SCICAP

Dataset Information
Modalities
Images, Texts
Languages
English
Introduced
2021
License
CC0 1.0
Homepage
Official Website
Contents

Overview

SCICAP is a large-scale image captioning dataset that contains real-world scientific figures and captions. SCICAP was constructed using more than two million images from over 290,000 papers collected and released by arXiv.

Image source: https://arxiv.org/pdf/2110.11624v1.pdf

Variants: SCICAP

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
Image Captioning CNN+LSTM (Vision only, First sentence) SciCap: Generating Captions for Scientific … 2021-10-22
Image Captioning CNN+LSTM (Text only, First sentence) SciCap: Generating Captions for Scientific … 2021-10-22
Image Captioning CNN+LSTM (Text only, Single-Sent Caption) SciCap: Generating Captions for Scientific … 2021-10-22
Image Captioning CNN+LSTM (Vision only, Single-Sent Caption) SciCap: Generating Captions for Scientific … 2021-10-22
Image Captioning CNN+LSTM (Vision + Text, First sentence) SciCap: Generating Captions for Scientific … 2021-10-22
Image Captioning CNN+LSTM (Vision + Text, Single-Sent Caption) SciCap: Generating Captions for Scientific … 2021-10-22
Image Captioning CNN+LSTM (Vision only, Caption w/ <=100 words) SciCap: Generating Captions for Scientific … 2021-10-22
Image Captioning CNN+LSTM (Vision + Text, Caption w/ <=100 words) SciCap: Generating Captions for Scientific … 2021-10-22
Image Captioning CNN+LSTM (Text only, Caption w/ <=100 words) SciCap: Generating Captions for Scientific … 2021-10-22

Research Papers

Recent papers with results on this dataset:

External Links: