2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) 2019
DOI: 10.1109/iccvw.2019.00181
|View full text |Cite
|
Sign up to set email alerts
|

Attention-Aware Age-Agnostic Visual Place Recognition

Abstract: A cross-domain visual place recognition (VPR) task is proposed in this work, i.e., matching images of the same architectures depicted in different domains. VPR is commonly treated as an image retrieval task, where a query image from an unknown location is matched with relevant instances from geo-tagged gallery database. Different from conventional VPR settings where the query images and gallery images come from the same domain, we propose a more common but challenging setup where the query images are collected… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
25
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
6
2
1

Relationship

1
8

Authors

Journals

citations
Cited by 19 publications
(25 citation statements)
references
References 37 publications
0
25
0
Order By: Relevance
“…Attention module is widely used in natural language processing [7] and computer vision [43], [56] fields by allowing the network to focus on key words or pixels. Self-attention mechanism is proposed to capture the relative relationship between words or pixels.…”
Section: Self-attentionmentioning
confidence: 99%
“…Attention module is widely used in natural language processing [7] and computer vision [43], [56] fields by allowing the network to focus on key words or pixels. Self-attention mechanism is proposed to capture the relative relationship between words or pixels.…”
Section: Self-attentionmentioning
confidence: 99%
“…One specific case of cross-domain place recognition is considered in [205]: the database is composed of present day RGB images and the queries are historic images from the same area. In this case the domain shift is caused not only by possible changes in the scene but also by the different technology used to take the photos.…”
Section: E Adapting To Different Environmental Conditionsmentioning
confidence: 99%
“…To learn domain-invariant features for cross-domain visual place recognition, Wang et al [160] propose an approach that combines weakly supervised learning with unsupervised learning. The proposed architecture has three primary modules: an attention module, an attention-aware VLAD module, and a domain adaptation module.…”
Section: Semi-supervised Place Recognitionmentioning
confidence: 99%