已发表成果:
WOK 论文 183 篇;中文核心 13 篇;其它论文 1 篇;专利发明 1 个;
Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentation
Positive-Negative Receptive Field Reasoning for Omni-Supervised 3D Segmentation
Farewell to Cyclegan: Single Gan with Decoupled Constraint for Unpaired Image Dehazing
Cross-modal Unsupervised Domain Adaptation for 3D Semantic Segmentation via Bidirectional Fusion-then-Distillation
Unveiling the Power of CLIP in Unsupervised Visible-Infrared Person Re-Identification
Hardware-friendly Scalable Image Super Resolution with Progressively Structured Sparsity
Bias to Balance: New-Knowledge-Preferred Few-Shot Class-Incremental Learning Via Transition Calibration
Weakly Supervised 3D Segmentation via Receptive-Driven Pseudo Label Consistency and Structural Consistency
Cascaded Degradation-Aware Blind Super-Resolution
Dynamic Image Super-Resolution Via Progressive Contrastive Self-Distillation
Forget less, count better: a domain-incremental self-distillation learning benchmark for lifelong crowd counting
Topology-guided Adversarial Deep Mutual Learning for Knowledge Distillation
Memory-friendly Scalable Super-resolution via Rewinding Lottery Ticket Hypothesis
Perturbed Progressive Learning for Semisupervised Defect Segmentation
Sample-Aware Knowledge Distillation for Long-Tailed Learning
Rethinking Gradient Projection Continual Learning: Stability / Plasticity Feature Space Decoupling
Multi-Centroid Task Descriptor for Dynamic Class Incremental Inference
VS-Boost: Boosting Visual-Semantic Association for Generalized Zero-Shot Learning
Joint Feature Aggregation for Stereo Image Super-resolution
Efficient Converted Spiking Neural Network for 3D and 2D Classification
BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation
Dual Pseudo-Labels Interactive Self-Training for Semi-Supervised Visible-Infrared Person Re-Identification
Instance and Category Supervision are Alternate Learners for Continual Learning
Learning Multi-Talented Image Restoration with Knowledge Factorization
Visible Embraces Infrared: Cross-Modality Person Re-Identification with Single-Modality Supervision
Knowledge Distillation on Multiple Experts for Long-Tailed Recognition
Tensor Multi-Task Learning for Multi-View Representation of 3D Shape
Learning Re-sampling Methods with Parameter Attribution for Image Super-resolution
忘得少,数得好:一种域增量式自蒸馏终身人群计数基准(英文)
Frontiers of Information Technology & Electronic Engineering,2095-9184,2023-02-03.