Litcius/Paper detail

Scene Attention Mechanism for Remote Sensing Image Caption Generation

Shiqi Wu, Xiangrong Zhang, Xin Wang, Chen Li, Licheng Jiao

202032 citationsDOI

Abstract

Remote sensing images play an important role in various applications. To make it easier for humans to understand remote sensing images, the task of remote sensing image captioning attracts more and more researchers' attention. Inspired from the way human receives visual information, attention mechanism has been widely used in remote sensing image understanding. To catch more scene information and improve the stability of the generated sentences, a new attention mechanism called scene attention is proposed. Except for the current attention via the current hidden state of the long shortterm memory network (LSTM), our proposed method simultaneously explores the global visual information from the mean feature of all convolutional features. The effectiveness of the proposed method is evaluated on UCM-captions, Sydney-captions and RSICD datasets. The results of our experiment show that comparing with some other captioning methods, our method is more stable and obtains a better performance.

Topics & Concepts

Closed captioningComputer scienceFeature (linguistics)Artificial intelligenceImage (mathematics)Convolutional neural networkTask (project management)Mechanism (biology)Computer visionFeature extractionVisualizationLinguisticsPhilosophyEconomicsManagementEpistemologyMultimodal Machine Learning ApplicationsAdvanced Image and Video Retrieval TechniquesDomain Adaptation and Few-Shot Learning
Scene Attention Mechanism for Remote Sensing Image Caption Generation | Litcius