FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313021481> ?p ?o ?g. }

• W4313021481 endingPage "20" @default.
• W4313021481 startingPage "1" @default.
• W4313021481 abstract "Analyzing land cover changes with multi-temporal remote sensing (RS) images is crucial for environmental protection and land planning. In this paper, we explore Remote Sensing Image Change Captioning (RSICC), a new task aiming at generating human-like language descriptions for the land cover changes in multi-temporal RS images. We propose a novel Transformer-based RSICC model (RSICCformer). It consists of three main components: 1) a CNN-based feature extractor to generate high-level features of RS image pairs, 2) a dual-branch Transformer encoder to improve the feature discrimination capacity for the changes, and 3) a caption decoder to generate sentences describing the differences. The dual-branch Transformer encoder consists of a hierarchy of processing stages to capture and recognize multiple changes of interest. Concretely, we use the bi-temporal feature differences as keys to enhance image features (queries) from each temporal image in the dual-branch Transformer encoder. To explore the RSICC task, we build a large-scale dataset named LEVIR-CC, which contains 10077 pairs of bi-temporal RS images and 50385 sentences describing the differences between images. We benchmark existing state-of-the-art synthetic image change captioning methods on the LEVIR-CC dataset, and our RSICCformer outperforms previous methods with a significant margin (+4.98% on BLEU-4 and +9.86% on CIDEr-D). The attention visualization results also suggest that our model can focus on changes of interest and ignore irrelevant changes." @default.
• W4313021481 created "2023-01-05" @default.
• W4313021481 creator A5010194873 @default.
• W4313021481 creator A5058849690 @default.
• W4313021481 creator A5059677848 @default.
• W4313021481 creator A5078304976 @default.
• W4313021481 creator A5088611151 @default.
• W4313021481 date "2022-01-01" @default.
• W4313021481 modified "2023-10-18" @default.
• W4313021481 title "Remote Sensing Image Change Captioning With Dual-Branch Transformers: A New Method and a Large Scale Dataset" @default.
• W4313021481 cites W1897761818 @default.
• W4313021481 cites W1956340063 @default.
• W4313021481 cites W1963949604 @default.
• W4313021481 cites W1969616664 @default.
• W4313021481 cites W1979061792 @default.
• W4313021481 cites W1980965483 @default.
• W4313021481 cites W1998595580 @default.
• W4313021481 cites W2006383776 @default.
• W4313021481 cites W2009175701 @default.
• W4313021481 cites W2048104909 @default.
• W4313021481 cites W2064675550 @default.
• W4313021481 cites W2085289201 @default.
• W4313021481 cites W2098594213 @default.
• W4313021481 cites W2101105183 @default.
• W4313021481 cites W2108598243 @default.
• W4313021481 cites W2131170350 @default.
• W4313021481 cites W2131228247 @default.
• W4313021481 cites W2133512280 @default.
• W4313021481 cites W2144552105 @default.
• W4313021481 cites W2149298154 @default.
• W4313021481 cites W2169386254 @default.
• W4313021481 cites W2194775991 @default.
• W4313021481 cites W2317688867 @default.
• W4313021481 cites W2510520237 @default.
• W4313021481 cites W2524665608 @default.
• W4313021481 cites W2561715562 @default.
• W4313021481 cites W2603566245 @default.
• W4313021481 cites W2627081599 @default.
• W4313021481 cites W2751993439 @default.
• W4313021481 cites W2758162718 @default.
• W4313021481 cites W2760327630 @default.
• W4313021481 cites W2794488615 @default.
• W4313021481 cites W2911584214 @default.
• W4313021481 cites W2951991161 @default.
• W4313021481 cites W2964196083 @default.
• W4313021481 cites W2965487241 @default.
• W4313021481 cites W2988981892 @default.
• W4313021481 cites W2992323514 @default.
• W4313021481 cites W2995904231 @default.
• W4313021481 cites W2997043451 @default.
• W4313021481 cites W3004423752 @default.
• W4313021481 cites W3006487741 @default.
• W4313021481 cites W3009942016 @default.
• W4313021481 cites W3011156941 @default.
• W4313021481 cites W3011916860 @default.
• W4313021481 cites W3027201985 @default.
• W4313021481 cites W3027225766 @default.
• W4313021481 cites W3036594286 @default.
• W4313021481 cites W3037640242 @default.
• W4313021481 cites W3046675509 @default.
• W4313021481 cites W3089472875 @default.
• W4313021481 cites W3089915566 @default.
• W4313021481 cites W3099167317 @default.
• W4313021481 cites W3100245404 @default.
• W4313021481 cites W3102516861 @default.
• W4313021481 cites W3108170342 @default.
• W4313021481 cites W3117344638 @default.
• W4313021481 cites W3118142692 @default.
• W4313021481 cites W3120467244 @default.
• W4313021481 cites W3138516171 @default.
• W4313021481 cites W3139912591 @default.
• W4313021481 cites W3140300848 @default.
• W4313021481 cites W3154766321 @default.
• W4313021481 cites W3157772069 @default.
• W4313021481 cites W3175933895 @default.
• W4313021481 cites W3176470992 @default.
• W4313021481 cites W3186032668 @default.
• W4313021481 cites W3194015448 @default.
• W4313021481 cites W3196922338 @default.
• W4313021481 cites W3203526456 @default.
• W4313021481 cites W3206617243 @default.
• W4313021481 cites W3207627484 @default.
• W4313021481 cites W3213119051 @default.
• W4313021481 cites W3214719104 @default.
• W4313021481 cites W3216130706 @default.
• W4313021481 cites W4206028074 @default.
• W4313021481 cites W4206111836 @default.
• W4313021481 cites W4211112734 @default.
• W4313021481 cites W4213449032 @default.
• W4313021481 cites W4213455776 @default.
• W4313021481 cites W4226228401 @default.
• W4313021481 cites W4285744637 @default.
• W4313021481 cites W4289537913 @default.
• W4313021481 cites W4293508747 @default.
• W4313021481 cites W62621907 @default.
• W4313021481 doi "https://doi.org/10.1109/tgrs.2022.3218921" @default.
• W4313021481 hasPublicationYear "2022" @default.
• W4313021481 type Work @default.

• next