Zhe Li

33

Papers

287

Total Citations

Papers (33)

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

Improved Dropout for Shallow and Deep Learning

NeurIPS 2016arXiv

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

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

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

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

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

Robust 3D Self-Portraits in Seconds

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

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

Temporal Action Segmentation From Timestamp Supervision

Focal and Global Knowledge Distillation for Detectors

Resource-Efficient RGBD Aerial Tracking

Prior-Aware Neural Network for Partially-Supervised Multi-Organ Segmentation

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

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

AvatarCap: Animatable Avatar Conditioned Monocular Human Volumetric Capture

Masked Generative Distillation

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

EIGEN: Ecologically-Inspired GENetic Approach for Neural Network Structure Searching From Scratch

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

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

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

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

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

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

Thoracic Disease Identification and Localization With Limited Supervision

Adaptive Negative Curvature Descent with Applications in Non-convex Optimization

Learning from brains how to regularize machines

Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank