inscription Image Retrieval Based on Improved ResNet Network
Oracle Character Recognition Based on Attention Enhancement and Multi-level Feature Fusion
Improving Retrieval-Based Dialogue Systems: Fine-Grained Post-training Prompt Adaptation and Pairwise Optimization Fine-Tuning Strategy
TextViTCNN: Enhancing Natural Scene Text Recognition with Hybrid Transformer and Convolutional Networks
Oracle Bone Script Recognition Based on Multi-scale Feature Fusion and Knowledge Distillation
Scene Uyghur Text Detection Based on Adaptive Feature Fusion
Multimodal sentiment system and method based on CRNN-SVM
FC-ResNet: A Multilingual Handwritten Signature Verification Model Using an Improved ResNet with CBAM
Advances in Offline Handwritten Signature Recognition Research: A Review
SUCOLA: Self-adaptive structure refinement unsupervised contrastive learning framework for food safety risk early warning
FAS-Res2net: An Improved Res2net-Based Script Identification Method for Natural Scenes