# Viewpoint-Aware Loss with Angular Regularization for Person Re-Identification

arXiv: https://arxiv.org/abs/1912.01300 · HTML: https://mlsanity.com/paper/1912.01300/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2019.

## Built on by (most cited first, 22 of 22)

- [Large-Scale Spatio-Temporal Person Re-identification: Algorithms and Benchmark](https://mlsanity.com/paper/2105.15076/) (2021)
- [Person Re-Identification with a Locally Aware Transformer](https://mlsanity.com/paper/2106.03720/) (2021)
- [CMTR: Cross-modality Transformer for Visible-infrared Person Re-identification](https://mlsanity.com/paper/2110.08994/) (2021)
- [Semi-supervised Keypoint Localization](https://mlsanity.com/paper/2101.07988/) (2021)
- [Dynamic Enhancement Network for Partial Multi-modality Person Re-identification](https://mlsanity.com/paper/2305.15762/) (2023)
- [MMD-ReID: A Simple but Effective Solution for Visible-Thermal Person ReID](https://mlsanity.com/paper/2111.05059/) (2021)
- [Bridging the Gap: Multi-Level Cross-Modality Joint Alignment for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2307.08316/) (2023)
- [GraFT: Gradual Fusion Transformer for Multimodal Re-Identification](https://mlsanity.com/paper/2310.16856/) (2023)
- [Multi-Camera Trajectory Forecasting with Trajectory Tensors](https://mlsanity.com/paper/2108.04694/) (2021)
- [Midpoint Regularization: from High Uncertainty Training to Conservative Classification](https://mlsanity.com/paper/2106.13913/) (2021)
- [Towards Homogeneous Modality Learning and Multi-Granularity Information Exploration for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2204.04842/) (2022)
- [FRIDA: Fisheye Re-Identification Dataset with Annotations](https://mlsanity.com/paper/2210.01582/) (2022)
- [Pose Invariant Person Re-Identification using Robust Pose-transformation GAN](https://mlsanity.com/paper/2105.00930/) (2021)
- [Large-Scale Unsupervised Person Re-Identification with Contrastive Learning](https://mlsanity.com/paper/2105.07914/) (2021)
- [Combining human parsing with analytical feature extraction and ranking schemes for high-generalization person reidentification](https://mlsanity.com/paper/2207.14243/) (2022)
- [VILLS -- Video-Image Learning to Learn Semantics for Person Re-Identification](https://mlsanity.com/paper/2311.17074/) (2023)
- [Multi-Domain Biometric Recognition using Body Embeddings](https://mlsanity.com/paper/2503.10931/) (2025)
- [Angular triangle distance for ordinal metric learning](https://mlsanity.com/paper/2211.15200/) (2022)
- [Spatio-Visual Fusion-Based Person Re-Identification for Overhead Fisheye Images](https://mlsanity.com/paper/2212.11477/) (2022)
- [Real-Time Online Unsupervised Domain Adaptation for Real-World Person Re-identification](https://mlsanity.com/paper/2306.03993/) (2023)
- [ISAR: A Benchmark for Single- and Few-Shot Object Instance Segmentation and Re-Identification](https://mlsanity.com/paper/2311.02734/) (2023)
- [MARs: Multi-view Attention Regularizations for Patch-based Feature Recognition of Space Terrain](https://mlsanity.com/paper/2410.05182/) (2024)

## Abstract (arXiv)

Although great progress in supervised person re-identification (Re-ID) has been made recently, due to the viewpoint variation of a person, Re-ID remains a massive visual challenge. Most existing viewpoint-based person Re-ID methods project images from each viewpoint into separated and unrelated sub-feature spaces. They only model the identity-level distribution inside an individual viewpoint but ignore the underlying relationship between different viewpoints. To address this problem, we propose a novel approach, called textitViewpoint-Aware Loss with Angular Regularization (VA-reID). Instead of one subspace for each viewpoint, our method projects the feature from different viewpoints into a unified hypersphere and effectively models the feature distribution on both the identity-level and the viewpoint-level. In addition, rather than modeling different viewpoints as hard labels used for conventional viewpoint classification, we introduce viewpoint-aware adaptive label smoothing regularization (VALSR) that assigns the adaptive soft label to feature representation. VALSR can effectively solve the ambiguity of the viewpoint cluster label assignment. Extensive experiments on the Market1501 and DukeMTMC-reID datasets demonstrated that our method outperforms the state-of-the-art supervised Re-ID methods.