已发表成果:
WOK 论文 50 篇;中文核心 1 篇;
CamoTeacher: Dual-Rotation Consistency Learning for Semi-Supervised Camouflaged Object Detection
Edge reconstruction and feature enhancement-driven architecture for blind super-resolution in medical imaging systems
HRSAM: Efficiently Segment Anything in High-Resolution Images
Local Manifold Learning for No-Reference Image Quality Assessment
Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text
FocSAM: Delving Deeply into Focused Objects in Segmenting Anything
GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplane
Dual3D: Efficient and Consistent Text-to-3D Generation with Dual-mode Multi-view Latent Diffusion
Cantor: Inspiring Multimodal Chain-of-Thought of MLLM
Multi-Modal Prompt Learning on Blind Image Quality Assessment
NeRF-DetS: Enhancing Multi-View 3D Object Detection with Sampling-adaptive Network of Continuous NeRF-based Representation
DMAD: Dual Memory Bank for Real-World Anomaly Detection
EBFT: Effective and Block-Wise Fine-Tuning for Sparse LLMs
Feature Denoising Diffusion Model for Blind Image Quality Assessment
Few-Shot Object Detection via Classify-Free RPN
Global Selection and Local Attention Network for Referring Image Segmentation
ISTR: Mask-Embedding-Based Instance Segmentation Transformer
GreedyAgent: Crafting Efficient Agents for Meta-learning from Learning Curves via Greedy Algorithm Selection
Backdoor Attack against Face Sketch Synthesis
Attack Can Benefit: An Adversarial Approach to Recognizing Facial Expressions under Noisy Annotations
InterFormer: Real-time Interactive Image Segmentation
Geometric-aware Pretraining for Vision-centric 3D Object Detection
You Only Segment Once: Towards Real-Time Panoptic Segmentation
DistilPose: Tokenized Pose Regression with Heatmap Distillation
CAM R-CNN: End-to-End Object Detection with Class Activation Maps
Automatic Network Pruning via Hilbert-Schmidt Independence Criterion Lasso under Information Bottleneck Principle
Pseudo-label Alignment for Semi-supervised Instance Segmentation
Bilateral Knowledge Interaction Network for Referring Image Segmentation
Open-World Few-Shot Object Detection
DistilPose: Tokenized Pose Regression with Heatmap Distillation
Self-Paced Partial Domain-Aware Learning for Face Anti-Spoofing
CANDY: Category-Kernelized Dynamic Convolution for Instance Segmentation
Improving Occluded Human Pose Estimation Via Linked Joints
Category-aware Allocation Transformer for Weakly Supervised Object Localization
InterFormer Real-time Interactive Image Segmentation
Privacy-Preserving Face Recognition with Learnable Privacy Budgets in Frequency Domain
Fast Monocular Depth Estimation via Side Prediction Aggregation with Continuous Spatial Refinement
Joint segmentation and detection of COVID-19 via a sequential region generation network
Image-to-image Translation via Hierarchical Style Disentanglement
Architecture Disentanglement for Deep Neural Networks
Multi-modal multi-layer fusion network with average binary center loss for face anti-spoofing
Towards visual feature translation
Information competing process for learning diversified representations
Generative Adversarial Learning Towards Fast Weakly Supervised Detection
Dense auto-encoder hashing for robust cross-modality retrieval
Deep-based fisher vector for mobile visual search
AAM Based Face Sketch Synthesis
Face Sketch Synthesis by Multidomain Adversarial Learning
Robust face sketch synthesis via generative adversarial fusion of priors and parametric sigmoid
Face sketch aging via aging oriented principal component analysis
基于注意力机制的实例分割算法
导航定位与授时,2095-8110,2021-11-15.