mlsanityData to 14 Oct 2026

Clothes-Changing Person Re-identification Based On Skeleton Dynamics

arXiv 2503.10759 ↗First posted 13 Mar 2025cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Clothes-Changing Person Re-Identification (ReID) aims to recognize the same individual across different videos captured at various times and locations. This task is particularly challenging due to changes in appearance, such as clothing, hairstyle, and accessories. We propose a Clothes-Changing ReID method that uses only skeleton data and does not use appearance features. Traditional ReID methods often depend on appearance features, leading to decreased accuracy when clothing changes. Our approach utilizes a spatio-temporal Graph Convolution Network (GCN) encoder to generate a skeleton-based descriptor for each individual. During testing, we improve accuracy by aggregating predictions from multiple segments of a video clip. Evaluated on the CCVID dataset with several different pose estimation models, our method achieves state-of-the-art performance, offering a robust and efficient solution for Clothes-Changing ReID.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 29 of its 42 references that are in the map. First posted on arXiv 13 Mar 2025.

Builds on

29 of 42 references.

References · 29

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  4. 2016An overview of gradient descent optimization algorithmscited by 1,033
  5. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 786
  6. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 499
  7. 2017Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)cited by 473
  8. 2017Re-ranking Person Re-identification with k-reciprocal Encodingcited by 262
  9. 2021Revisiting Skeleton-based Action Recognitioncited by 257
  10. 2019Understanding Attention and Generalization in Graph Neural Networkscited by 169
  11. 2020MediaPipe Hands: On-device Real-time Hand Trackingcited by 161
  12. 2020BlazePose: On-device Real-time Body Pose trackingcited by 113
17 more
  1. 2022Clothes-Changing Person Re-identification with RGB Modality Onlycited by 98
  2. 2020Person Re-identification by Contour Sketch under Moderate Clothing Changecited by 91
  3. 2020Long-Term Cloth-Changing Person Re-identificationcited by 85
  4. 2019BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUscited by 74
  5. 2021Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularizationcited by 69
  6. 2020Appearance-Preserving 3D Convolution for Video-based Person Re-identificationcited by 63
  7. 2018Multi-scale 3D Convolution Network for Video Based Person Re-Identificationcited by 41
  8. 2017Jointly Attentive Spatial-Temporal Pooling Networks for Video-based Person Re-Identificationcited by 39
  9. 2023Part-Aware Transformer for Generalizable Person Re-identificationcited by 35
  10. 2019Adaptive Graph Representation Learning for Video Person Re-identificationcited by 34
  11. 2016Nesterov's Accelerated Gradient and Momentum as approximations to Regularised Update Descentcited by 26
  12. 2020Learning Longterm Representations for Person Re-Identification Using Radio Signalscited by 25
  13. 2017Person Re-Identification via Recurrent Feature Aggregationcited by 17
  14. 2018Video-based Person Re-identification via 3D Convolutional Networks and Non-local Attentioncited by 14
  15. 2016Best-Buddies Similarity - Robust Template Matching using Mutual Nearest Neighborscited by 12
  16. 2017Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identificationcited by 12
  17. 2022GEFF: Improving Any Clothes-Changing Person ReID Model using Gallery Enrichment with Face Featurescited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Multi-modal Multi-platform Person Re-Identification: Benchmark and Methodcited by 6
  2. 2025Try Harder: Hard Sample Generation and Learning for Clothes-Changing Person Re-IDcited by 5
  3. 2025Addressing the ID-Matching Challenge in Long Video Captioningcited by 2
  4. 2026Reliability-Aware 3D Geometric Injection for Universal Person Re-identificationcited by 0