mlsanityData to 7 Oct 2026

Anchor-Free Person Search

arXiv 2103.11617 ↗First posted 22 Mar 2021cs.CVcited by 42

Not on the map. Why?

Abstract (arXiv)

Person search aims to simultaneously localize and identify a query person from realistic, uncropped images, which can be regarded as the unified task of pedestrian detection and person re-identification (re-id). Most existing works employ two-stage detectors like Faster-RCNN, yielding encouraging accuracy but with high computational overhead. In this work, we present the Feature-Aligned Person Search Network (AlignPS), the first anchor-free framework to efficiently tackle this challenging task. AlignPS explicitly addresses the major challenges, which we summarize as the misalignment issues in different levels (i.e., scale, region, and task), when accommodating an anchor-free detector for this task. More specifically, we propose an aligned feature aggregation module to generate more discriminative and robust feature embeddings by following a "re-id first" principle. Such a simple design directly improves the baseline anchor-free model on CUHK-SYSU by more than 20% in mAP. Moreover, AlignPS outperforms state-of-the-art two-stage methods, with a higher speed. Code is available at https://github.com/daodaofr/AlignPS

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). Builds on 37 of its 57 references that are in the map. First posted on arXiv 22 Mar 2021.

Builds on

37 of 57 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  4. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  5. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  6. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  7. 2017Deformable Convolutional Networkscited by 1,481
  8. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  9. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  10. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  11. 2019Objects as Pointscited by 1,172
  12. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 784
25 more
  1. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  2. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  3. 2020FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Trackingcited by 489
  4. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 479
  5. 2017Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)cited by 472
  6. 2017Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitrocited by 280
  7. 2019RepPoints: Point Set Representation for Object Detectioncited by 264
  8. 2019Libra R-CNN: Towards Balanced Learning for Object Detectioncited by 255
  9. 2016Joint Detection and Identification Feature Learning for Person Searchcited by 190
  10. 2017Beyond triplet loss: a deep quadruplet network for person re-identificationcited by 172
  11. 2017CityPersons: A Diverse Dataset for Pedestrian Detectioncited by 171
  12. 2016Person Re-identification in the Wildcited by 157
  13. 2017Single-Shot Refinement Neural Network for Object Detectioncited by 129
  14. 2017Pose-driven Deep Convolutional Model for Person Re-identificationcited by 86
  15. 2020Revisiting the Sibling Head in Object Detectorcited by 82
  16. 2018FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identificationcited by 70
  17. 2019Learning Context Graph for Person Searchcited by 55
  18. 2018Person Search via A Mask-Guided Two-Stream CNN Modelcited by 44
  19. 2019Re-ID Driven Localization Refinement for Person Searchcited by 41
  20. 2019Query-guided End-to-End Person Searchcited by 40
  21. 2018Person Search by Multi-Scale Matchingcited by 36
  22. 2017Person Re-Identification by Camera Correlation Aware Feature Augmentationcited by 35
  23. 2017Neural Person Search Machinescited by 35
  24. 2017IAN: The Individual Aggregation Network for Person Searchcited by 29
  25. 2016Person Re-Identification by Discriminative Selection in Video Rankingcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 10; 2023: 12; 2024: 6; 2025: 5; 2026: 1.

42 papers.

Sort:

By area:

  1. 2023Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Taskscited by 94
  2. 2022Cascade Transformers for End-to-End Person Searchcited by 31
  3. 2022PSTR: End-to-End One-Step Person Search With Transformerscited by 26
  4. 2021Exploring Visual Context for Weakly Supervised Person Searchcited by 16
  5. 2021EAN: Event Adaptive Network for Enhanced Action Recognitioncited by 16
  6. 2022OIMNet++: Prototypical Normalization and Localization-aware Learning for Person Searchcited by 12
  7. 2023Ground-to-Aerial Person Search: Benchmark Dataset and Approachcited by 9
  8. 2022Gallery Filter Network for Person Searchcited by 8
  9. 2022Domain Adaptive Person Searchcited by 7
  10. 2023Self-similarity Driven Scale-invariant Learning for Weakly Supervised Person Searchcited by 7
  11. 2021Context-Aware Unsupervised Clustering for Person Searchcited by 6
  12. 2021Efficient Person Search: An Anchor-Free Approachcited by 5
30 more
  1. 2023Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-Free One-Stage Detectorscited by 5
  2. 2021MovieNet-PS: A Large-Scale Person Search Dataset in the Wildcited by 4
  3. 2023Deep Intra-Image Contrastive Learning for Weakly Supervised One-Step Person Searchcited by 4
  4. 2021Making Person Search Enjoy the Merits of Person Re-identificationcited by 3
  5. 2022CGUA: Context-Guided and Unpaired-Assisted Weakly Supervised Person Searchcited by 3
  6. 2022Query-Guided Networks for Few-shot Fine-grained Classification and Person Searchcited by 3
  7. 2023PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinementcited by 2
  8. 2024Scene-Adaptive Person Search via Bilateral Modulationscited by 2
  9. 2021Head and Body: Unified Detector and Graph Network for Person Search in Mediacited by 1
  10. 2022Grouped Adaptive Loss Weighting for Person Searchcited by 1
  11. 2022PS-ARM: An End-to-End Attention-aware Relation Mixer Network for Person Searchcited by 1
  12. 2022Sequential Transformer for End-to-End Person Searchcited by 1
  13. 2023LEAPS: End-to-End One-Step Person Search With Learnable Proposalscited by 1
  14. 2023DDAM-PS: Diligent Domain Adaptive Mixer for Person Searchcited by 1
  15. 2024Fast One-Stage Unsupervised Domain Adaptive Person Searchcited by 1
  16. 2024Unsupervised Domain Adaptive Person Search via Dual Self-Calibrationcited by 1
  17. 2025Uncertainty-Aware Prototype Semantic Decoupling for Text-Based Person Search in Full Imagescited by 1
  18. 2025SA-Person: Text-Based Person Retrieval with Scene-aware Re-rankingcited by 1
  19. 2025To New Beginnings: A Survey of Unified Perception in Autonomous Vehicle Softwarecited by 1
  20. 2025Leveraging Prior Knowledge of Diffusion Model for Person Searchcited by 1
  21. 2021Subtask-dominated Transfer Learning for Long-tail Person Searchcited by 0
  22. 2023CA-CentripetalNet: A novel anchor-free deep learning framework for hardhat wearing detectioncited by 0
  23. 2023Domain Adaptive Person Search via GAN-based Scene Synthesis for Cross-scene Videoscited by 0
  24. 2023Towards Fully Decoupled End-to-End Person Searchcited by 0
  25. 2023Prototype-Guided Text-based Person Search based on Rich Chinese Descriptionscited by 0
  26. 2024Lifelong Person Searchcited by 0
  27. 2024Mean Height Aided Post-Processing for Pedestrian Detectioncited by 0
  28. 2024Swap Path Network for Robust Person Search Pre-trainingcited by 0
  29. 2025Transformer-Based Person Search with High-Frequency Augmentation and Multi-Wave Mixingcited by 0
  30. 2026ICON: Invariant Counterfactual Optimization with Neuro-Symbolic Priors for Text-Based Person Searchcited by 0