Haoyu Ma

Affiliations

Meta Platforms, IncUniversity of California, Irvine

papers

279

total citations

papers (10)

Coarse-To-Fine Domain Adaptive Semantic Segmentation With Photometric Alignment and Category-Center Regularization

CVPR 2021arXiv

citations

PPT: Token-Pruned Pose Transformer for Monocular and Multi-View Human Pose Estimation

ECCV 2022arXiv

citations

Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning

NEURIPS 2023arXiv

citations

HarmonyDream: Task Harmonization Inside World Models

ICML 2024arXiv

citations

Identity-Aware Hand Mesh Estimation and Personalization from RGB Images

ECCV 2022arXiv

citations

Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts

CVPR 2025arXiv

citations

EI-CLIP: Entity-Aware Interventional Contrastive Learning for E-Commerce Cross-Modal Retrieval

CVPR 2022

citations

Haoyu Ma

Affiliations

papers (10)

Coarse-To-Fine Domain Adaptive Semantic Segmentation With Photometric Alignment and Category-Center Regularization

PPT: Token-Pruned Pose Transformer for Monocular and Multi-View Human Pose Estimation

Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning

HarmonyDream: Task Harmonization Inside World Models

Identity-Aware Hand Mesh Estimation and Personalization from RGB Images

Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts

Instance Tracking in 3D Scenes from Egocentric Videos

HOIGPT: Learning Long-Sequence Hand-Object Interaction with Language Models

MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers

EI-CLIP: Entity-Aware Interventional Contrastive Learning for E-Commerce Cross-Modal Retrieval

papers (10)

Coarse-To-Fine Domain Adaptive Semantic Segmentation With Photometric Alignment and Category-Center Regularization

PPT: Token-Pruned Pose Transformer for Monocular and Multi-View Human Pose Estimation

Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning

HarmonyDream: Task Harmonization Inside World Models

Identity-Aware Hand Mesh Estimation and Personalization from RGB Images

Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts

Instance Tracking in 3D Scenes from Egocentric Videos

HOIGPT: Learning Long-Sequence Hand-Object Interaction with Language Models

MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers

EI-CLIP: Entity-Aware Interventional Contrastive Learning for E-Commerce Cross-Modal Retrieval