Joey Tianyi Zhou

papers

1,026

total citations

papers (25)

Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions

NEURIPS 2021arXiv

citations

Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games

NEURIPS 2020arXiv

citations

Multi-Scale Adaptive Network for Single Image Denoising

NEURIPS 2022arXiv

citations

A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation From a Single RGB Image

CVPR 2023arXiv

citations

Sequential Subset Matching for Dataset Distillation

NEURIPS 2023arXiv

citations

Cross-modal Active Complementary Learning with Self-refining Correspondence

NEURIPS 2023arXiv

citations

Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning

CVPR 2024arXiv

citations

You Only Condense Once: Two Rules for Pruning Condensed Datasets

NEURIPS 2023arXiv

citations

Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer

NEURIPS 2023arXiv

citations

Towards Distribution-Agnostic Generalized Category Discovery

NEURIPS 2023arXiv

citations

Real-Time Multi-Person Eyeblink Detection in the Wild for Untrimmed Video

CVPR 2023arXiv

citations

KPL: Training-Free Medical Knowledge Mining of Vision-Language Models

AAAI 2025arXiv

citations

Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering

ICCV 2023arXiv

citations

Deep Unsupervised Hashing via External Guidance

ICML 2025

citations

C3P: Cross-Domain Pose Prior Propagation for Weakly Supervised 3D Human Pose Estimation

ECCV 2022

citations

Learning with Noisy Triplet Correspondence for Composed Image Retrieval

CVPR 2025

citations

Frequency Guidance Matters in Few-Shot Learning

ICCV 2023

citations

Partially View-aligned Clustering

NEURIPS 2020

citations

ProjAttacker: A Configurable Physical Adversarial Attack for Face Recognition via Projector

CVPR 2025

citations

Joey Tianyi Zhou

papers (25)

Minimizing the Accumulated Trajectory Error To Improve Dataset Distillation

Sharpness-Aware Training for Free

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

3DV: 3D Dynamic Voxel for Action Recognition in Depth Video

Fast Model DeBias with Machine Unlearning

PointBA: Towards Backdoor Attacks in 3D Point Cloud

Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions

Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games

Multi-Scale Adaptive Network for Single Image Denoising

A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation From a Single RGB Image

Sequential Subset Matching for Dataset Distillation

Cross-modal Active Complementary Learning with Self-refining Correspondence

Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning

You Only Condense Once: Two Rules for Pruning Condensed Datasets

Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer

Towards Distribution-Agnostic Generalized Category Discovery

Real-Time Multi-Person Eyeblink Detection in the Wild for Untrimmed Video

KPL: Training-Free Medical Knowledge Mining of Vision-Language Models

Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering

Deep Unsupervised Hashing via External Guidance

C3P: Cross-Domain Pose Prior Propagation for Weakly Supervised 3D Human Pose Estimation

Learning with Noisy Triplet Correspondence for Composed Image Retrieval

Frequency Guidance Matters in Few-Shot Learning

Partially View-aligned Clustering

ProjAttacker: A Configurable Physical Adversarial Attack for Face Recognition via Projector

papers (25)

Minimizing the Accumulated Trajectory Error To Improve Dataset Distillation

Sharpness-Aware Training for Free

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

3DV: 3D Dynamic Voxel for Action Recognition in Depth Video

Fast Model DeBias with Machine Unlearning

PointBA: Towards Backdoor Attacks in 3D Point Cloud

Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions

Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games

Multi-Scale Adaptive Network for Single Image Denoising

A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation From a Single RGB Image

Sequential Subset Matching for Dataset Distillation

Cross-modal Active Complementary Learning with Self-refining Correspondence

Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning

You Only Condense Once: Two Rules for Pruning Condensed Datasets

Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer

Towards Distribution-Agnostic Generalized Category Discovery

Real-Time Multi-Person Eyeblink Detection in the Wild for Untrimmed Video

KPL: Training-Free Medical Knowledge Mining of Vision-Language Models

Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering

Deep Unsupervised Hashing via External Guidance

C3P: Cross-Domain Pose Prior Propagation for Weakly Supervised 3D Human Pose Estimation

Learning with Noisy Triplet Correspondence for Composed Image Retrieval

Frequency Guidance Matters in Few-Shot Learning

Partially View-aligned Clustering

ProjAttacker: A Configurable Physical Adversarial Attack for Face Recognition via Projector