Liujuan Cao

36

Papers

64

Total Citations

Papers (36)

Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-identification

Weakly Supervised Open-Vocabulary Object Detection

CamoTeacher: Dual-Rotation Consistency Learning for Semi-Supervised Camouflaged Object Detection

WildSeg3D: Segment Any 3D Objects in the Wild from 2D Images

UniPTS: A Unified Framework for Proficient Post-Training Sparsity

UCOD-DPL: Unsupervised Camouflaged Object Detection via Dynamic Pseudo-label Learning

Few-Shot Image Quality Assessment via Adaptation of Vision-Language Models

FocSAM: Delving Deeply into Focused Objects in Segmenting Anything

DS-VLM: Diffusion Supervision Vision Language Model

Cyclic Guidance for Weakly Supervised Joint Detection and Segmentation

Towards Optimal Structured CNN Pruning via Generative Adversarial Learning

Multi-Task Collaborative Network for Joint Referring Expression Comprehension and Segmentation

Toward Joint Thing-and-Stuff Mining for Weakly Supervised Panoptic Segmentation

SDD-FIQA: Unsupervised Face Image Quality Assessment With Similarity Distribution Distance

Image-to-Image Translation via Hierarchical Style Disentanglement

Active Teacher for Semi-Supervised Object Detection

You Only Segment Once: Towards Real-Time Panoptic Segmentation

DistilPose: Tokenized Pose Regression With Heatmap Distillation

Architecture Disentanglement for Deep Neural Networks

EC-DARTS: Inducing Equalized and Consistent Optimization Into DARTS

Parallel Detection-and-Segmentation Learning for Weakly Supervised Instance Segmentation

Pseudo-label Alignment for Semi-supervised Instance Segmentation

Category-aware Allocation Transformer for Weakly Supervised Object Localization

InterFormer: Real-time Interactive Image Segmentation

API-Net: Robust Generative Classifier via a Single Discriminator

Knowledge Condensation Distillation

Privacy-Preserving Face Recognition with Learnable Privacy Budgets in Frequency Domain

ARM: Any-Time Super-Resolution Method

Evolving High-Quality Rendering and Reconstruction in a Unified Framework with Contribution-Adaptive Regularization

SeqTR: A Simple Yet Universal Network for Visual Grounding

Distilling Spatially-Heterogeneous Distortion Perception for Blind Image Quality Assessment

Inter2Former: Dynamic Hybrid Attention for Efficient High-Precision Interactive Segmentation

ESCNet:Edge-Semantic Collaborative Network for Camouflaged Object Detection

TextRefiner: Internal Visual Feature as Efficient Refiner for Vision-Language Models Prompt Tuning

Occluded Person Re-identification via Saliency-Guided Patch Transfer

RepAn: Enhanced Annealing through Re-parameterization