mlsanityData to 7 Oct 2026

UniHCP: A Unified Model for Human-Centric Perceptions

arXiv 2303.02936 ↗First posted 6 Mar 2023cs.CVcited by 59

Not on the map. Why?

Abstract (arXiv)

Human-centric perceptions (e.g., pose estimation, human parsing, pedestrian detection, person re-identification, etc.) play a key role in industrial applications of visual models. While specific human-centric tasks have their own relevant semantic aspect to focus on, they also share the same underlying semantic structure of the human body. However, few works have attempted to exploit such homogeneity and design a general-propose model for human-centric tasks. In this work, we revisit a broad range of human-centric tasks and unify them in a minimalist manner. We propose UniHCP, a Unified Model for Human-Centric Perceptions, which unifies a wide range of human-centric tasks in a simplified end-to-end manner with the plain vision transformer architecture. With large-scale joint training on 33 human-centric datasets, UniHCP can outperform strong baselines on several in-domain and downstream tasks by direct evaluation. When adapted to a specific task, UniHCP achieves new SOTAs on a wide range of human-centric tasks, e.g., 69.8 mIoU on CIHP for human parsing, 86.18 mA on PA-100K for attribute prediction, 90.3 mAP on Market1501 for ReID, and 85.8 JI on CrowdHuman for pedestrian detection, performing better than specialized models tailored for each task.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). Builds on 89 of its 131 references that are in the map. First posted on arXiv 6 Mar 2023.

Builds on

89 of 131 references.

References · 89

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  7. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  8. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  9. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  10. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  11. 2021Scaling Vision Transformerscited by 993
  12. 2018Adafactor: Adaptive Learning Rates with Sublinear Memory Costcited by 896
38 more
  1. 2021Florence: A New Foundation Model for Computer Visioncited by 802
  2. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  3. 2022OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Frameworkcited by 742
  4. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 723
  5. 2021P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Taskscited by 686
  6. 2021LiT: Zero-Shot Transfer with Locked-image text Tuningcited by 572
  7. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  8. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  9. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 479
  10. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  11. 2021TransReID: Transformer-based Object Re-Identificationcited by 432
  12. 2022Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Taskscited by 420
  13. 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 402
  14. 2019Dynamic Convolution: Attention over Convolution Kernelscited by 355
  15. 2022Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentationcited by 341
  16. 2018CrowdHuman: A Benchmark for Detecting Human in a Crowdcited by 283
  17. 201912-in-1: Multi-Task Vision and Language Representation Learningcited by 278
  18. 2013OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networkscited by 224
  19. 2019Joint Discriminative and Generative Learning for Person Re-identificationcited by 211
  20. 2016UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memorycited by 200
  21. 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 199
  22. 2021UniT: Multimodal Multitask Learning with a Unified Transformercited by 195
  23. 2019PolarMask: Single Shot Instance Segmentation with Polar Representationcited by 188
  24. 2019Self-Correction for Human Parsingcited by 179
  25. 2020Whole-Body Human Pose Estimation in the Wildcited by 178
  26. 2017PoseTrack: A Benchmark for Human Pose Estimation and Trackingcited by 173
  27. 2017CityPersons: A Diverse Dataset for Pedestrian Detectioncited by 171
  28. 2021ExT5: Towards Extreme Multi-Task Scaling for Transfer Learningcited by 161
  29. 2022A Unified Sequence Interface for Vision Taskscited by 152
  30. 2018Instance-level Human Parsing via Part Grouping Networkcited by 134
  31. 2019DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Imagescited by 132
  32. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  33. 2020General Multi-label Image Classification with Transformerscited by 126
  34. 2020TransPose: Keypoint Localization via Transformercited by 126
  35. 2021Query2Label: A Simple Transformer Way to Multi-Label Classificationcited by 126
  36. 2021Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Taskscited by 124
  37. 2020Deep Snake for Real-Time Instance Segmentationcited by 111
  38. 2017Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsingcited by 109

50 most cited of 89 All 89 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 20; 2025: 22; 2026: 9.

59 papers.

