Pedestrian Retrieval is a task that involves the identification and retrieval of images or video frames containing pedestrians. This task is particularly relevant in applications such as surveillance, autonomous vehicles, crowd analysis, and pedestrian tracking. The goal is to locate instances of pedestrians within a given dataset, which could be a collection of images, video frames, or a video stream. Pedestrian retrieval plays a crucial role in applications where the identification and tracking of pedestrians are essential, contributing to the development of intelligent systems for surveillance, transportation, and crowd management.


Channel Recurrent Attention Networks for Video Pedestrian Retrieval

Full attention, which generates an attention value per element of the input feature maps, has been successfully demonstrated to be beneficial in visual tasks. In this work, we propose a fully attentional network, termed channel recurrent attention network, for the task of video pedestrian retrieval. The main attention unit, channel recurrent attention, identifies attention maps at the frame level by jointly leveraging spatial and channel patterns via a recurrent neural network. This channel recurrent attention is designed to build a global receptive field by recurrently receiving and learning the spatial vectors. Then, a set aggregation cell is employed to generate a compact video representation. Empirical experimental results demonstrate the superior performance of the proposed deep network, outperforming current state-of-the-art results across standard video person retrieval benchmarks, and a thorough ablation study shows the effectiveness of the proposed units.