{"url":"/dataset/banglalekhaimagecaptions","name":"BanglaLekhaImageCaptions","full_name":null,"description_markdown":"This dataset consists of images and annotations in Bengali. The images are human annotated in Bengali by two adult native Bengali speakers. All popular image captioning datasets have a predominant western cultural bias with the annotations done in English. Using such datasets to train an image captioning system assumes that a good English to target language translation system exists and that the original dataset had elements of the target culture. Both these assumptions are false, leading to the need of a culturally relevant dataset in Bengali, to generate appropriate image captions of images relevant to the Bangladeshi and wider subcontinental context. The dataset presented consists of 9,154 images.","description_withheld":null,"homepage":"https://data.mendeley.com/datasets/rxxch9vw59/2","introduced_date":"2018-09-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/chittron-an-automatic-bangla-image-captioning","title":"Chittron: An Automatic Bangla Image Captioning System","first_author":"Motiur Rahman","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"}],"languages":[{"name":"Bengali","url":"/datasets/language/bengali"}],"variants":["BanglaLekhaImageCaptions"],"data_loaders":[],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-captioning-on-banglalekhaimagecaptions","task":"Image Captioning","dataset_variant":"BanglaLekhaImageCaptions","rows":1,"metrics":["BLEU-1","BLEU-2","BLEU-3","BLEU-4","CIDEr","METEOR","ROUGE-L","SPICE"],"first_row_in_archive_order":{"model":"CNN + 1D CNN","paper":"/paper/improved-bengali-image-captioning-via-deep","metrics":{"BLEU-1":"65.1","BLEU-2":"42.6","BLEU-3":"27.8","BLEU-4":"17.5","CIDEr":"57.2","METEOR":"29.7","ROUGE-L":"43.4","SPICE":"35.7"},"code_links":[{"title":"FaiyazKhan11/Improved-Bengali-Image-Captioning-via-deep-convolutional-neural-network-based-encoder-decoder-model","url":"https://github.com/FaiyazKhan11/Improved-Bengali-Image-Captioning-via-deep-convolutional-neural-network-based-encoder-decoder-model"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/improved-bengali-image-captioning-via-deep","title":"Improved Bengali Image Captioning via deep convolutional neural network based encoder-decoder model","date":"2021-02-14","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}