# Recognizing People by Body Shape Using Deep Networks of Images and Words

arXiv: https://arxiv.org/abs/2305.19160 · HTML: https://mlsanity.com/paper/2305.19160/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 23 references that are in the map.
- First posted on arXiv 30 May 2023.

## Builds on (most cited first, 9 of 9)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (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)
- [Multi-Modal Human Authentication Using Silhouettes, Gait and RGB](https://mlsanity.com/paper/2210.04050/) (2022)

## Built on by (most cited first, 8 of 8)

- [From Data to Insights: A Covariate Analysis of the IARPA BRIAR Dataset for Multimodal Biometric Recognition Algorithms at Altitude and Range](https://mlsanity.com/paper/2409.01514/) (2024)
- [Dissecting Human Body Representations in Deep Networks Trained for Person Identification](https://mlsanity.com/paper/2502.15934/) (2025)
- [The Paradox of Motion: Evidence for Spurious Correlations in Skeleton-based Gait Recognition Models](https://mlsanity.com/paper/2402.08320/) (2024)
- [Unconstrained Body Recognition at Altitude and Range: Comparing Four Approaches](https://mlsanity.com/paper/2502.07130/) (2025)
- [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)
- [Human Body Model based ID using Shape and Pose Parameters](https://mlsanity.com/paper/2312.03227/) (2023)
- [AttriBE: Quantifying Attribute Expressivity in Body Embeddings for Recognition and Identification](https://mlsanity.com/paper/2604.27218/) (2026)

## Abstract (arXiv)

Common and important applications of person identification occur at distances and viewpoints in which the face is not visible or is not sufficiently resolved to be useful. We examine body shape as a biometric across distance and viewpoint variation. We propose an approach that combines standard object classification networks with representations based on linguistic (word-based) descriptions of bodies. Algorithms with and without linguistic training were compared on their ability to identify people from body shape in images captured across a large range of distances/views (close-range, 100m, 200m, 270m, 300m, 370m, 400m, 490m, 500m, 600m, and at elevated pitch in images taken by an unmanned aerial vehicle [UAV]). Accuracy, as measured by identity-match ranking and false accept errors in an open-set test, was surprisingly good. For identity-ranking, linguistic models were more accurate for close-range images, whereas non-linguistic models fared better at intermediary distances. Fusion of the linguistic and non-linguistic embeddings improved performance at all, but the farthest distance. Although the non-linguistic model yielded fewer false accepts at all distances, fusion of the linguistic and non-linguistic models decreased false accepts for all, but the UAV images. We conclude that linguistic and non-linguistic representations of body shape can offer complementary identity information for bodies that can improve identification in applications of interest.