# Learning Visual Relation Priors for Image-Text Matching and Image Captioning with Neural Scene Graph Generators

arXiv: https://arxiv.org/abs/1909.09953 · HTML: https://mlsanity.com/paper/1909.09953/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Sep 2019.

## Built on by (most cited first, 13 of 13)

- [A Comprehensive Survey of Scene Graphs: Generation and Application](https://mlsanity.com/paper/2104.01111/) (2021)
- [RelTR: Relation Transformer for Scene Graph Generation](https://mlsanity.com/paper/2201.11460/) (2022)
- [LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval](https://mlsanity.com/paper/2103.08784/) (2021)
- [Deep Learning Approaches on Image Captioning: A Review](https://mlsanity.com/paper/2201.12944/) (2022)
- [In Defense of Scene Graphs for Image Captioning](https://mlsanity.com/paper/2102.04990/) (2021)
- [Parts2Words: Learning Joint Embedding of Point Clouds and Texts by Bidirectional Matching between Parts and Words](https://mlsanity.com/paper/2107.01872/) (2021)
- [Plug-and-Play Regulators for Image-Text Matching](https://mlsanity.com/paper/2303.13371/) (2023)
- [Tackling Vision Language Tasks Through Learning Inner Monologues](https://mlsanity.com/paper/2308.09970/) (2023)
- [ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval](https://mlsanity.com/paper/2207.14757/) (2022)
- [Towards Efficient Cross-Modal Visual Textual Retrieval using Transformer-Encoder Deep Features](https://mlsanity.com/paper/2106.00358/) (2021)
- [HiVLP: Hierarchical Vision-Language Pre-Training for Fast Image-Text Retrieval](https://mlsanity.com/paper/2205.12105/) (2022)
- [Composed Multi-modal Retrieval: A Survey of Approaches and Applications](https://mlsanity.com/paper/2503.01334/) (2025)
- [Efficient Image-Text Retrieval via Keyword-Guided Pre-Screening](https://mlsanity.com/paper/2303.07740/) (2023)

## Abstract (arXiv)

Grounding language to visual relations is critical to various language-and-vision applications. In this work, we tackle two fundamental language-and-vision tasks: image-text matching and image captioning, and demonstrate that neural scene graph generators can learn effective visual relation features to facilitate grounding language to visual relations and subsequently improve the two end applications. By combining relation features with the state-of-the-art models, our experiments show significant improvement on the standard Flickr30K and MSCOCO benchmarks. Our experimental results and analysis show that relation features improve downstream models' capability of capturing visual relations in end vision-and-language applications. We also demonstrate the importance of learning scene graph generators with visually relevant relations to the effectiveness of relation features.