# RGB-Event based Pedestrian Attribute Recognition: A Benchmark Dataset and An Asymmetric RWKV Fusion Framework

arXiv: https://arxiv.org/abs/2504.10018 · HTML: https://mlsanity.com/paper/2504.10018/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 64 references that are in the map.
- First posted on arXiv 14 Apr 2025.

## Builds on (most cited first, 30 of 46)

- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [RWKV: Reinventing RNNs for the Transformer Era](https://mlsanity.com/paper/2305.13048/) (2023)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [SGD: General Analysis and Improved Rates](https://mlsanity.com/paper/1901.09401/) (2019)
- [Probabilistic and Geometric Depth: Detecting Objects in Perspective](https://mlsanity.com/paper/2107.14160/) (2021)
- [An Attention Free Transformer](https://mlsanity.com/paper/2105.14103/) (2021)
- [DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval](https://mlsanity.com/paper/2109.05534/) (2021)
- [Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures](https://mlsanity.com/paper/2403.02308/) (2024)
- [HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis](https://mlsanity.com/paper/1709.09930/) (2017)
- [Learning Event-Based Motion Deblurring](https://mlsanity.com/paper/2004.05794/) (2020)
- [Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark](https://mlsanity.com/paper/2306.02898/) (2023)
- [State Space Model for New-Generation Network Alternative to Transformers: A Survey](https://mlsanity.com/paper/2404.09516/) (2024)
- [Pedestrian Attribute Recognition: A Survey](https://mlsanity.com/paper/1901.07474/) (2019)
- [PLIP: Language-Image Pre-training for Person Representation Learning](https://mlsanity.com/paper/2305.08386/) (2023)
- [Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization](https://mlsanity.com/paper/1910.04562/) (2019)
- [EventSR: From Asynchronous Events to Image Reconstruction, Restoration, and Super-Resolution via End-to-End Adversarial Learning](https://mlsanity.com/paper/2003.07640/) (2020)
- [COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification](https://mlsanity.com/paper/2005.07862/) (2020)
- [A Richly Annotated Dataset for Pedestrian Attribute Recognition](https://mlsanity.com/paper/1603.07054/) (2016)
- [Learning Spatial-Temporal Implicit Neural Representations for Event-Guided Video Super-Resolution](https://mlsanity.com/paper/2303.13767/) (2023)
- [HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception](https://mlsanity.com/paper/2310.20695/) (2023)
- [Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition](https://mlsanity.com/paper/2109.05686/) (2021)
- [Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting](https://mlsanity.com/paper/2107.03576/) (2021)
- [Uni3DETR: Unified 3D Detection Transformer](https://mlsanity.com/paper/2310.05699/) (2023)
- [Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion](https://mlsanity.com/paper/2312.10692/) (2023)
- [Label2Label: A Language Modeling Framework for Multi-Attribute Learning](https://mlsanity.com/paper/2207.08677/) (2022)
- [PARFormer: Transformer-based Multi-Task Network for Pedestrian Attribute Recognition](https://mlsanity.com/paper/2304.07230/) (2023)
- [Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Model](https://mlsanity.com/paper/2406.19369/) (2024)

## Built on by (most cited first, 7 of 7)

- [Adversarial Semantic and Label Perturbation Attack for Pedestrian Attribute Recognition](https://mlsanity.com/paper/2505.23313/) (2025)
- [EvRainDrop: HyperGraph-guided Completion for Effective Frame and Event Stream Aggregation](https://mlsanity.com/paper/2511.21439/) (2025)
- [SMV-EAR: Bring Spatiotemporal Multi-View Representation Learning into Efficient Event-Based Action Recognition](https://mlsanity.com/paper/2601.17391/) (2026)
- [Reconstruction as a Bridge for Event-Based Visual Question Answering](https://mlsanity.com/paper/2512.11510/) (2025)
- [RGB-Event HyperGraph Prompt for Kilometer Marker Recognition based on Pre-trained Foundation Models](https://mlsanity.com/paper/2602.22026/) (2026)
- [UniPAR: A Unified Framework for Pedestrian Attribute Recognition](https://mlsanity.com/paper/2603.05114/) (2026)
- [PFM-VEPAR: Prompting Foundation Models for RGB-Event Camera based Pedestrian Attribute Recognition](https://mlsanity.com/paper/2603.19565/) (2026)

## Abstract (arXiv)

Existing pedestrian attribute recognition methods are generally developed based on RGB frame cameras. However, these approaches are constrained by the limitations of RGB cameras, such as sensitivity to lighting conditions and motion blur, which hinder their performance. Furthermore, current attribute recognition primarily focuses on analyzing pedestrians' external appearance and clothing, lacking an exploration of emotional dimensions. In this paper, we revisit these issues and propose a novel multi-modal RGB-Event attribute recognition task by drawing inspiration from the advantages of event cameras in low-light, high-speed, and low-power consumption. Specifically, we introduce the first large-scale multi-modal pedestrian attribute recognition dataset, termed EventPAR, comprising 100K paired RGB-Event samples that cover 50 attributes related to both appearance and six human emotions, diverse scenes, and various seasons. By retraining and evaluating mainstream PAR models on this dataset, we establish a comprehensive benchmark and provide a solid foundation for future research in terms of data and algorithmic baselines. In addition, we propose a novel RWKV-based multi-modal pedestrian attribute recognition framework, featuring an RWKV visual encoder and an asymmetric RWKV fusion module. Extensive experiments are conducted on our proposed dataset as well as two simulated datasets (MARS-Attribute and DukeMTMC-VID-Attribute), achieving state-of-the-art results. The source code and dataset will be released on https://github.com/Event-AHU/OpenPAR