Sort:

By area:

  1. 2023SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimationcited by 154
  2. 2024VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Taskscited by 136
  3. 2023Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructionscited by 46
  4. 2023HAP: Structure-Aware Masked Image Modeling for Human-Centric Perceptioncited by 33
  5. 2025SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimationcited by 31
  6. 2023Hulk: A Universal Knowledge Translator for Human-Centric Taskscited by 22
  7. 2024Transformer for Object Re-Identification: A Surveycited by 21
  8. 2025Referring to Any Personcited by 20
  9. 2024Spider: A Unified Framework for Context-dependent Concept Segmentationcited by 18
  10. 2024MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusioncited by 15
  11. 2025Face-Human-Bench: A Comprehensive Benchmark of Face and Human Understanding for Multi-modal Assistantscited by 12
  12. 2024When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Datasetcited by 10
38 more
  1. 2025Human-Centric Foundation Models: Perception, Generation and Agentic Modelingcited by 10
  2. 2023You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perceptioncited by 9
  3. 2024A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectivescited by 9
  4. 2024MLLMReID: Multimodal Large Language Model-based Person Re-identificationcited by 8
  5. 2024PoseEmbroider: Towards a 3D, Visual, Semantic-aware Human Pose Representationcited by 8
  6. 2023Structural Information Guided Multimodal Pre-training for Vehicle-centric Perceptioncited by 7
  7. 2024HERM: Benchmarking and Enhancing Multimodal LLMs for Human-Centric Understandingcited by 7
  8. 2024Diverse Representation Embedding for Lifelong Person Re-Identificationcited by 5
  9. 2025Hier-EgoPack: Hierarchical Egocentric Video Understanding with Diverse Task Perspectivescited by 5
  10. 2025CM3AE: A Unified RGB Frame and Event-Voxel/-Frame Pre-training Frameworkcited by 4
  11. 2025Towards Anytime Retrieval: A Benchmark for Anytime Person Re-Identificationcited by 4
  12. 2023Part Representation Learning with Teacher-Student Decoder for Occluded Person Re-identificationcited by 3
  13. 2024A Novel Framework for Multi-Person Temporal Gaze Following and Social Gaze Predictioncited by 3
  14. 2024Robust Pedestrian Detection via Constructing Versatile Pedestrian Knowledge Bankcited by 3
  15. 2024CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognitioncited by 3
  16. 2025UniSTD: Towards Unified Spatio-Temporal Learning across Diverse Disciplinescited by 3
  17. 2025Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learningcited by 3
  18. 2023VILLS -- Video-Image Learning to Learn Semantics for Person Re-Identificationcited by 2
  19. 2024UniFS: Universal Few-shot Instance Perception with Point Representationscited by 2
  20. 2024Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circlecited by 2
  21. 2025Scale-Aware Pre-Training for Human-Centric Visual Perception: Enabling Lightweight and Generalizable Modelscited by 2
  22. 2025SCHNet: SAM Marries CLIP for Human Parsingcited by 2
  23. 2025HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenescited by 2
  24. 2024GatedUniPose: A Novel Approach for Pose Estimation Combining UniRepLKNet and Gated Convolutioncited by 1
  25. 2024RefHCM: A Unified Model for Referring Perceptions in Human-Centric Scenarioscited by 1
  26. 2025PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimationcited by 1
  27. 2025One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Modelscited by 1
  28. 2025CrowdQuery: Density-Guided Query Module for Enhanced 2D and 3D Detection in Crowded Scenescited by 1
  29. 2024Multi Positive Contrastive Learning with Pose-Consistent Generated Imagescited by 0
  30. 2024GateAttentionPose: Enhancing Pose Estimation with Agent Attention and Improved Gated Convolutionscited by 0
  31. 2024Y-MAP-Net: Real-time depth, normals, segmentation, multi-label captioning and 2D human pose in RGB imagescited by 0
  32. 2025Dense Object Detection Based on De-homogenized Queriescited by 0
  33. 2025Periodontal Bone Loss Analysis via Keypoint Detection With Heuristic Post-Processingcited by 0
  34. 2025Adept: Annotation-Denoising Auxiliary Tasks with Discrete Cosine Transform Map and Keypoint for Human-Centric Pretrainingcited by 0
  35. 2025Dynamic Pattern Alignment Learning for Pretraining Lightweight Human-Centric Vision Modelscited by 0
  36. 2025A review of Recent Techniques for Person Re-Identificationcited by 0
  37. 2025Vision Transformer for Robust Occluded Person Reidentification in Complex Surveillance Scenescited by 0
  38. 2025HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentationcited by 0

50 most cited of 59 All 59 (JSON)