# Cross-Spectral Body Recognition with Side Information Embedding: Benchmarks on LLCM and Analyzing Range-Induced Occlusions on IJB-MDF

arXiv: https://arxiv.org/abs/2506.08953 · HTML: https://mlsanity.com/paper/2506.08953/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 10 Jun 2025.

## Builds on (most cited first, 22 of 22)

- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [Intriguing Properties of Vision Transformers](https://mlsanity.com/paper/2105.10497/) (2021)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Unsupervised Pre-training for Person Re-identification](https://mlsanity.com/paper/2012.03753/) (2020)
- [Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2303.14481/) (2023)
- [Occluded Person Re-identification](https://mlsanity.com/paper/1804.02792/) (2018)
- [Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification](https://mlsanity.com/paper/2104.14913/) (2021)
- [Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approach](https://mlsanity.com/paper/1801.00881/) (2018)
- [Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification](https://mlsanity.com/paper/1904.00537/) (2019)
- [Foreground-aware Pyramid Reconstruction for Alignment-free Occluded Person Re-identification](https://mlsanity.com/paper/1904.04975/) (2019)
- [Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions](https://mlsanity.com/paper/2306.07520/) (2023)
- [Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification](https://mlsanity.com/paper/2107.02380/) (2021)
- [Feature Erasing and Diffusion Network for Occluded Person Re-Identification](https://mlsanity.com/paper/2112.08740/) (2021)
- [Robust Partial Matching for Person Search in the Wild](https://mlsanity.com/paper/2004.09329/) (2020)
- [Minimum-Distortion Embedding](https://mlsanity.com/paper/2103.02559/) (2021)
- [Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2403.11708/) (2024)
- [STNReID : Deep Convolutional Networks with Pairwise Spatial Transformer Networks for Partial Person Re-identification](https://mlsanity.com/paper/1903.07072/) (2019)
- [CMTR: Cross-modality Transformer for Visible-infrared Person Re-identification](https://mlsanity.com/paper/2110.08994/) (2021)
- [WRIM-Net: Wide-Ranging Information Mining Network for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2408.10624/) (2024)
- [Exploring Stronger Transformer Representation Learning for Occluded Person Re-Identification](https://mlsanity.com/paper/2410.15613/) (2024)

## Abstract (arXiv)

Vision Transformers (ViTs) have demonstrated impressive performance across a wide range of biometric tasks, including face and body recognition. In this work, we adapt a ViT model pretrained on visible (VIS) imagery to the challenging problem of cross-spectral body recognition, which involves matching images captured in the visible and infrared (IR) domains. Recent ViT architectures have explored incorporating additional embeddings beyond traditional positional embeddings. Building on this idea, we integrate Side Information Embedding (SIE) and examine the impact of encoding domain and camera information to enhance cross-spectral matching. Surprisingly, our results show that encoding only camera information - without explicitly incorporating domain information - achieves state-of-the-art performance on the LLCM dataset. While occlusion handling has been extensively studied in visible-spectrum person re-identification (Re-ID), occlusions in visible-infrared (VI) Re-ID remain largely underexplored - primarily because existing VI-ReID datasets, such as LLCM, SYSU-MM01, and RegDB, predominantly feature full-body, unoccluded images. To address this gap, we analyze the impact of range-induced occlusions using the IARPA Janus Benchmark Multi-Domain Face (IJB-MDF) dataset, which provides a diverse set of visible and infrared images captured at various distances, enabling cross-range, cross-spectral evaluations.