Ailing Zeng

papers

2,973

total citations

papers (28)

SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction

NEURIPS 2022arXiv

668

citations

Human Pose Regression With Residual Log-Likelihood Estimation

ICCV 2021arXiv

275

citations

Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset

NEURIPS 2023arXiv

216

citations

SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach

ECCV 2020arXiv

214

citations

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

ICCV 2023arXiv

129

citations

HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation

ICCV 2023arXiv

125

citations

HumanTOMATO: Text-aligned Whole-body Motion Generation

ICML 2024arXiv

111

citations

Lite DETR: An Interleaved Multi-Scale Encoder for Efficient DETR

CVPR 2023arXiv

105

citations

SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos

ECCV 2022arXiv

citations

DreamWaltz: Make a Scene with Complex 3D Animatable Avatars

NEURIPS 2023arXiv

citations

Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes

CVPR 2023arXiv

citations

DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation

CVPR 2024arXiv

citations

GPAvatar: Generalizable and Precise Head Avatar from Image(s)

ICLR 2024arXiv

citations

AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation

CVPR 2024arXiv

citations

IDOL: Instant Photorealistic 3D Human Creation from a Single Image

CVPR 2025arXiv

citations

Open-World Human-Object Interaction Detection via Multi-modal Prompts

CVPR 2024arXiv

citations

MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls

AAAI 2025arXiv

citations

Neural Interactive Keypoint Detection

ICCV 2023arXiv

citations

SkillMimic: Learning Basketball Interaction Skills from Demonstrations

CVPR 2025arXiv

citations

FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions

CVPR 2024arXiv

citations

DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior

ICCV 2025arXiv

citations

A Comprehensive Benchmark for Neural Human Radiance Fields

NEURIPS 2023

citations

UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation

ICML 2025arXiv

citations

DeciWatch: A Simple Baseline for 10× Efficient 2D and 3D Pose Estimation

ECCV 2022

citations

Ailing Zeng

papers (28)

SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction

Human Pose Regression With Residual Log-Likelihood Estimation

Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset

SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach

SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation

One-Stage 3D Whole-Body Mesh Recovery With Component Aware Transformer

Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation

HuMMan: Multi-modal 4D Human Dataset for Versatile Sensing and Modeling

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

HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation

HumanTOMATO: Text-aligned Whole-body Motion Generation

Lite DETR: An Interleaved Multi-Scale Encoder for Efficient DETR

SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos

DreamWaltz: Make a Scene with Complex 3D Animatable Avatars

Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes

DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation

GPAvatar: Generalizable and Precise Head Avatar from Image(s)

AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation

IDOL: Instant Photorealistic 3D Human Creation from a Single Image

Open-World Human-Object Interaction Detection via Multi-modal Prompts

MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls

Neural Interactive Keypoint Detection

SkillMimic: Learning Basketball Interaction Skills from Demonstrations

FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions

DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior

A Comprehensive Benchmark for Neural Human Radiance Fields

UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation

DeciWatch: A Simple Baseline for 10× Efficient 2D and 3D Pose Estimation

papers (28)

SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction

Human Pose Regression With Residual Log-Likelihood Estimation

Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset

SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach

SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation

One-Stage 3D Whole-Body Mesh Recovery With Component Aware Transformer

Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation

HuMMan: Multi-modal 4D Human Dataset for Versatile Sensing and Modeling

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

HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation

HumanTOMATO: Text-aligned Whole-body Motion Generation

Lite DETR: An Interleaved Multi-Scale Encoder for Efficient DETR

SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos

DreamWaltz: Make a Scene with Complex 3D Animatable Avatars

Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes

DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation

GPAvatar: Generalizable and Precise Head Avatar from Image(s)

AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation

IDOL: Instant Photorealistic 3D Human Creation from a Single Image

Open-World Human-Object Interaction Detection via Multi-modal Prompts

MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls

Neural Interactive Keypoint Detection

SkillMimic: Learning Basketball Interaction Skills from Demonstrations

FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions

DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior

A Comprehensive Benchmark for Neural Human Radiance Fields

UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation

DeciWatch: A Simple Baseline for 10× Efficient 2D and 3D Pose Estimation