Zhe Li

Affiliations

Rochester Institute of Technology

papers

1,298

total citations

papers (26)

From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels

ICCV 2023arXiv

129

citations

Temporal Action Segmentation From Timestamp Supervision

CVPR 2021arXiv

citations

Robust 3D Self-Portraits in Seconds

CVPR 2020arXiv

citations

Lightweight Multi-Person Total Motion Capture Using Sparse Multi-View Cameras

ICCV 2021arXiv

citations

AvatarCap: Animatable Avatar Conditioned Monocular Human Volumetric Capture

ECCV 2022arXiv

citations

MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning

CVPR 2024arXiv

citations

A₀ : An Affordance-Aware Hierarchical Model for General Robotic Manipulation

ICCV 2025arXiv

citations

POSEFusion: Pose-Guided Selective Fusion for Single-View Human Volumetric Capture

CVPR 2021arXiv

citations

MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos

ECCV 2024arXiv

citations

AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction

CVPR 2025arXiv

citations

Implicit Feature Alignment: Learn To Convert Text Recognizer to Text Spotter

CVPR 2021arXiv

citations

Bridging the User-side Knowledge Gap in Knowledge-aware Recommendations with Large Language Models

AAAI 2025arXiv

citations

General Point Model Pretraining with Autoencoding and Autoregressive

CVPR 2024

citations

TexVocab: Texture Vocabulary-conditioned Human Avatars

CVPR 2024arXiv

citations

Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable

NEURIPS 2025arXiv

citations

Decouple Distortion from Perception: Region Adaptive Diffusion for Extreme-low Bitrate Perception Image Compression

CVPR 2025

citations

DH-Set: Improving Vision-Language Alignment with Diverse and Hybrid Set-Embeddings Learning

CVPR 2025

citations

DanceEditor: Towards Iterative Editable Music-driven Dance Generation with Open-Vocabulary Descriptions

ICCV 2025arXiv

citations

Hierarchy-Aware Pseudo Word Learning with Text Adaptation for Zero-Shot Composed Image Retrieval

ICCV 2025

citations

Energy-based Backdoor Defense without Task-Specific Samples and Model Retraining

ICML 2024

citations

Towards Generic 3D Tracking in RGBD Videos: Benchmark and Baseline

ECCV 2022

citations

Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling

CVPR 2024

citations

Resource-Efficient RGBD Aerial Tracking

CVPR 2023

citations

Zhe Li

Affiliations

papers (26)

Focal and Global Knowledge Distillation for Detectors

Masked Generative Distillation

Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians

From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels

Temporal Action Segmentation From Timestamp Supervision

Robust 3D Self-Portraits in Seconds

Lightweight Multi-Person Total Motion Capture Using Sparse Multi-View Cameras

AvatarCap: Animatable Avatar Conditioned Monocular Human Volumetric Capture

MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning

A₀ : An Affordance-Aware Hierarchical Model for General Robotic Manipulation

POSEFusion: Pose-Guided Selective Fusion for Single-View Human Volumetric Capture

MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos

AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction

Implicit Feature Alignment: Learn To Convert Text Recognizer to Text Spotter

Bridging the User-side Knowledge Gap in Knowledge-aware Recommendations with Large Language Models

General Point Model Pretraining with Autoencoding and Autoregressive

TexVocab: Texture Vocabulary-conditioned Human Avatars

Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable

Decouple Distortion from Perception: Region Adaptive Diffusion for Extreme-low Bitrate Perception Image Compression

DH-Set: Improving Vision-Language Alignment with Diverse and Hybrid Set-Embeddings Learning

DanceEditor: Towards Iterative Editable Music-driven Dance Generation with Open-Vocabulary Descriptions

Hierarchy-Aware Pseudo Word Learning with Text Adaptation for Zero-Shot Composed Image Retrieval

Energy-based Backdoor Defense without Task-Specific Samples and Model Retraining

Towards Generic 3D Tracking in RGBD Videos: Benchmark and Baseline

Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling

Resource-Efficient RGBD Aerial Tracking

papers (26)

Focal and Global Knowledge Distillation for Detectors

Masked Generative Distillation

Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians

From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels

Temporal Action Segmentation From Timestamp Supervision

Robust 3D Self-Portraits in Seconds

Lightweight Multi-Person Total Motion Capture Using Sparse Multi-View Cameras

AvatarCap: Animatable Avatar Conditioned Monocular Human Volumetric Capture

MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning

A₀ : An Affordance-Aware Hierarchical Model for General Robotic Manipulation

POSEFusion: Pose-Guided Selective Fusion for Single-View Human Volumetric Capture

MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos

AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction

Implicit Feature Alignment: Learn To Convert Text Recognizer to Text Spotter

Bridging the User-side Knowledge Gap in Knowledge-aware Recommendations with Large Language Models

General Point Model Pretraining with Autoencoding and Autoregressive

TexVocab: Texture Vocabulary-conditioned Human Avatars

Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable

Decouple Distortion from Perception: Region Adaptive Diffusion for Extreme-low Bitrate Perception Image Compression

DH-Set: Improving Vision-Language Alignment with Diverse and Hybrid Set-Embeddings Learning

DanceEditor: Towards Iterative Editable Music-driven Dance Generation with Open-Vocabulary Descriptions

Hierarchy-Aware Pseudo Word Learning with Text Adaptation for Zero-Shot Composed Image Retrieval

Energy-based Backdoor Defense without Task-Specific Samples and Model Retraining

Towards Generic 3D Tracking in RGBD Videos: Benchmark and Baseline

Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling

Resource-Efficient RGBD Aerial Tracking