Mang Ye

43

Papers

242

Total Citations

Papers (43)

An Empirical Study of CLIP for Text-Based Person Search

FedAS: Bridging Inconsistency in Personalized Federated Learning

Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversity

LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models

EMOE: Modality-Specific Enhanced Dynamic Emotion Experts

Synergy of Sight and Semantics: Visual Intention Understanding with CLIP

Chat-based Person Retrieval via Dialogue-Refined Cross-Modal Alignment

Uncertain Multimodal Intention and Emotion Understanding in the Wild

FedSPA: Generalizable Federated Graph Learning under Homophily Heterogeneity

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

Splitting with Importance-aware Updating for Heterogeneous Federated Learning with Large Language Models

$S^2$FGL: Spatial Spectral Federated Graph Learning

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

S3GCL: Spectral, Swift, Spatial Graph Contrastive Learning

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

Unsupervised Embedding Learning via Invariant and Spreading Instance Feature

Probabilistic Structural Latent Representation for Unsupervised Embedding

Learn From Others and Be Yourself in Heterogeneous Federated Learning

Robust Federated Learning With Noisy and Heterogeneous Clients

Rethinking Federated Learning With Domain Shift: A Prototype View

Unsupervised Visible-Infrared Person Re-Identification via Progressive Graph Matching and Alternate Learning

Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval

Dynamic Label Graph Matching for Unsupervised Video Re-Identification

Cross-Modality Person Re-Identification via Modality Confusion and Center Aggregation

Channel Augmented Joint Learning for Visible-Infrared Recognition

Towards Grand Unified Representation Learning for Unsupervised Visible-Infrared Person Re-Identification

Prototype Reminiscence and Augmented Asymmetric Knowledge Aggregation for Non-Exemplar Class-Incremental Learning

Robust Heterogeneous Federated Learning under Data Corruption

Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification

Improving Self-Supervised Lightweight Model Learning via Hard-Aware Metric Distillation

Towards Modality-Agnostic Person Re-Identification With Descriptive Query

Synthetic Data is an Elegant GIFT for Continual Vision-Language Models

Pose-Star: Anatomy-Aware Editing for Open-World Fashion Images

Unsupervised Visible-Infrared Person Re-identification under Unpaired Settings

TokenMatcher: Diverse Tokens Matching for Unsupervised Visible-Infrared Person Re-Identification

NightReID: A Large-Scale Nighttime Person Re-Identification Benchmark

MDFG: Multi-Dimensional Fine-Grained Modeling for Fatigue Detection

Label-Free Backdoor Attacks in Vertical Federated Learning

Federated Graph Learning under Domain Shift with Generalizable Prototypes

Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-Identification

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

Contextual Augmented Global Contrast for Multimodal Intent Recognition

Dynamic Personalized Federated Learning with Adaptive Differential Privacy