Channel Recurrent Attention Networks for Video Pedestrian Retrieval

TL;DR

This paper introduces a novel fully attentional network with channel recurrent attention for video pedestrian retrieval, leveraging recurrent neural networks to identify attention maps and improve global feature representation.

Contribution

It proposes a new channel recurrent attention mechanism that jointly models spatial and channel patterns for enhanced video pedestrian retrieval.

Findings

Outperforms state-of-the-art on standard benchmarks

Demonstrates effectiveness through ablation studies

Builds a global receptive field via recurrent learning

Abstract

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 {\it channel recurrent attention network}, for the task of video pedestrian retrieval. The main attention unit, \textit{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 \textit{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.