# Generating captions without looking beyond objects

arXiv: https://arxiv.org/abs/1610.03708 · HTML: https://mlsanity.com/paper/1610.03708/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Oct 2016.

## Built on by (most cited first, 3 of 3)

- [On the Foundations of Shortcut Learning](https://mlsanity.com/paper/2310.16228/) (2023)
- [Towards Scalable Physically Consistent Neural Networks: an Application to Data-driven Multi-zone Thermal Building Models](https://mlsanity.com/paper/2212.12380/) (2022)
- [Towards Real-world Debiasing: Rethinking Evaluation, Challenge, and Solution](https://mlsanity.com/paper/2405.15240/) (2024)

## Abstract (arXiv)

This paper explores new evaluation perspectives for image captioning and introduces a noun translation task that achieves comparative image caption generation performance by translating from a set of nouns to captions. This implies that in image captioning, all word categories other than nouns can be evoked by a powerful language model without sacrificing performance on n-gram precision. The paper also investigates lower and upper bounds of how much individual word categories in the captions contribute to the final BLEU score. A large possible improvement exists for nouns, verbs, and prepositions.