Bo Du

41

Papers

46

Total Citations

Papers (41)

Online GNN Evaluation Under Test-time Graph Distribution Shifts

Improving Bird's Eye View Semantic Segmentation by Task Decomposition

Joint Learning Neuronal Skeleton and Brain Circuit Topology with Permutation Invariant Encoders for Neuron Classification

WaterDiffusion: Learning a Prior-involved Unrolling Diffusion for Joint Underwater Saliency Detection and Visual Restoration

Cheb-GR: Rethinking K-nearest Neighbor Search in Re-ranking for Person Re-identification

AiDE-Q: Synthetic Labeled Datasets Can Enhance Learning Models for Quantum Property Estimation

Mesoscopic Insights: Orchestrating Multi-Scale & Hybrid Architecture for Image Manipulation Localization

Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning

Cycle Self-Refinement for Multi-Source Domain Adaptation

Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names

All in One Framework for Multimodal Re-identification in the Wild

UniGS: Unified Representation for Image Generation and Segmentation

Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning

Sparse is Enough in Fine-tuning Pre-trained Large Language Models

MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependence

Imitation Learning from Purified Demonstrations

Self-Driven Entropy Aggregation for Byzantine-Robust Heterogeneous Federated Learning

Fast Spatio-Temporal Residual Network for Video Super-Resolution

Recurrent Feature Reasoning for Image Inpainting

Learning Affinity From Attention: End-to-End Weakly-Supervised Semantic Segmentation With Transformers

Learn From Others and Be Yourself in Heterogeneous Federated Learning

Multi-Marginal Contrastive Learning for Multi-Label Subcellular Protein Localization

Rethinking Federated Learning With Domain Shift: A Prototype View

Robust Generalization Against Photon-Limited Corruptions via Worst-Case Sharpness Minimization

Token Contrast for Weakly-Supervised Semantic Segmentation

Progressive Reconstruction of Visual Structure for Image Inpainting

Federated Learning for Non-IID Data via Unified Feature Learning and Optimization Objective Alignment

Channel Augmented Joint Learning for Visible-Infrared Recognition

Not All Operations Contribute Equally: Hierarchical Operation-Adaptive Predictor for Neural Architecture Search

Generating Dynamic Kernels via Transformers for Lane Detection

DeepSolo: Let Transformer Decoder With Explicit Points Solo for Text Spotting

CogNav: Cognitive Process Modeling for Object Goal Navigation with LLMs

Unsupervised Visible-Infrared Person Re-identification under Unpaired Settings

Conditional Visual Autoregressive Modeling for Pathological Image Restoration

Rethink Sparse Signals for Pose-guided Text-to-image Generation

Vox-UDA: Voxel-wise Unsupervised Domain Adaptation for Cryo-Electron Subtomogram Segmentation with Denoised Pseudo-Labeling

VF-PS: How to Select Important Participants in Vertical Federated Learning, Efficiently and Securely?

SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model

AIMS: All-Inclusive Multi-Level Segmentation for Anything

Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm

Revisit Weakly-Supervised Audio-Visual Video Parsing from the Language Perspective