mlsanityData to 14 Oct 2026

AFRICAPTION: Establishing a New Paradigm for Image Captioning in African Languages

arXiv 2510.17405 ↗First posted 20 Oct 2025cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Multimodal AI research has overwhelmingly focused on high-resource languages, hindering the democratization of advancements in the field. To address this, we present AfriCaption, a comprehensive framework for multilingual image captioning in 20 African languages and our contributions are threefold: (i) a curated dataset built on Flickr8k, featuring semantically aligned captions generated via a context-aware selection and translation process; (ii) a dynamic, context-preserving pipeline that ensures ongoing quality through model ensembling and adaptive substitution; and (iii) the AfriCaption model, a 0.5B parameter vision-to-text architecture that integrates SigLIP and NLLB200 for caption generation across under-represented languages. This unified framework ensures ongoing data quality and establishes the first scalable image-captioning resource for under-represented African languages, laying the groundwork for truly inclusive multimodal AI.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 40 references that are in the map. First posted on arXiv 20 Oct 2025.

Builds on

23 of 40 references.

References · 23

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  6. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  7. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  8. 2018Datasheets for Datasetscited by 1,386
  9. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,312
  10. 2024The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scalecited by 1,160
  11. 2020Language-agnostic BERT Sentence Embeddingcited by 627
  12. 2020Beyond English-Centric Multilingual Machine Translationcited by 561
11 more
  1. 2021WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learningcited by 287
  2. 2016Multi30K: Multilingual English-German Image Descriptionscited by 250
  3. 2019CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEBcited by 177
  4. 2019CCAligned: A Massive Collection of Cross-Lingual Web-Document Pairscited by 136
  5. 2022Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Datasetcited by 100
  6. 2023Image Captioners Are Scalable Vision Learners Toocited by 89
  7. 2018COCO-CN for Cross-Lingual Image Tagging, Captioning and Retrievalcited by 80
  8. 2020Crisscrossed Captions: Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCOcited by 46
  9. 2019Translationese in Machine Translation Evaluationcited by 38
  10. 2024LocCa: Visual Pretraining with Location-aware Captionerscited by 35
  11. 2024No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languagescited by 19

Built on by

Not cited yet.