Xing Wei

papers

647

total citations

papers (20)

Driving by the Rules: A Benchmark for Integrating Traffic Sign Regulations into Vectorized HD Map

CVPR 2025arXiv

citations

FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training

CVPR 2025arXiv

citations

Dynamic Integration of Task-Specific Adapters for Class Incremental Learning

CVPR 2025arXiv

citations

Autoregressive Sequential Pretraining for Visual Tracking

CVPR 2025

citations

Evolving Parameterized Prompt Memory for Continual Learning

AAAI 2024

citations

DYSON: Dynamic Feature Space Self-Organization for Online Task-Free Class Incremental Learning

CVPR 2024

citations

Topology-Preserving Class-Incremental Learning

ECCV 2020

citations

DKT: Diverse Knowledge Transfer Transformer for Class Incremental Learning

CVPR 2023

citations

Autoregressive Visual Tracking

CVPR 2023

citations

Preference-driven Knowledge Distillation for Few-shot Node Classification

NEURIPS 2025arXiv

citations

Learnable Fractional Reaction-Diffusion Dynamics for Under-Display ToF Imaging and Beyond

ICCV 2025arXiv

citations

Person-in-WiFi 3D: End-to-End Multi-Person 3D Pose Estimation with Wi-Fi

CVPR 2024

citations

Towards a Universal Model for Cross-Dataset Crowd Counting

ICCV 2021

citations

End-to-End Multi-Person Pose Estimation With Transformers

CVPR 2022

citations

Learning Symmetry-Aware Geometry Correspondences for 6D Object Pose Estimation

ICCV 2023

citations

Sparse Parameterization for Epitomic Dataset Distillation

NEURIPS 2023

citations

Xing Wei

papers (20)

Few-Shot Class-Incremental Learning

ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe

Knowledge Restore and Transfer for Multi-Label Class-Incremental Learning

SeqGrowGraph: Learning Lane Topology as a Chain of Graph Expansions

Driving by the Rules: A Benchmark for Integrating Traffic Sign Regulations into Vectorized HD Map

FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training

Dynamic Integration of Task-Specific Adapters for Class Incremental Learning

Autoregressive Sequential Pretraining for Visual Tracking

Evolving Parameterized Prompt Memory for Continual Learning

DYSON: Dynamic Feature Space Self-Organization for Online Task-Free Class Incremental Learning

Topology-Preserving Class-Incremental Learning

DKT: Diverse Knowledge Transfer Transformer for Class Incremental Learning

Autoregressive Visual Tracking

Preference-driven Knowledge Distillation for Few-shot Node Classification

Learnable Fractional Reaction-Diffusion Dynamics for Under-Display ToF Imaging and Beyond

Person-in-WiFi 3D: End-to-End Multi-Person 3D Pose Estimation with Wi-Fi

Towards a Universal Model for Cross-Dataset Crowd Counting

End-to-End Multi-Person Pose Estimation With Transformers

Learning Symmetry-Aware Geometry Correspondences for 6D Object Pose Estimation

Sparse Parameterization for Epitomic Dataset Distillation

papers (20)

Few-Shot Class-Incremental Learning

ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe

Knowledge Restore and Transfer for Multi-Label Class-Incremental Learning

SeqGrowGraph: Learning Lane Topology as a Chain of Graph Expansions

Driving by the Rules: A Benchmark for Integrating Traffic Sign Regulations into Vectorized HD Map

FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training

Dynamic Integration of Task-Specific Adapters for Class Incremental Learning

Autoregressive Sequential Pretraining for Visual Tracking

Evolving Parameterized Prompt Memory for Continual Learning

DYSON: Dynamic Feature Space Self-Organization for Online Task-Free Class Incremental Learning

Topology-Preserving Class-Incremental Learning

DKT: Diverse Knowledge Transfer Transformer for Class Incremental Learning

Autoregressive Visual Tracking

Preference-driven Knowledge Distillation for Few-shot Node Classification

Learnable Fractional Reaction-Diffusion Dynamics for Under-Display ToF Imaging and Beyond

Person-in-WiFi 3D: End-to-End Multi-Person 3D Pose Estimation with Wi-Fi

Towards a Universal Model for Cross-Dataset Crowd Counting

End-to-End Multi-Person Pose Estimation With Transformers

Learning Symmetry-Aware Geometry Correspondences for 6D Object Pose Estimation

Sparse Parameterization for Epitomic Dataset Distillation