# Dissecting Human Body Representations in Deep Networks Trained for Person Identification

arXiv: https://arxiv.org/abs/2502.15934 · HTML: https://mlsanity.com/paper/2502.15934/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 48 references that are in the map.
- First posted on arXiv 21 Feb 2025.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Clothes-Changing Person Re-identification with RGB Modality Only](https://mlsanity.com/paper/2204.06890/) (2022)
- [UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles](https://mlsanity.com/paper/2104.00946/) (2021)
- [Person Re-identification by Contour Sketch under Moderate Clothing Change](https://mlsanity.com/paper/2002.02295/) (2020)
- [Expanding Accurate Person Recognition to New Altitudes and Ranges: The BRIAR Dataset](https://mlsanity.com/paper/2211.01917/) (2022)
- [MEVA: A Large-Scale Multiview, Multimodal Video Dataset for Activity Detection](https://mlsanity.com/paper/2012.00914/) (2020)
- [Learning Clothing and Pose Invariant 3D Shape Representation for Long-Term Person Re-Identification](https://mlsanity.com/paper/2308.10658/) (2023)
- [Beyond Identity: What Information Is Stored in Biometric Face Templates?](https://mlsanity.com/paper/2009.09918/) (2020)
- [Deep Convolutional Neural Networks in the Face of Caricature: Identity and Image Revealed](https://mlsanity.com/paper/1812.10902/) (2018)
- [How are attributes expressed in face DCNNs?](https://mlsanity.com/paper/1910.05657/) (2019)
- [How important are faces for person re-identification?](https://mlsanity.com/paper/2010.06307/) (2020)
- [Deep Convolutional Neural Network Features and the Original Image](https://mlsanity.com/paper/1611.01751/) (2016)
- [Recognizing People by Body Shape Using Deep Networks of Images and Words](https://mlsanity.com/paper/2305.19160/) (2023)
- [Whole-body Detection, Recognition and Identification at Altitude and Range](https://mlsanity.com/paper/2311.05725/) (2023)
- [Advancing Person Re-Identification: Tensor-based Feature Fusion and Multilinear Subspace Learning](https://mlsanity.com/paper/2312.16226/) (2023)

## Built on by (most cited first, 4 of 4)

- [A Quantitative Evaluation of the Expressivity of BMI, Pose and Gender in Body Embeddings for Recognition and Identification](https://mlsanity.com/paper/2503.06451/) (2025)
- [Not All Starting Points Are Equal: Pre-trained Priors and Their Outsized Impact on Person Identification](https://mlsanity.com/paper/2507.17640/) (2025)
- [Face, Whole-Person, and Object Classification in a Unified Space Via The Interleaved Multi-Domain Identity Curriculum](https://mlsanity.com/paper/2511.19846/) (2025)
- [AttriBE: Quantifying Attribute Expressivity in Body Embeddings for Recognition and Identification](https://mlsanity.com/paper/2604.27218/) (2026)

## Abstract (arXiv)

Long-term body identification algorithms have emerged recently with the increased availability of high-quality training data. We seek to fill knowledge gaps about these models by analyzing body image embeddings from four body identification networks trained with 1.9 million images across 4,788 identities and 9 databases. By analyzing a diverse range of architectures (ViT, SWIN-ViT, CNN, and linguistically primed CNN), we first show that the face contributes to the accuracy of body identification algorithms and that these algorithms can identify faces to some extent -- with no explicit face training. Second, we show that representations (embeddings) generated by body identification algorithms encode information about gender, as well as image-based information including view (yaw) and even the dataset from which the image originated. Third, we demonstrate that identification accuracy can be improved without additional training by operating directly and selectively on the learned embedding space. Leveraging principal component analysis (PCA), identity comparisons were consistently more accurate in subspaces that eliminated dimensions that explained large amounts of variance. These three findings were surprisingly consistent across architectures and test datasets. This work represents the first analysis of body representations produced by long-term re-identification networks trained on challenging unconstrained datasets.