Composed Image Retrieval for Remote Sensing

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00379044" target="_blank" >RIV/68407700:21230/24:00379044 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/IGARSS53475.2024.10642874" target="_blank" >https://doi.org/10.1109/IGARSS53475.2024.10642874</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/IGARSS53475.2024.10642874" target="_blank" >10.1109/IGARSS53475.2024.10642874</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Composed Image Retrieval for Remote Sensing

Popis výsledku v původním jazyce

This work introduces composed image retrieval to remote sensing. It allows to query a large image archive by image examples alternated by a textual description, enriching the descriptive power over unimodal queries, either visual or textual. Various attributes can be modified by the textual part, such as shape, color, or context. A novel method fusing image-to-image and text-to-image similarity is introduced. We demonstrate that a vision-language model possesses sufficient descriptive power and no further learning step or training data are necessary. We present a new evaluation benchmark focused on color, context, density, existence, quantity, and shape modifications. Our work not only sets the state-of-the-art for this task, but also serves as a foundational step in addressing a gap in the field of remote sensing image retrieval. Code at: https://github.com/billpsomas/rscir.

Název v anglickém jazyce

Composed Image Retrieval for Remote Sensing

Popis výsledku anglicky

This work introduces composed image retrieval to remote sensing. It allows to query a large image archive by image examples alternated by a textual description, enriching the descriptive power over unimodal queries, either visual or textual. Various attributes can be modified by the textual part, such as shape, color, or context. A novel method fusing image-to-image and text-to-image similarity is introduced. We demonstrate that a vision-language model possesses sufficient descriptive power and no further learning step or training data are necessary. We present a new evaluation benchmark focused on color, context, density, existence, quantity, and shape modifications. Our work not only sets the state-of-the-art for this task, but also serves as a foundational step in addressing a gap in the field of remote sensing image retrieval. Code at: https://github.com/billpsomas/rscir.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GM21-28830M" target="_blank" >GM21-28830M: Učení Univerzální Vizuální Reprezentace s Omezenou Supervizí</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium Proceedings

ISBN

979-8-3503-6033-2

ISSN

2153-6996

e-ISSN

2153-7003

Počet stran výsledku

9

Strana od-do

8526-8534

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Athens

Datum konání akce

7. 7. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001415226903077