Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387245802> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4387245802 abstract "<p>Remote sensing image change captioning (RSICC) is a novel task that aims to describe the differences between bi-temporal images by natural language. Previous methods ignore a significant specificity of the task: the difficulty of RSICC is different for unchanged and changed image pairs. They process the unchanged and changed image pairs in a coupled way, which usually causes confusion for change captioning. In this paper, we decouple the task into two issues to ease it: whether and what changes have occurred. An image-level classifier performs binary classification to address the first issue. A feature-level encoder contributes to extracting discriminative features to help the caption generation module address the second issue. For caption generation, we utilize prompt learning to introduce pre-trained large language models (LLMs) into the RSICC task. A multi-prompt learning strategy is proposed to generate a set of unified prompts and a class-specific prompt conditioned on the image-level classifier's results. It can prompt a pre-trained LLM to know whether changes exist and generate captions. Finally, the multiple prompts and the features of the feature-level encoder are fed into a frozen LLM for captioning. Compared with previous methods, our method can leverage the powerful abilities of the pre-trained LLM in language to generate plausible captions, which is free of training. Extensive experiments show that our method is effective and achieves state-of-the-art performance. Besides, an additional experiment demonstrates that our decoupling paradigm is more promising than the previous coupled paradigm for the RSICC task. We will make our codebase publicly available to facilitate future research at https://github.com/Chen-Yang-Liu/PromptCC</p>" @default.
- W4387245802 created "2023-10-03" @default.
- W4387245802 creator A5015773637 @default.
- W4387245802 creator A5058849690 @default.
- W4387245802 creator A5059677848 @default.
- W4387245802 creator A5078304976 @default.
- W4387245802 creator A5081214225 @default.
- W4387245802 creator A5088611151 @default.
- W4387245802 date "2023-10-02" @default.
- W4387245802 modified "2023-10-03" @default.
- W4387245802 title "A Decoupling Paradigm with Prompt Learning for Remote Sensing Image Change Captioning" @default.
- W4387245802 doi "https://doi.org/10.36227/techrxiv.23269310.v2" @default.
- W4387245802 hasPublicationYear "2023" @default.
- W4387245802 type Work @default.
- W4387245802 citedByCount "0" @default.
- W4387245802 crossrefType "posted-content" @default.
- W4387245802 hasAuthorship W4387245802A5015773637 @default.
- W4387245802 hasAuthorship W4387245802A5058849690 @default.
- W4387245802 hasAuthorship W4387245802A5059677848 @default.
- W4387245802 hasAuthorship W4387245802A5078304976 @default.
- W4387245802 hasAuthorship W4387245802A5081214225 @default.
- W4387245802 hasAuthorship W4387245802A5088611151 @default.
- W4387245802 hasBestOaLocation W43872458021 @default.
- W4387245802 hasConcept C101738243 @default.
- W4387245802 hasConcept C108583219 @default.
- W4387245802 hasConcept C111919701 @default.
- W4387245802 hasConcept C115961682 @default.
- W4387245802 hasConcept C118505674 @default.
- W4387245802 hasConcept C119857082 @default.
- W4387245802 hasConcept C153180895 @default.
- W4387245802 hasConcept C154945302 @default.
- W4387245802 hasConcept C157657479 @default.
- W4387245802 hasConcept C204321447 @default.
- W4387245802 hasConcept C28490314 @default.
- W4387245802 hasConcept C41008148 @default.
- W4387245802 hasConcept C95623464 @default.
- W4387245802 hasConcept C97931131 @default.
- W4387245802 hasConceptScore W4387245802C101738243 @default.
- W4387245802 hasConceptScore W4387245802C108583219 @default.
- W4387245802 hasConceptScore W4387245802C111919701 @default.
- W4387245802 hasConceptScore W4387245802C115961682 @default.
- W4387245802 hasConceptScore W4387245802C118505674 @default.
- W4387245802 hasConceptScore W4387245802C119857082 @default.
- W4387245802 hasConceptScore W4387245802C153180895 @default.
- W4387245802 hasConceptScore W4387245802C154945302 @default.
- W4387245802 hasConceptScore W4387245802C157657479 @default.
- W4387245802 hasConceptScore W4387245802C204321447 @default.
- W4387245802 hasConceptScore W4387245802C28490314 @default.
- W4387245802 hasConceptScore W4387245802C41008148 @default.
- W4387245802 hasConceptScore W4387245802C95623464 @default.
- W4387245802 hasConceptScore W4387245802C97931131 @default.
- W4387245802 hasLocation W43872458021 @default.
- W4387245802 hasOpenAccess W4387245802 @default.
- W4387245802 hasPrimaryLocation W43872458021 @default.
- W4387245802 hasRelatedWork W2024160000 @default.
- W4387245802 hasRelatedWork W2061273563 @default.
- W4387245802 hasRelatedWork W2292254049 @default.
- W4387245802 hasRelatedWork W2547835662 @default.
- W4387245802 hasRelatedWork W2729514902 @default.
- W4387245802 hasRelatedWork W2773500201 @default.
- W4387245802 hasRelatedWork W2897995864 @default.
- W4387245802 hasRelatedWork W2998168123 @default.
- W4387245802 hasRelatedWork W4287995534 @default.
- W4387245802 hasRelatedWork W4321789545 @default.
- W4387245802 isParatext "false" @default.
- W4387245802 isRetracted "false" @default.
- W4387245802 workType "article" @default.