# Unifying Two-Stream Encoders with Transformers for Cross-Modal Retrieval

arXiv: https://arxiv.org/abs/2308.04343 · HTML: https://mlsanity.com/paper/2308.04343/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 77 references that are in the map.
- First posted on arXiv 8 Aug 2023.

## Builds on (most cited first, 30 of 41)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [End-to-End Video Instance Segmentation with Transformers](https://mlsanity.com/paper/2011.14503/) (2020)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning](https://mlsanity.com/paper/2012.15409/) (2020)
- [End-to-End Dense Video Captioning with Masked Transformer](https://mlsanity.com/paper/1804.00819/) (2018)
- [Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models](https://mlsanity.com/paper/1411.2539/) (2014)
- [Visual Semantic Reasoning for Image-Text Matching](https://mlsanity.com/paper/1909.02701/) (2019)
- [BEVT: BERT Pretraining of Video Transformers](https://mlsanity.com/paper/2112.01529/) (2021)
- [Dual-Path Convolutional Image-Text Embeddings with Instance Loss](https://mlsanity.com/paper/1711.05535/) (2017)

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

- [MAS-SAM: Segment Any Marine Animal with Aggregated Features](https://mlsanity.com/paper/2404.15700/) (2024)
- [Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval](https://mlsanity.com/paper/2409.19961/) (2024)
- [Reversed in Time: A Novel Temporal-Emphasized Benchmark for Cross-Modal Video-Text Retrieval](https://mlsanity.com/paper/2412.19178/) (2024)
- [Multi-modal Reference Learning for Fine-grained Text-to-Image Retrieval](https://mlsanity.com/paper/2504.07718/) (2025)
- [MM-Forecast: A Multimodal Approach to Temporal Event Forecasting with Large Language Models](https://mlsanity.com/paper/2408.04388/) (2024)
- [Deep Reversible Consistency Learning for Cross-modal Retrieval](https://mlsanity.com/paper/2501.05686/) (2025)
- [DAFM: Dynamic Adaptive Fusion for Multi-Model Collaboration in Composed Image Retrieval](https://mlsanity.com/paper/2511.05020/) (2025)
- [T2I-VeRW: Part-level Fine-grained Perception for Text-to-Image Vehicle Retrieval](https://mlsanity.com/paper/2605.06012/) (2026)

## Abstract (arXiv)

Most existing cross-modal retrieval methods employ two-stream encoders with different architectures for images and texts, textite.g., CNN for images and RNN/Transformer for texts. Such discrepancy in architectures may induce different semantic distribution spaces and limit the interactions between images and texts, and further result in inferior alignment between images and texts. To fill this research gap, inspired by recent advances of Transformers in vision tasks, we propose to unify the encoder architectures with Transformers for both modalities. Specifically, we design a cross-modal retrieval framework purely based on two-stream Transformers, dubbed Hierarchical Alignment Transformers (HAT), which consists of an image Transformer, a text Transformer, and a hierarchical alignment module. With such identical architectures, the encoders could produce representations with more similar characteristics for images and texts, and make the interactions and alignments between them much easier. Besides, to leverage the rich semantics, we devise a hierarchical alignment scheme to explore multi-level correspondences of different layers between images and texts. To evaluate the effectiveness of the proposed HAT, we conduct extensive experiments on two benchmark datasets, MSCOCO and Flickr30K. Experimental results demonstrate that HAT outperforms SOTA baselines by a large margin. Specifically, on two key tasks, textiti.e., image-to-text and text-to-image retrieval, HAT achieves 7.6% and 16.7% relative score improvement of Recall@1 on MSCOCO, and 4.4% and 11.6% on Flickr30k respectively. The code is available at urlhttps://github.com/LuminosityX/HAT.