Wenjie Pei

papers

646

total citations

papers (20)

Self-Support Few-Shot Semantic Segmentation

ECCV 2022arXiv

199

citations

Audio2Gestures: Generating Diverse Gestures From Speech Audio With Conditional Variational Autoencoders

ICCV 2021arXiv

136

citations

Saliency-Associated Object Tracking

ICCV 2021arXiv

citations

Multi-faceted Distillation of Base-Novel Commonality for Few-Shot Object Detection

ECCV 2022arXiv

citations

Global Tracking via Ensemble of Local Trackers

CVPR 2022arXiv

citations

Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation

ECCV 2020arXiv

citations

Domain-Rectifying Adapter for Cross-Domain Few-Shot Segmentation

CVPR 2024arXiv

citations

Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroid

NEURIPS 2022arXiv

citations

Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representations

ECCV 2022arXiv

citations

Robust 3D Tracking with Quality-Aware Shape Completion

AAAI 2024arXiv

citations

Hierarchical Contrastive Learning for Pattern-Generalizable Image Corruption Detection

ICCV 2023arXiv

citations

WeCromCL: Weakly Supervised Cross-Modality Contrastive Learning for Transcription-only Supervised Text Spotting

ECCV 2024arXiv

citations

Recognition-Synergistic Scene Text Editing

CVPR 2025arXiv

citations

MotionShot: Adaptive Motion Transfer across Arbitrary Objects for Text-to-Video Generation

ICCV 2025arXiv

citations

D2ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition

ICCV 2025

citations

UniVoxel: Fast Inverse Rendering by Unified Voxelization of Scene Representation

ECCV 2024arXiv

citations

Learning Compatible Multi-Prize Subnetworks for Asymmetric Retrieval

CVPR 2025arXiv

citations

CPGAN: Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis

ECCV 2020

citations

Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation

ICCV 2025arXiv

citations

SA²VP: Spatially Aligned-and-Adapted Visual Prompt

AAAI 2024

citations