Wentao Liu

papers

2,007

total citations

papers (27)

Whole-Body Human Pose Estimation in the Wild

ECCV 2020arXiv

308

citations

Human Pose Regression With Residual Log-Likelihood Estimation

ICCV 2021arXiv

275

citations

Not All Tokens Are Equal: Human-Centric Visual Analysis via Token Clustering Transformer

CVPR 2022arXiv

167

citations

Aligning Bag of Regions for Open-Vocabulary Object Detection

CVPR 2023arXiv

156

citations

Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation

ECCV 2020arXiv

139

citations

CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction

ICLR 2024arXiv

110

citations

HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation

ECCV 2020arXiv

citations

When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks

CVPR 2021arXiv

citations

Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images

ICCV 2021arXiv

citations

ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search

CVPR 2021arXiv

citations

3D Interacting Hand Pose Estimation by Hand De-Occlusion and Removal

ECCV 2022arXiv

citations

Pose for Everything: Towards Category-Agnostic Pose Estimation

ECCV 2022arXiv

citations

Harmonizing Visual Representations for Unified Multimodal Understanding and Generation

ICCV 2025arXiv

citations

PoseTrans: A Simple yet Effective Pose Transformation Augmentation for Human Pose Estimation

ECCV 2022arXiv

citations

CLIM: Contrastive Language-Image Mosaic for Region Representation

AAAI 2024arXiv

citations

F-LMM: Grounding Frozen Large Multimodal Models

CVPR 2025arXiv

citations

AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision Tasks

AAAI 2025arXiv

citations

Automatic Animation of Hair Blowing in Still Portrait Photos

ICCV 2023arXiv

citations

You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception

ECCV 2024arXiv

citations

UniFS: Universal Few-shot Instance Perception with Point Representations

ECCV 2024arXiv

citations

NADER: Neural Architecture Design via Multi-Agent Collaboration

CVPR 2025arXiv

citations

ShotVL: Human-Centric Highlight Frame Retrieval via Language Queries

AAAI 2025arXiv

citations

Unsupervised Continual Domain Shift Learning with Multi-Prototype Modeling

CVPR 2025

citations

Leveraging Frame Affinity for sRGB-to-RAW Video De-rendering

CVPR 2024

citations

Wentao Liu

papers (27)

Whole-Body Human Pose Estimation in the Wild

Human Pose Regression With Residual Log-Likelihood Estimation

Not All Tokens Are Equal: Human-Centric Visual Analysis via Token Clustering Transformer

Aligning Bag of Regions for Open-Vocabulary Object Detection

Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation

CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction

3D Human Mesh Regression With Dense Correspondence

SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation

Omni-sourced Webly-supervised Learning for Video Recognition

HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation

When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks

Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images

ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search

3D Interacting Hand Pose Estimation by Hand De-Occlusion and Removal

Pose for Everything: Towards Category-Agnostic Pose Estimation

Harmonizing Visual Representations for Unified Multimodal Understanding and Generation

PoseTrans: A Simple yet Effective Pose Transformation Augmentation for Human Pose Estimation

CLIM: Contrastive Language-Image Mosaic for Region Representation

F-LMM: Grounding Frozen Large Multimodal Models

AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision Tasks

Automatic Animation of Hair Blowing in Still Portrait Photos

You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception

UniFS: Universal Few-shot Instance Perception with Point Representations

NADER: Neural Architecture Design via Multi-Agent Collaboration

ShotVL: Human-Centric Highlight Frame Retrieval via Language Queries

Unsupervised Continual Domain Shift Learning with Multi-Prototype Modeling

Leveraging Frame Affinity for sRGB-to-RAW Video De-rendering

papers (27)

Whole-Body Human Pose Estimation in the Wild

Human Pose Regression With Residual Log-Likelihood Estimation

Not All Tokens Are Equal: Human-Centric Visual Analysis via Token Clustering Transformer

Aligning Bag of Regions for Open-Vocabulary Object Detection

Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation

CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction

3D Human Mesh Regression With Dense Correspondence

SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation

Omni-sourced Webly-supervised Learning for Video Recognition

HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation

When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks

Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images

ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search

3D Interacting Hand Pose Estimation by Hand De-Occlusion and Removal

Pose for Everything: Towards Category-Agnostic Pose Estimation

Harmonizing Visual Representations for Unified Multimodal Understanding and Generation

PoseTrans: A Simple yet Effective Pose Transformation Augmentation for Human Pose Estimation

CLIM: Contrastive Language-Image Mosaic for Region Representation

F-LMM: Grounding Frozen Large Multimodal Models

AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision Tasks

Automatic Animation of Hair Blowing in Still Portrait Photos

You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception

UniFS: Universal Few-shot Instance Perception with Point Representations

NADER: Neural Architecture Design via Multi-Agent Collaboration

ShotVL: Human-Centric Highlight Frame Retrieval via Language Queries

Unsupervised Continual Domain Shift Learning with Multi-Prototype Modeling

Leveraging Frame Affinity for sRGB-to-RAW Video De-rendering