mlsanityData to 7 Oct 2026

Cascade Transformers for End-to-End Person Search

arXiv 2203.09642 ↗First posted 17 Mar 2022cs.CVcited by 31

Not on the map. Why?

Abstract (arXiv)

The goal of person search is to localize a target person from a gallery set of scene images, which is extremely challenging due to large scale variations, pose/viewpoint changes, and occlusions. In this paper, we propose the Cascade Occluded Attention Transformer (COAT) for end-to-end person search. Our three-stage cascade design focuses on detecting people in the first stage, while later stages simultaneously and progressively refine the representation for person detection and re-identification. At each stage the occluded attention transformer applies tighter intersection over union thresholds, forcing the network to learn coarse-to-fine pose/scale invariant features. Meanwhile, we calculate each detection's occluded attention to differentiate a person's tokens from other people or the background. In this way, we simulate the effect of other objects occluding a person of interest at the token-level. Through comprehensive experiments, we demonstrate the benefits of our method by achieving state-of-the-art performance on two benchmark datasets.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Builds on 30 of its 39 references that are in the map. First posted on arXiv 17 Mar 2022.

Builds on

30 of 39 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  7. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  8. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  9. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  10. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  11. 2021TransReID: Transformer-based Object Re-Identificationcited by 432
  12. 2019Bag of Tricks and A Strong Baseline for Deep Person Re-identificationcited by 429
18 more
  1. 2016Joint Detection and Identification Feature Learning for Person Searchcited by 190
  2. 2016Person Re-identification in the Wildcited by 157
  3. 2021Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformercited by 119
  4. 2021CAT: Cross Attention in Vision Transformercited by 92
  5. 2019Learning Context Graph for Person Searchcited by 55
  6. 2018Batch DropBlock Network for Person Re-identification and Beyondcited by 45
  7. 2018Person Search via A Mask-Guided Two-Stream CNN Modelcited by 44
  8. 2021Anchor-Free Person Searchcited by 42
  9. 2019Re-ID Driven Localization Refinement for Person Searchcited by 41
  10. 2019Query-guided End-to-End Person Searchcited by 40
  11. 2021HAT: Hierarchical Aggregation Transformers for Person Re-identificationcited by 39
  12. 2021Sequential End-to-end Network for Efficient Person Searchcited by 38
  13. 2018Person Search by Multi-Scale Matchingcited by 36
  14. 2017Neural Person Search Machinescited by 35
  15. 2020Robust Partial Matching for Person Search in the Wildcited by 30
  16. 2017IAN: The Individual Aggregation Network for Person Searchcited by 29
  17. 2019STNReID : Deep Convolutional Networks with Pairwise Spatial Transformer Networks for Partial Person Re-identificationcited by 23
  18. 2021Decoupled and Memory-Reinforced Networks: Towards Effective Feature Learning for One-Step Person Searchcited by 19

Built on by

Cited by year

Citing papers per year: 2022: 6; 2023: 13; 2024: 8; 2025: 4.

31 papers.

Sort:

By area:

  1. 2024Transformer for Object Re-Identification: A Surveycited by 21
  2. 2022Cross-receptive Focused Inference Network for Lightweight Image Super-Resolutioncited by 16
  3. 2022MEVID: Multi-view Extended Videos with Identities for Video Person Re-Identificationcited by 16
  4. 2022Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Networkcited by 13
  5. 2024X-Light: Cross-City Traffic Signal Control Using Transformer on Transformer as Meta Multi-Agent Reinforcement Learnercited by 10
  6. 2023Ground-to-Aerial Person Search: Benchmark Dataset and Approachcited by 9
  7. 2022Gallery Filter Network for Person Searchcited by 8
  8. 2025PRVQL: Progressive Knowledge-guided Refinement for Robust Egocentric Visual Query Localizationcited by 8
  9. 2023Self-similarity Driven Scale-invariant Learning for Weakly Supervised Person Searchcited by 7
  10. 2022Transformer in Transformer as Backbone for Deep Reinforcement Learningcited by 6
  11. 2023PDiT: Interleaving Perception and Decision-making Transformers for Deep Reinforcement Learningcited by 5
  12. 2024From Attributes to Natural Language: A Survey and Foresight on Text-based Person Re-identificationcited by 5
19 more
  1. 2023Deep Intra-Image Contrastive Learning for Weakly Supervised One-Step Person Searchcited by 4
  2. 2023OccluTrack: Rethinking Awareness of Occlusion for Enhancing Multiple Pedestrian Trackingcited by 3
  3. 2023PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinementcited by 2
  4. 2024Domain Generalizable Person Search Using Unreal Datasetcited by 2
  5. 2024Scene-Adaptive Person Search via Bilateral Modulationscited by 2
  6. 2024Prompting Continual Person Searchcited by 2
  7. 2022Sequential Transformer for End-to-End Person Searchcited by 1
  8. 2023LEAPS: End-to-End One-Step Person Search With Learnable Proposalscited by 1
  9. 2023DDAM-PS: Diligent Domain Adaptive Mixer for Person Searchcited by 1
  10. 2025Leveraging Prior Knowledge of Diffusion Model for Person Searchcited by 1
  11. 2023Recent Advances of Local Mechanisms in Computer Vision: A Survey and Outlook of Recent Workcited by 0
  12. 2023Domain Adaptive Person Search via GAN-based Scene Synthesis for Cross-scene Videoscited by 0
  13. 2023Towards Fully Decoupled End-to-End Person Searchcited by 0
  14. 2023Generalizable Person Search on Open-world User-Generated Video Contentcited by 0
  15. 2023Prototype-Guided Text-based Person Search based on Rich Chinese Descriptionscited by 0
  16. 2024Lifelong Person Searchcited by 0
  17. 2024Swap Path Network for Robust Person Search Pre-trainingcited by 0
  18. 2025Transformer-Based Person Search with High-Frequency Augmentation and Multi-Wave Mixingcited by 0
  19. 2025CLIPVehicle: A Unified Framework for Vision-based Vehicle Searchcited by 0