CityGuard introduces a graph-aware transformer with dispersion-adaptive metrics, spatially conditioned attention using coarse geometry, and differentially private embeddings to support privacy-preserving identity retrieval across city cameras.
A Richly Annotated Dataset for Pedestrian Attribute Recognition
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
In this paper, we aim to improve the dataset foundation for pedestrian attribute recognition in real surveillance scenarios. Recognition of human attributes, such as gender, and clothes types, has great prospects in real applications. However, the development of suitable benchmark datasets for attribute recognition remains lagged behind. Existing human attribute datasets are collected from various sources or an integration of pedestrian re-identification datasets. Such heterogeneous collection poses a big challenge on developing high quality fine-grained attribute recognition algorithms. Furthermore, human attribute recognition are generally severely affected by environmental or contextual factors, such as viewpoints, occlusions and body parts, while existing attribute datasets barely care about them. To tackle these problems, we build a Richly Annotated Pedestrian (RAP) dataset from real multi-camera surveillance scenarios with long term collection, where data samples are annotated with not only fine-grained human attributes but also environmental and contextual factors. RAP has in total 41,585 pedestrian samples, each of which is annotated with 72 attributes as well as viewpoints, occlusions, body parts information. To our knowledge, the RAP dataset is the largest pedestrian attribute dataset, which is expected to greatly promote the study of large-scale attribute recognition systems. Furthermore, we empirically analyze the effects of different environmental and contextual factors on pedestrian attribute recognition. Experimental results demonstrate that viewpoints, occlusions and body parts information could assist attribute recognition a lot in real applications.
fields
cs.CV 5representative citing papers
A LoRA-adapted diffusion model generates surveillance-style pedestrian images whose labels are verified by a Bayesian classifier on BLIP scores, improving PAR accuracy over naive synthetic labeling.
UAPAR is the first evidential deep learning framework for pedestrian attribute recognition that estimates attribute-wise epistemic uncertainty via a region-aware module and uses uncertainty-guided curriculum learning to handle label noise, achieving competitive results on PA100K, PETA, RAPv1 and RAP
Proposes attribute aware pooling that integrates branch predictions and context information to exploit correlations between pedestrian attributes.
YOLOv8n detection plus ResNet18 classification on semantically mapped PETA and PA-100K data yields 99.89% gender accuracy, 4.23-year age MAE, 89.96% multi-attribute accuracy, and 25-30 FPS on RTX 5060.
citing papers explorer
-
CityGuard: Graph-Aware Private Descriptors for Bias-Resilient Identity Search Across Urban Cameras
CityGuard introduces a graph-aware transformer with dispersion-adaptive metrics, spatially conditioned attention using coarse geometry, and differentially private embeddings to support privacy-preserving identity retrieval across city cameras.
-
ReSAGE-PAR: Representational Similarity Assessment for Generative Expansion in Pedestrian Attribute Recognition
A LoRA-adapted diffusion model generates surveillance-style pedestrian images whose labels are verified by a Bayesian classifier on BLIP scores, improving PAR accuracy over naive synthetic labeling.
-
Uncertainty-Aware Pedestrian Attribute Recognition via Evidential Deep Learning
UAPAR is the first evidential deep learning framework for pedestrian attribute recognition that estimates attribute-wise epistemic uncertainty via a region-aware module and uses uncertainty-guided curriculum learning to handle label noise, achieving competitive results on PA100K, PETA, RAPv1 and RAP
-
Attribute Aware Pooling for Pedestrian Attribute Recognition
Proposes attribute aware pooling that integrates branch predictions and context information to exploit correlations between pedestrian attributes.
-
Real-time pedestrian attribute recognition with YOLOv8 and ResNet18
YOLOv8n detection plus ResNet18 classification on semantically mapped PETA and PA-100K data yields 99.89% gender accuracy, 4.23-year age MAE, 89.96% multi-attribute accuracy, and 25-30 FPS on RTX 5060.