Channel Recurrent Attention Networks for Video Pedestrian Retrieval

10/07/2020
by   Pengfei Fang, et al.
0

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.

READ FULL TEXT

page 14

page 23

page 27

research
05/09/2019

Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Information

Multi-person pose estimation is an important but challenging problem in ...
research
08/03/2018

Where-and-When to Look: Deep Siamese Attention Networks for Video-based Person Re-identification

Video-based person re-identification (re-id) is a central application in...
research
09/23/2022

Pose-Aided Video-based Person Re-Identification via Recurrent Graph Convolutional Network

Existing methods for video-based person re-identification (ReID) mainly ...
research
01/17/2019

Video-Based Pedestrian Attribute Recognition

In this paper, we first tackle the problem of pedestrian attribute recog...
research
04/22/2019

Stochastic Region Pooling: Make Attention More Expressive

Global Average Pooling (GAP) is used by default on the channel-wise atte...
research
07/19/2020

A Generic Visualization Approach for Convolutional Neural Networks

Retrieval networks are essential for searching and indexing. Compared to...
research
05/26/2021

Spatio-Contextual Deep Network Based Multimodal Pedestrian Detection For Autonomous Driving

Pedestrian Detection is the most critical module of an Autonomous Drivin...

Please sign up or login with your details

Forgot password? Click here to reset