Dataset Open Access

RSVQAxBEN

Sylvain Lobry; Begüm Demir; Devis Tuia

Visual Question Answering is a new task that can facilitate the extraction of information from images through textual queries: it aims at answering an open-ended question formulated in natural language about a given image. In this work, we introduce a new dataset to tackle the task of visual question answering on remote sensing images: this large-scale, open access dataset extracts image/question/answer triplets from the BigEarthNet dataset.This new dataset contains close to 15 millions samples and is openly available

With data splits
Files (28.6 GB)
Name Size
Images.zip
md5:70fe678b081aa2f01bb2624947d1e425
16.0 GB Download
LRBENanswers.json
md5:b23ded7e7c2d65f93c516a0ac2c6b64b
2.0 GB Download
LRBENimages.json
md5:018759f6c65f588272c3b667316c0a46
298.9 MB Download
LRBENpeople.json
md5:8024e13d1fbd50fab0e9e0f9cfbca98f
277.6 MB Download
LRBENquestions.json
md5:971fcd999e29555818c1a8262e8756a4
3.2 GB Download
RSVQAxBEN_split_test_answers.json
md5:cbf605f6ff30f8a624a7ff7ef2216cf1
790.7 MB Download
RSVQAxBEN_split_test_images.json
md5:73df473db7f7dd01fb96a9a4f3bfd04c
75.0 MB Download
RSVQAxBEN_split_test_questions.json
md5:0ccc69b08253297896fb05362581dfd3
1.0 GB Download
RSVQAxBEN_split_train_answers.json
md5:4fd72603d0b7f14543ab51ea88a862c7
1.3 GB Download
RSVQAxBEN_split_train_images.json
md5:2b5c686d1badd71fa93f1ffeb8e5bec7
182.2 MB Download
RSVQAxBEN_split_train_questions.json
md5:fd00fe8270ee2749d0f797ecb35fce53
2.1 GB Download
RSVQAxBEN_split_val_answers.json
md5:d49d19210e139073d8166d5c9388c847
633.7 MB Download
RSVQAxBEN_split_val_images.json
md5:22ce9734fef57828432250bba080946c
46.5 MB Download
RSVQAxBEN_split_val_questions.json
md5:1a74962446dafaa089d39b6d308f8a5f
756.1 MB Download
146
1,313
views
downloads
All versions This version
Views 146132
Downloads 1,3131,312
Data volume 18.1 TB18.1 TB
Unique views 127120
Unique downloads 312311

Share

Cite as