Zobrazeno 1 - 10
of 103
pro vyhledávání: '"remote sensing image captioning"'
Publikováno v:
International Journal of Digital Earth, Vol 17, Iss 1 (2024)
ABSTRACTThe training of image captioning (IC) models requires a large number of caption-labeled samples, which is usually difficult to satisfy in the actual remote sensing scenarios. The performance of the models will be damaged due to the few-shot p
Externí odkaz:
https://doaj.org/article/b22f0d2726014ff098a5807b6dcb0be1
Publikováno v:
Remote Sensing, Vol 16, Iss 21, p 3987 (2024)
Recent Transformer-based works can generate high-quality captions for remote sensing images (RSIs). However, these methods generally feed global or grid visual features to a Transformer-based captioning model for associating cross-modal information,
Externí odkaz:
https://doaj.org/article/0ec844584a794a23ad6f31a13d854939
Publikováno v:
Remote Sensing, Vol 16, Iss 16, p 2961 (2024)
Pioneering remote sensing image captioning (RSIC) works use autoregressive decoding for fluent and coherent sentences but suffer from high latency and high computation costs. In contrast, non-autoregressive approaches improve inference speed by predi
Externí odkaz:
https://doaj.org/article/531bc0f3d10c4be5ac90c21d794010dd
Publikováno v:
International Journal of Applied Earth Observations and Geoinformation, Vol 127, Iss , Pp 103672- (2024)
Remote sensing image captioning (RSIC), an emerging field of cross-modal tasks, has become a popular research topic in recent years. Feature extraction underlies all RSIC tasks, with current tasks using grid features. Compared with grid features, reg
Externí odkaz:
https://doaj.org/article/eca56442822e4e1f8399846c502c366e
Publikováno v:
Remote Sensing, Vol 16, Iss 11, p 1843 (2024)
In the field of remote sensing image captioning (RSIC), mainstream methods typically adopt an encoder–decoder framework. Methods based on this framework often use only simple feature fusion strategies, failing to fully mine the fine-grained feature
Externí odkaz:
https://doaj.org/article/b5641bb8f8524eb3910c495bb4f8f6c5
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 16, Pp 7704-7717 (2023)
With the growth of remote sensing images, understanding image content automatically has attracted many researchers' interests in deep learning for remote sensing image. Inspired from the natural image captioning, the model with convolutional neural n
Externí odkaz:
https://doaj.org/article/36bdc25d7c4a4495b0ba97d0d0751c5a
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Rita Ramos, Bruno Martins
Publikováno v:
IEEE Access, Vol 10, Pp 24852-24863 (2022)
Remote sensing image captioning involves generating a concise textual description for an input aerial image. The task has received significant attention, and several recent proposals are based on neural encoder-decoder models. Most previous methods a
Externí odkaz:
https://doaj.org/article/387749269577415d981d6a65cd23ee81
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 15, Pp 2154-2165 (2022)
Much of the recent work in remote sensing image captioning is influenced by natural image captioning. These methods tend to fix the defects of the model architecture to improve the previous work, but pay little attention to the differences between re
Externí odkaz:
https://doaj.org/article/6ad623011fb04f2bbfd1a1f7ee79cdf0
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.