mlsanityData to 7 Oct 2026

STAIR Captions: Constructing a Large-Scale Japanese Image Caption Dataset

arXiv 1705.00823 ↗First posted 2 May 2017cs.CL cs.CVcited by 47

Not on the map. Why?

Abstract (arXiv)

In recent years, automatic generation of image descriptions (captions), that is, image captioning, has attracted a great deal of attention. In this paper, we particularly consider generating Japanese captions for images. Since most available caption datasets have been constructed for English language, there are few datasets for Japanese. To tackle this problem, we construct a large-scale Japanese image caption dataset based on images from MS-COCO, which is called STAIR Captions. STAIR Captions consists of 820,310 Japanese captions for 164,062 images. In the experiment, we show that a neural network trained using STAIR Captions can generate more natural and better Japanese captions, compared to those generated using English-Japanese machine translation after generating English captions.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 8; 2023: 9; 2024: 11; 2025: 7; 2026: 1.

47 papers.

Sort:

By area:

  1. 2021Visually Grounded Reasoning across Languages and Culturescited by 188
  2. 2023Document Understanding Dataset and Evaluation (DUDE)cited by 132
  3. 2021UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-trainingcited by 64
  4. 2022IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languagescited by 54
  5. 2021LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrievalcited by 44
  6. 2021Grounding 'Grounding' in NLPcited by 44
  7. 2021MURAL: Multimodal, Multitask Retrieval Across Languagescited by 44
  8. 2021Visually grounded models of spoken language: A survey of datasets, architectures and evaluation techniquescited by 32
  9. 2022Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-trainingcited by 24
  10. 2023NLLB-CLIP -- train performant multilingual image retrieval model on a budgetcited by 24
  11. 2024No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languagescited by 19
  12. 2022Recent Advances in Neural Text Generation: A Task-Agnostic Surveycited by 14
35 more
  1. 2023Universal Multimodal Representation for Language Understandingcited by 14
  2. 2024Multimodal LLM Enhanced Cross-lingual Cross-modal Retrievalcited by 13
  3. 2023Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representationscited by 11
  4. 2023CL2CM: Improving Cross-Lingual Cross-Modal Retrieval via Cross-Lingual Knowledge Transfercited by 10
  5. 2022MaXM: Towards Multilingual Visual Question Answeringcited by 9
  6. 2022X2-VLM: All-In-One Pre-trained Model For Vision-Language Taskscited by 9
  7. 2023Semantic and Expressive Variation in Image Captions Across Languagescited by 8
  8. 2024mOSCAR: A Large-scale Multilingual and Multimodal Document-level Corpuscited by 8
  9. 2024CVLUE: A New Benchmark Dataset for Chinese Vision-Language Understanding Evaluationcited by 8
  10. 2021Egocentric Image Captioning for Privacy-Preserved Passive Dietary Intake Monitoringcited by 7
  11. 2024A Gaze-grounded Visual Question Answering Dataset for Clarifying Ambiguous Japanese Questionscited by 7
  12. 2021Improved Bengali Image Captioning via deep convolutional neural network based encoder-decoder modelcited by 6
  13. 2023JaSPICE: Automatic Evaluation Metric Using Predicate-Argument Structures for Image Captioning Modelscited by 6
  14. 2021Bornon: Bengali Image Captioning with Transformer-based Deep learning approachcited by 5
  15. 2024Cross-Lingual and Cross-Cultural Variation in Image Descriptionscited by 5
  16. 2024Quantifying the Gaps Between Translation and Native Perception in Training for Multimodal, Multilingual Retrievalcited by 5
  17. 2021Towards Zero-shot Cross-lingual Image Retrieval and Taggingcited by 4
  18. 2025MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMscited by 4
  19. 2025Competition and Attraction Improve Model Fusioncited by 4
  20. 2022Generalizing Multimodal Pre-training into Multilingual via Language Acquisitioncited by 3
  21. 2022GLAMI-1M: A Multilingual Image-Text Fashion Datasetcited by 3
  22. 2023A Large-Scale Multilingual Study of Visual Constraints on Linguistic Selection of Descriptionscited by 2
  23. 2024FoodMLLM-JP: Leveraging Multimodal Large Language Models for Japanese Recipe Generationcited by 2
  24. 2022Multilingual Multimodality: A Taxonomical Survey of Datasets, Techniques, Challenges and Opportunitiescited by 1
  25. 2024KTVIC: A Vietnamese Image Captioning Dataset on the Life Domaincited by 1
  26. 2024Improving the Consistency in Cross-Lingual Cross-Modal Retrieval with 1-to-K Contrastive Learningcited by 1
  27. 2025A Multimodal Recaptioning Framework to Account for Perceptual Diversity Across Languages in Vision-Language Modelingcited by 1
  28. 2025Multilingual Vision-Language Models, A Surveycited by 1
  29. 2025DEJIMA: A Novel Large-scale Japanese Dataset for Image Captioning and Visual Question Answeringcited by 1
  30. 2021Backretrieval: An Image-Pivoted Evaluation Metric for Cross-Lingual Text Representations Without Parallel Corporacited by 0
  31. 2023Accountable Textual-Visual Chat Learns to Reject Human Instructions in Image Re-creationcited by 0
  32. 2024Image captioning in different languagescited by 0
  33. 2025A Benchmark for Multi-Lingual Vision-Language Learning in Remote Sensing Image Captioningcited by 0
  34. 2025Pre-Trained CNN Architecture for Transformer-Based Image Caption Generation Modelcited by 0
  35. 2026Multilingual-To-Multimodal (M2M): Unlocking New Languages with Monolingual Textcited by 0