# HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception

arXiv: https://arxiv.org/abs/2310.20695 · HTML: https://mlsanity.com/paper/2310.20695/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 74 of its 91 references that are in the map.
- First posted on arXiv 31 Oct 2023.

## Builds on (most cited first, 30 of 74)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://mlsanity.com/paper/1909.12828/) (2019)
- [Masked Feature Prediction for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2112.09133/) (2021)
- [Dense Contrastive Learning for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2011.09157/) (2020)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Humans in 4D: Reconstructing and Tracking Humans with Transformers](https://mlsanity.com/paper/2305.20091/) (2023)

## Built on by (most cited first, 30 of 33)

- [Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis](https://mlsanity.com/paper/2402.18078/) (2024)
- [Follow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation](https://mlsanity.com/paper/2409.01055/) (2024)
- [Masked Image Modeling: A Survey](https://mlsanity.com/paper/2408.06687/) (2024)
- [Hulk: A Universal Knowledge Translator for Human-Centric Tasks](https://mlsanity.com/paper/2312.01697/) (2023)
- [Follow-Your-Preference: Towards Preference-Aligned Image Inpainting](https://mlsanity.com/paper/2509.23082/) (2025)
- [SapiensID: Foundation for Human Recognition](https://mlsanity.com/paper/2504.04708/) (2025)
- [Human-Centric Foundation Models: Perception, Generation and Agentic Modeling](https://mlsanity.com/paper/2502.08556/) (2025)
- [Pedestrian Attribute Recognition: A New Benchmark Dataset and A Large Language Model Augmented Framework](https://mlsanity.com/paper/2408.09720/) (2024)
- [PoseEmbroider: Towards a 3D, Visual, Semantic-aware Human Pose Representation](https://mlsanity.com/paper/2409.06535/) (2024)
- [RGB-Event based Pedestrian Attribute Recognition: A Benchmark Dataset and An Asymmetric RWKV Fusion Framework](https://mlsanity.com/paper/2504.10018/) (2025)
- [Spatio-Temporal Side Tuning Pre-trained Foundation Models for Video-based Pedestrian Attribute Recognition](https://mlsanity.com/paper/2404.17929/) (2024)
- [Instruct-ReID++: Towards Universal Purpose Instruction-Guided Person Re-identification](https://mlsanity.com/paper/2405.17790/) (2024)
- [TextAlign: Preference Alignment for Text Rendering with Hierarchical Rewards](https://mlsanity.com/paper/2605.19320/) (2026)
- [Sapiens2](https://mlsanity.com/paper/2604.21681/) (2026)
- [CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition](https://mlsanity.com/paper/2410.07153/) (2024)
- [OmniTraj: Pre-Training on Heterogeneous Data for Adaptive and Zero-Shot Human Trajectory Prediction](https://mlsanity.com/paper/2507.23657/) (2025)
- [VasoMIM: Vascular Anatomy-Aware Masked Image Modeling for Vessel Segmentation](https://mlsanity.com/paper/2508.10794/) (2025)
- [Asynchronous Denoising Diffusion Models for Aligning Text-to-Image Generation](https://mlsanity.com/paper/2510.04504/) (2025)
- [VILLS -- Video-Image Learning to Learn Semantics for Person Re-Identification](https://mlsanity.com/paper/2311.17074/) (2023)
- [Scale-Aware Pre-Training for Human-Centric Visual Perception: Enabling Lightweight and Generalizable Models](https://mlsanity.com/paper/2503.08201/) (2025)
- [Pedestrian Attribute Recognition via Hierarchical Cross-Modality HyperGraph Learning](https://mlsanity.com/paper/2509.22331/) (2025)
- [RefHCM: A Unified Model for Referring Perceptions in Human-Centric Scenarios](https://mlsanity.com/paper/2412.14643/) (2024)
- [Uncertainty-Aware Pedestrian Attribute Recognition via Evidential Deep Learning](https://mlsanity.com/paper/2604.26873/) (2026)
- [SapiensID 2.0: Aligning Human Recognition Foundation Models with Human Perception](https://mlsanity.com/paper/2608.10497/) (2026)
- [Multi Positive Contrastive Learning with Pose-Consistent Generated Images](https://mlsanity.com/paper/2404.03256/) (2024)
- [Dynamic Pattern Alignment Learning for Pretraining Lightweight Human-Centric Vision Models](https://mlsanity.com/paper/2508.07144/) (2025)
- [Vascular anatomy-aware self-supervised pre-training for X-ray angiogram analysis](https://mlsanity.com/paper/2602.11536/) (2026)
- [UniPAR: A Unified Framework for Pedestrian Attribute Recognition](https://mlsanity.com/paper/2603.05114/) (2026)
- [PFM-VEPAR: Prompting Foundation Models for RGB-Event Camera based Pedestrian Attribute Recognition](https://mlsanity.com/paper/2603.19565/) (2026)
- [What Will Happen Next: Large Models-Driven Deduction for Emergency Instances](https://mlsanity.com/paper/2605.08599/) (2026)

## Abstract (arXiv)

Model pre-training is essential in human-centric perception. In this paper, we first introduce masked image modeling (MIM) as a pre-training approach for this task. Upon revisiting the MIM training strategy, we reveal that human structure priors offer significant potential. Motivated by this insight, we further incorporate an intuitive human structure prior - human parts - into pre-training. Specifically, we employ this prior to guide the mask sampling process. Image patches, corresponding to human part regions, have high priority to be masked out. This encourages the model to concentrate more on body structure information during pre-training, yielding substantial benefits across a range of human-centric perception tasks. To further capture human characteristics, we propose a structure-invariant alignment loss that enforces different masked views, guided by the human part prior, to be closely aligned for the same image. We term the entire method as HAP. HAP simply uses a plain ViT as the encoder yet establishes new state-of-the-art performance on 11 human-centric benchmarks, and on-par result on one dataset. For example, HAP achieves 78.1% mAP on MSMT17 for person re-identification, 86.54% mA on PA-100K for pedestrian attribute recognition, 78.2% AP on MS COCO for 2D pose estimation, and 56.0 PA-MPJPE on 3DPW for 3D pose and shape estimation.