mlsanityData to 14 Oct 2026

Unpaired Image Captioning by Language Pivoting

arXiv 1803.05526 ↗First posted 14 Mar 2018cs.CVcited by 27

Not on the map. Why?

Abstract (arXiv)

Image captioning is a multimodal task involving computer vision and natural language processing, where the goal is to learn a mapping from the image to its natural language description. In general, the mapping function is learned from a training set of image-caption pairs. However, for some language, large scale image-caption paired corpus might not be available. We present an approach to this unpaired image captioning problem by language pivoting. Our method can effectively capture the characteristics of an image captioner from the pivot language (Chinese) and align it to the target language (English) using another pivot-target (Chinese-English) sentence parallel corpus. We evaluate our method on two image-to-English benchmark datasets: MSCOCO and Flickr30K. Quantitative comparisons against several baseline approaches demonstrate the effectiveness of our method.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 8; 2022: 7; 2023: 8; 2024: 2; 2025: 2.

27 papers.

Sort:

By area:

  1. 2021VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioningcited by 191
  2. 2021From Show to Tell: A Survey on Deep Learning-based Image Captioningcited by 138
  3. 2022VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMixcited by 45
  4. 2022Deep Learning Approaches on Image Captioning: A Reviewcited by 43
  5. 2021MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-based Image Captioningcited by 27
  6. 2023LMCap: Few-shot Multilingual Image Captioning by Retrieval Augmented Language Model Promptingcited by 17
  7. 2023Cross2StrA: Unpaired Cross-lingual Image Captioning with Cross-lingual Cross-modal Structure-pivoted Alignmentcited by 15
  8. 2021Removing Word-Level Spurious Alignment between Images and Pseudo-Captions in Unsupervised Image Captioningcited by 14
  9. 2022Aligning Source Visual and Target Language Domains for Unpaired Video Captioningcited by 14
  10. 2022CLEAR: Improving Vision-Language Navigation with Cross-Lingual, Environment-Agnostic Representationscited by 10
  11. 2023CgT-GAN: CLIP-guided Text GAN for Image Captioningcited by 10
  12. 2021Object-Centric Unsupervised Image Captioningcited by 9
15 more
  1. 2024MedRAT: Unpaired Medical Report Generation via Auxiliary Taskscited by 9
  2. 2022Unpaired Image Captioning by Image-level Weakly-Supervised Visual Concept Recognitioncited by 7
  3. 2021Exploring Semantic Relationships for Unpaired Image Captioningcited by 6
  4. 2023Multimodal Data Augmentation for Image Captioning using Diffusion Modelscited by 6
  5. 2021"Wikily" Supervised Neural Translation Tailored to Cross-Lingual Taskscited by 5
  6. 2025DescribeEarth: Describe Anything for Remote Sensing Imagescited by 5
  7. 2023Semi-Supervised Image Captioning by Adversarially Propagating Labeled Datacited by 4
  8. 2023ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language Generationcited by 4
  9. 2022Emergence of Machine Language: Towards Symbolic Intelligence with Neural Networkscited by 3
  10. 2022Multilingual Multimodality: A Taxonomical Survey of Datasets, Techniques, Challenges and Opportunitiescited by 1
  11. 2023Embedded Heterogeneous Attention Transformer for Cross-lingual Image Captioningcited by 1
  12. 2024Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysiscited by 1
  13. 2025Align Where the Words Look: Cross-Attention-Guided Patch Alignment with Contrastive and Transport Regularization for Bengali Captioningcited by 1
  14. 2021Experimenting with Self-Supervision using Rotation Prediction for Image Captioningcited by 0
  15. 2023KENGIC: KEyword-driven and N-Gram Graph based Image Captioningcited by 0