An image speaks a thousand words, but can everyone listen? On image transcreation for cultural relevance

• URL: http://arxiv.org/abs/2404.01247v3
• Date: Wed, 19 Jun 2024 18:07:19 GMT
• Title: An image speaks a thousand words, but can everyone listen? On image transcreation for cultural relevance
• Authors: Simran Khanuja, Sathyanarayanan Ramamoorthy, Yueqi Song, Graham Neubig,
• Abstract summary: We take a first step towards translating images to make them culturally relevant. We build three pipelines comprising state-of-the-art generative models to do the task. We conduct a human evaluation of translated images to assess for cultural relevance and meaning preservation.
• Score: 53.974497865647336
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Given the rise of multimedia content, human translators increasingly focus on culturally adapting not only words but also other modalities such as images to convey the same meaning. While several applications stand to benefit from this, machine translation systems remain confined to dealing with language in speech and text. In this work, we take a first step towards translating images to make them culturally relevant. First, we build three pipelines comprising state-of-the-art generative models to do the task. Next, we build a two-part evaluation dataset: i) concept: comprising 600 images that are cross-culturally coherent, focusing on a single concept per image, and ii) application: comprising 100 images curated from real-world applications. We conduct a multi-faceted human evaluation of translated images to assess for cultural relevance and meaning preservation. We find that as of today, image-editing models fail at this task, but can be improved by leveraging LLMs and retrievers in the loop. Best pipelines can only translate 5% of images for some countries in the easier concept dataset and no translation is successful for some countries in the application dataset, highlighting the challenging nature of the task. Our code and data is released here: https://github.com/simran-khanuja/image-transcreation.

Related papers

• Multilingual Diversity Improves Vision-Language Representations [66.41030381363244]
  Pre-training on this dataset outperforms using English-only or English-dominated datasets on ImageNet. On a geographically diverse task like GeoDE, we also observe improvements across all regions, with the biggest gain coming from Africa.
  arXiv  Detail & Related papers  (2024-05-27T08:08:51Z)
• NewsStories: Illustrating articles with visual summaries [49.924916589209374]
  We introduce a large-scale multimodal dataset containing over 31M articles, 22M images and 1M videos. We show that state-of-the-art image-text alignment methods are not robust to longer narratives with multiple images. We introduce an intuitive baseline that outperforms these methods on zero-shot image-set retrieval by 10% on the GoodNews dataset.
  arXiv  Detail & Related papers  (2022-07-26T17:34:11Z)
• Multimodal Neural Machine Translation with Search Engine Based Image Retrieval [4.662583832063716]
  We propose an open-vocabulary image retrieval method to collect descriptive images for bilingual parallel corpus. Our proposed method achieves significant improvements over strong baselines.
  arXiv  Detail & Related papers  (2022-07-26T08:42:06Z)
• On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization [89.94078728495423]
  We show that recent advances in each modality, CLIP image representations and scaling of language models, do not consistently improve multimodal self-rationalization of tasks with multimodal inputs. Our findings call for a backbone modelling approach that can be built on to advance text generation from images and text beyond image captioning.
  arXiv  Detail & Related papers  (2022-05-24T00:52:40Z)
• Visually Grounded Reasoning across Languages and Cultures [27.31020761908739]
  We develop a new protocol to construct an ImageNet-style hierarchy representative of more languages and cultures. We focus on a typologically diverse set of languages, namely, Indonesian, Mandarin Chinese, Swahili, Tamil, and Turkish. We create a multilingual dataset for Multicultural Reasoning over Vision and Language (MaRVL) by eliciting statements from native speaker annotators about pairs of images.
  arXiv  Detail & Related papers  (2021-09-28T16:51:38Z)
• Exploiting BERT For Multimodal Target SentimentClassification Through Input Space Translation [75.82110684355979]
  We introduce a two-stream model that translates images in input space using an object-aware transformer. We then leverage the translation to construct an auxiliary sentence that provides multimodal information to a language model. We achieve state-of-the-art performance on two multimodal Twitter datasets.
  arXiv  Detail & Related papers  (2021-08-03T18:02:38Z)
• TextMage: The Automated Bangla Caption Generator Based On Deep Learning [1.2330326247154968]
  TextMage is a system that is capable of understanding visual scenes that belong to the Bangladeshi geographical context. This dataset contains 9,154 images along with two annotations for each image.
  arXiv  Detail & Related papers  (2020-10-15T23:24:15Z)
• Semi-supervised Learning for Few-shot Image-to-Image Translation [89.48165936436183]
  We propose a semi-supervised method for few-shot image translation, called SEMIT. Our method achieves excellent results on four different datasets using as little as 10% of the source labels.
  arXiv  Detail & Related papers  (2020-03-30T22:46:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.