Hong Liu

Affiliations

National Institute of Informatics, JapanStanford University

papers

1,323

total citations

papers (26)

MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation

CVPR 2022arXiv

353

citations

Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training

ICLR 2024arXiv

241

citations

ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models

AAAI 2025arXiv

citations

TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose Estimation

AAAI 2025arXiv

citations

FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation

ICCV 2023arXiv

citations

Near-Optimal Resilient Aggregation Rules for Distributed Learning Using 1-Center and 1-Mean Clustering with Outliers

AAAI 2024arXiv

citations

SVTformer: Spatial-View-Temporal Transformer for Multi-View 3D Human Pose Estimation

AAAI 2025

citations

Position: Towards Implicit Prompt For Text-To-Image Models

ICML 2024arXiv

citations

Recognizing Actions from Robotic View for Natural Human-Robot Interaction

ICCV 2025arXiv

citations

PDDM: Pseudo Depth Diffusion Model for RGB-PD Semantic Segmentation Based in Complex Indoor Scenes

AAAI 2025arXiv

citations

API-Net: Robust Generative Classifier via a Single Discriminator

ECCV 2020

citations

Learning to Adapt to Evolving Domains

NEURIPS 2020

citations

An Information Theoretic Approach for Attention-Driven Face Forgery Detection

ECCV 2022

citations

LiD-FL: Towards List-Decodable Federated Learning

AAAI 2025arXiv

citations

Learning Concordant Attention via Target-aware Alignment for Visible-Infrared Person Re-identification

ICCV 2023

citations

Improving Adversarial Robustness via Information Bottleneck Distillation

NEURIPS 2023

citations

UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling

ICCV 2025arXiv

citations

Hong Liu

Affiliations

papers (26)

MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation

Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training

Cycle Self-Training for Domain Adaptation

Spatial Pyramid Based Graph Reasoning for Semantic Segmentation

STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection

Projection & Probability-Driven Black-Box Attack

Black-Box Dissector: Towards Erasing-Based Hard-Label Model Stealing Attack

Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video

Anti-Bandit Neural Architecture Search for Model Defense

Audio Generation with Multiple Conditional Diffusion Model

Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation

ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models

TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose Estimation

FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation

Near-Optimal Resilient Aggregation Rules for Distributed Learning Using 1-Center and 1-Mean Clustering with Outliers

SVTformer: Spatial-View-Temporal Transformer for Multi-View 3D Human Pose Estimation

Position: Towards Implicit Prompt For Text-To-Image Models

Recognizing Actions from Robotic View for Natural Human-Robot Interaction

PDDM: Pseudo Depth Diffusion Model for RGB-PD Semantic Segmentation Based in Complex Indoor Scenes

API-Net: Robust Generative Classifier via a Single Discriminator

Learning to Adapt to Evolving Domains

An Information Theoretic Approach for Attention-Driven Face Forgery Detection

LiD-FL: Towards List-Decodable Federated Learning

Learning Concordant Attention via Target-aware Alignment for Visible-Infrared Person Re-identification

Improving Adversarial Robustness via Information Bottleneck Distillation

UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling

papers (26)

MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation

Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training

Cycle Self-Training for Domain Adaptation

Spatial Pyramid Based Graph Reasoning for Semantic Segmentation

STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection

Projection & Probability-Driven Black-Box Attack

Black-Box Dissector: Towards Erasing-Based Hard-Label Model Stealing Attack

Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video

Anti-Bandit Neural Architecture Search for Model Defense

Audio Generation with Multiple Conditional Diffusion Model

Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation

ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models

TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose Estimation

FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation

Near-Optimal Resilient Aggregation Rules for Distributed Learning Using 1-Center and 1-Mean Clustering with Outliers

SVTformer: Spatial-View-Temporal Transformer for Multi-View 3D Human Pose Estimation

Position: Towards Implicit Prompt For Text-To-Image Models

Recognizing Actions from Robotic View for Natural Human-Robot Interaction

PDDM: Pseudo Depth Diffusion Model for RGB-PD Semantic Segmentation Based in Complex Indoor Scenes

API-Net: Robust Generative Classifier via a Single Discriminator

Learning to Adapt to Evolving Domains

An Information Theoretic Approach for Attention-Driven Face Forgery Detection

LiD-FL: Towards List-Decodable Federated Learning

Learning Concordant Attention via Target-aware Alignment for Visible-Infrared Person Re-identification

Improving Adversarial Robustness via Information Bottleneck Distillation

UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling