Area of research
Nuclear and High Energy Physics · Artificial Intelligence
Research interest
Research interests include Nuclear physics research studies, Domain Adaptation and Few-Shot Learning, Nuclear Physics and Applications, and Nuclear reactor physics and engineering.
Intra-class progressive and adaptive self-distillation
Hypnos: A domain-specific large language model for anesthesiology
Reciprocal Teacher-Student Learning via Forward and Feedback Knowledge Distillation
SkipNode: On Alleviating Performance Degradation for Deep Graph Convolutional Networks
PointWavelet: Learning in Spectral Domain for 3-D Point Cloud Analysis
Multi-target Knowledge Distillation via Student Self-reflection
Learnable Skeleton-Aware 3D Point Cloud Sampling
Domain-Specific Risk Minimization for Domain Generalization
Bounding Box Vectorization for Oriented Object Detection With Tanimoto Coefficient Regression
Hierarchical Locality-Aware Deep Dictionary Learning for Classification
Intra- and Inter-Class Induced Discriminative Deep Dictionary Learning for Visual Recognition
Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers
Contrastive Boundary Learning for Point Cloud Segmentation
Multilevel Attention-Based Sample Correlations for Knowledge Distillation
BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning
Hierarchical Multi-Attention Transfer for Knowledge Distillation
Collaborative Knowledge Distillation via Multiknowledge Transfer
Resistance Training Using Prior Bias: Toward Unbiased Scene Graph Generation
MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis
Channel-Correlation-Based Selective Knowledge Distillation
Knowledge Distillation: A Survey
Affordance Transfer Learning for Human-Object Interaction Detection
Detecting Human-Object Interaction via Fabricated Compositional Learning
TGRNet: A Table Graph Reconstruction Network for Table Structure Recognition
Multi-Stream Interaction Networks for Human Action Recognition
Heatmap Regression via Randomized Rounding
Model and Transfer Spatial-Temporal Knowledge for Fine-Grained Radio Map Reconstruction
Skeleton edge motion networks for human action recognition
Deep Metric Learning With Tuplet Margin Loss
Correcting the Triplet Selection Bias for Triplet Loss