# Semantic and Expressive Variation in Image Captions Across Languages

arXiv: https://arxiv.org/abs/2310.14356 · HTML: https://mlsanity.com/paper/2310.14356/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 60 of its 130 references that are in the map.
- First posted on arXiv 22 Oct 2023.

## Builds on (most cited first, 30 of 60)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization](https://mlsanity.com/paper/2003.11080/) (2020)
- [GIT: A Generative Image-to-text Transformer for Vision and Language](https://mlsanity.com/paper/2205.14100/) (2022)
- [What you can cram into a single vector: Probing sentence embeddings for linguistic properties](https://mlsanity.com/paper/1805.01070/) (2018)
- [Measuring Robustness to Natural Distribution Shifts in Image Classification](https://mlsanity.com/paper/2007.00644/) (2020)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding](https://mlsanity.com/paper/2010.07954/) (2020)
- [Snorkel: Rapid Training Data Creation with Weak Supervision](https://mlsanity.com/paper/1711.10160/) (2017)
- [Evaluation of Text Generation: A Survey](https://mlsanity.com/paper/2006.14799/) (2020)
- [Action Genome: Actions as Composition of Spatio-temporal Scene Graphs](https://mlsanity.com/paper/1912.06992/) (2019)
- [Visually Grounded Reasoning across Languages and Cultures](https://mlsanity.com/paper/2109.13238/) (2021)
- [Emerging Cross-lingual Structure in Pretrained Language Models](https://mlsanity.com/paper/1911.01464/) (2019)
- [Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine](https://mlsanity.com/paper/2301.08745/) (2023)
- [Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis](https://mlsanity.com/paper/2304.04675/) (2023)
- [Algorithmic Monoculture and Social Welfare](https://mlsanity.com/paper/2101.05853/) (2021)
- [Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset](https://mlsanity.com/paper/2205.12522/) (2022)
- ["This is my unicorn, Fluffy": Personalizing frozen vision-language representations](https://mlsanity.com/paper/2204.01694/) (2022)

## Built on by (most cited first, 8 of 8)

- [Exploring Visual Culture Awareness in GPT-4V: A Comprehensive Probing](https://mlsanity.com/paper/2402.06015/) (2024)
- [Vision-Language Models under Cultural and Inclusive Considerations](https://mlsanity.com/paper/2407.06177/) (2024)
- [Multi3Hate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision-Language Models](https://mlsanity.com/paper/2411.03888/) (2024)
- [No Detail Left Behind: Revisiting Self-Retrieval for Fine-Grained Image Captioning](https://mlsanity.com/paper/2409.03025/) (2024)
- [World in a Frame: Understanding Culture Mixing as a New Challenge for Vision-Language Models](https://mlsanity.com/paper/2511.22787/) (2025)
- [A Grounded Typology of Word Classes](https://mlsanity.com/paper/2412.10369/) (2024)
- [Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning](https://mlsanity.com/paper/2602.23351/) (2026)
- [Interrogating Design Homogenization in Web Vibe Coding](https://mlsanity.com/paper/2603.13036/) (2026)

## Abstract (arXiv)

Computer vision often treats human perception as homogeneous: an implicit assumption that visual stimuli are perceived similarly by everyone. This assumption is reflected in the way researchers collect datasets and train vision models. By contrast, literature in cross-cultural psychology and linguistics has provided evidence that people from different cultural backgrounds observe vastly different concepts even when viewing the same visual stimuli. In this paper, we study how these differences manifest themselves in vision-language datasets and models, using language as a proxy for culture. By comparing textual descriptions generated across 7 languages for the same images, we find significant differences in the semantic content and linguistic expression. When datasets are multilingual as opposed to monolingual, descriptions have higher semantic coverage on average, where coverage is measured using scene graphs, model embeddings, and linguistic taxonomies. For example, multilingual descriptions have on average 29.9% more objects, 24.5% more relations, and 46.0% more attributes than a set of monolingual captions. When prompted to describe images in different languages, popular models (e.g. LLaVA) inherit this bias and describe different parts of the image. Moreover, finetuning models on captions from one language performs best on corresponding test data from that language, while finetuning on multilingual data performs consistently well across all test data compositions. Our work points towards the need to account for and embrace the diversity of human perception in the computer vision community.