NetVLAD: CNN architecture for weakly supervised place recognition

1.1k indexed citations

Abstract

loading...

About

This paper, published in 2015, received 1.1k indexed citations. Written by Relja Arandjelović, Petr Gronát, Akihiko Torii, Tomáš Pajdla and Josef Šivic covering the research area of Media Technology, Aerospace Engineering and Computer Vision and Pattern Recognition. It is primarily cited by scholars working on Computer Vision and Pattern Recognition (974 citations), Aerospace Engineering (645 citations) and Artificial Intelligence (171 citations). Published in arXiv (Cornell University).

In The Last Decade

doi.org/w14796693 →

Countries where authors are citing NetVLAD: CNN architecture for weakly supervised place recognition

Specialization
Citations

This map shows the geographic impact of NetVLAD: CNN architecture for weakly supervised place recognition. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by NetVLAD: CNN architecture for weakly supervised place recognition with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites NetVLAD: CNN architecture for weakly supervised place recognition more than expected).

Fields of papers citing NetVLAD: CNN architecture for weakly supervised place recognition

Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of NetVLAD: CNN architecture for weakly supervised place recognition. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the NetVLAD: CNN architecture for weakly supervised place recognition.

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

This paper is also available at doi.org/w14796693.

Explore hit-papers with similar magnitude of impact

Rankless by CCL
2026