Xi Peng

55

Papers

147

Total Citations

Papers (55)

Decoupled Contrastive Multi-View Clustering with High-Order Random Walks

Multi-granularity Correspondence Learning from Long-term Noisy Videos

Deep Evidential Hashing for Trustworthy Cross-Modal Retrieval

Human-centered Interactive Learning via MLLMs for Text-to-Image Person Re-identification

LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-Identification

Interpretable Failure Detection with Human-Level Concepts

Deep Unsupervised Hashing via External Guidance

Cross-View Graph Consistency Learning for Invariant Graph Representations

Ensemble Pruning for Out-of-distribution Generalization

Test-Time Degradation Adaptation for Open-Set Image Restoration

Image Clustering with External Guidance

Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clients

A Generative Adversarial Approach for Zero-Shot Learning From Noisy Texts

Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation

Semantic Graph Convolutional Networks for 3D Human Pose Regression

Low-Rank Tensor Completion With a New Tensor Nuclear Norm Induced by Invertible Linear Transforms

Knowledge As Priors: Cross-Modal Knowledge Generalization for Datasets Without Superior Knowledge

Learning to Learn Single Domain Generalization

Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization

Uncertainty-Guided Model Generalization to Unseen Domains

Learning Cross-Modal Retrieval With Noisy Labels

Partially View-Aligned Representation Learning With Noise-Robust Contrastive Loss

COMPLETER: Incomplete Multi-View Clustering via Contrastive Prediction

Symmetry and Uncertainty-Aware Object SLAM for 6DoF Object Pose Estimation

Learning With Twin Noisy Labels for Visible-Infrared Person Re-Identification

All-in-One Image Restoration for Unknown Corruption

Deep Fair Clustering via Maximizing and Minimizing Mutual Information: Theory, Algorithm and Metric

Rethinking Image Super Resolution From Long-Tailed Distribution Learning Perspective

RONO: Robust Discriminative Learning With Noisy Labels for 2D-3D Cross-Modal Retrieval

Comprehensive and Delicate: An Efficient Transformer for Image Restoration

Are Data-Driven Explanations Robust Against Out-of-Distribution Data?

PIEFA: Personalized Incremental and Ensemble Face Alignment

Reconstruction-Based Disentanglement for Pose-Invariant Face Recognition

AdaTransform: Adaptive Data Transformation

Reciprocal Multi-Layer Subspace Learning for Multi-View Clustering

Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognition

Graph Matching with Bi-level Noisy Correspondence

Deep Multiview Clustering by Contrasting Cluster Assignments

Are Multimodal Transformers Robust to Missing Modality?

Detecting Open World Objects via Partial Attribute Assignment

Learning with Noisy Triplet Correspondence for Composed Image Retrieval

MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration

Why Slow Feels Fast and Fast Feels Slow: Evaluating and Predicting Speed Misperception

Beyond Accuracy: On the Effects of Fine-Tuning Towards Vision-Language Model’s Prediction Rationality

PrefAce: Face-Centric Pretraining with Self-Structure Aware Distillation

Noisy-Correspondence Learning for Text-to-Image Person Re-identification

Semantic-Guided Multi-Attention Localization for Zero-Shot Learning

Rethinking Kernel Methods for Node Representation Learning on Graphs

Partially View-aligned Clustering

Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness

CLEARER: Multi-Scale Neural Architecture Search for Image Restoration

Learning with Noisy Correspondence for Cross-modal Matching

Multi-Scale Adaptive Network for Single Image Denoising

Cross-modal Active Complementary Learning with Self-refining Correspondence

COMIC: Multi-view Clustering Without Parameter Selection