MPAR-RCNN: a multi-task network for multiple person detection with attribute recognition.

Abstract

Multi-label attribute recognition is a critical task in computer vision, with applications ranging across diverse fields. This problem often involves detecting objects with multiple attributes, necessitating sophisticated models capable of both high-level differentiation and fine-grained feature extraction. The integration of object detection and attribute recognition typically relies on approaches such as dual-stage networks, where accurate predictions depend on advanced feature extraction techniques, such as Region of Interest (RoI) pooling. To meet these demands, an efficient method that achieves both reliable detection and attribute classification in a unified framework is essential. This study introduces an innovative MTL framework designed to incorporate Multi-Person Attribute Recognition (MPAR) within a single-model architecture. Named MPAR-RCNN, this framework unifies object detection and attribute recognition tasks through a spatially aware, shared backbone, facilitating efficient and accurate multi-label prediction. Unlike the traditional Fast Region-based Convolutional Neural Network (R-CNN), which separately manages person detection and attribute classification with a dual-stage network, the MPAR-RCNN architecture optimizes both tasks within a single structure. Validated on the WIDER (Web Image Dataset for Event Recognition) dataset, the proposed model demonstrates an improvement over current state-of-the-art (SOTA) architectures, showcasing its potential in advancing multi-label attribute recognition.