# ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval

arXiv: https://arxiv.org/abs/2203.16778 · HTML: https://mlsanity.com/paper/2203.16778/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 50 references that are in the map.
- First posted on arXiv 31 Mar 2022.

## Builds on (most cited first, 30 of 40)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [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)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training](https://mlsanity.com/paper/1908.06066/) (2019)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [TextCaps: a Dataset for Image Captioning with Reading Comprehension](https://mlsanity.com/paper/2003.12462/) (2020)
- [Attention Bottlenecks for Multimodal Fusion](https://mlsanity.com/paper/2107.00135/) (2021)
- [Scene Text Visual Question Answering](https://mlsanity.com/paper/1905.13648/) (2019)
- [Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers](https://mlsanity.com/paper/2004.00849/) (2020)
- [12-in-1: Multi-Task Vision and Language Representation Learning](https://mlsanity.com/paper/1912.02315/) (2019)
- [ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph](https://mlsanity.com/paper/2006.16934/) (2020)
- [Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning](https://mlsanity.com/paper/2104.03135/) (2021)
- [Visual Semantic Reasoning for Image-Text Matching](https://mlsanity.com/paper/1909.02701/) (2019)
- [Probabilistic Embeddings for Cross-Modal Retrieval](https://mlsanity.com/paper/2101.05068/) (2021)
- [ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data](https://mlsanity.com/paper/2001.07966/) (2020)
- [Learning the Best Pooling Strategy for Visual Semantic Embedding](https://mlsanity.com/paper/2011.04305/) (2020)
- [Similarity Reasoning and Filtration for Image-Text Matching](https://mlsanity.com/paper/2101.01368/) (2021)
- [IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval](https://mlsanity.com/paper/2003.03772/) (2020)
- [Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQA](https://mlsanity.com/paper/1911.06258/) (2019)

## Built on by (most cited first, 29 of 29)

- [Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models](https://mlsanity.com/paper/2307.14061/) (2023)
- [Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory](https://mlsanity.com/paper/2403.12445/) (2024)
- [Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models](https://mlsanity.com/paper/2311.03799/) (2023)
- [A Large Cross-Modal Video Retrieval Dataset with Reading Comprehension](https://mlsanity.com/paper/2305.03347/) (2023)
- [PreSTU: Pre-Training for Scene-Text Understanding](https://mlsanity.com/paper/2209.05534/) (2022)
- [EDIS: Entity-Driven Image Search over Multimodal Web Content](https://mlsanity.com/paper/2305.13631/) (2023)
- [Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack](https://mlsanity.com/paper/2411.02669/) (2024)
- [Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection](https://mlsanity.com/paper/2307.13529/) (2023)
- [Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training](https://mlsanity.com/paper/2306.08789/) (2023)
- [Grounded Image Text Matching with Mismatched Relation Reasoning](https://mlsanity.com/paper/2308.01236/) (2023)
- [RoCOCO: Robustness Benchmark of MS-COCO to Stress-test Image-Text Matching Models](https://mlsanity.com/paper/2304.10727/) (2023)
- [Multimodal Neural Databases](https://mlsanity.com/paper/2305.01447/) (2023)
- [GPTSee: Enhancing Moment Retrieval and Highlight Detection via Description-Based Similarity Features](https://mlsanity.com/paper/2403.01437/) (2024)
- [NeighborRetr: Balancing Hub Centrality in Cross-Modal Retrieval](https://mlsanity.com/paper/2503.10526/) (2025)
- [Resolving Sentiment Discrepancy for Multimodal Sentiment Detection via Semantics Completion and Decomposition](https://mlsanity.com/paper/2407.07026/) (2024)
- [Hierarchical Banzhaf Interaction for General Video-Language Representation Learning](https://mlsanity.com/paper/2412.20964/) (2024)
- [Cross-Modal Pre-Aligned Method with Global and Local Information for Remote-Sensing Image and Text Retrieval](https://mlsanity.com/paper/2411.14704/) (2024)
- [Unified Loss of Pair Similarity Optimization for Vision-Language Retrieval](https://mlsanity.com/paper/2209.13869/) (2022)
- [Image-Text Retrieval with Binary and Continuous Label Supervision](https://mlsanity.com/paper/2210.11319/) (2022)
- [SLAN: Self-Locator Aided Network for Cross-Modal Understanding](https://mlsanity.com/paper/2211.16208/) (2022)
- [BagFormer: Better Cross-Modal Retrieval via bag-wise interaction](https://mlsanity.com/paper/2212.14322/) (2022)
- [LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Retrieval](https://mlsanity.com/paper/2302.02908/) (2023)
- [VITR: Augmenting Vision Transformers with Relation-Focused Learning for Cross-Modal Information Retrieval](https://mlsanity.com/paper/2302.06350/) (2023)
- [Artificial-Spiking Hierarchical Networks for Vision-Language Representation Learning](https://mlsanity.com/paper/2308.09455/) (2023)
- [MSTAR: Box-free Multi-query Scene Text Retrieval with Attention Recycling](https://mlsanity.com/paper/2506.10609/) (2025)
- [Superpixel Semantics Representation and Pre-training for Vision-Language Task](https://mlsanity.com/paper/2310.13447/) (2023)
- [Hierarchical Multi-modal Transformer for Cross-modal Long Document Classification](https://mlsanity.com/paper/2407.10105/) (2024)
- [Improving vision-language alignment with graph spiking hybrid Networks](https://mlsanity.com/paper/2501.19069/) (2025)
- [Anatomy-Aware Conditional Image-Text Retrieval](https://mlsanity.com/paper/2503.07456/) (2025)

## Abstract (arXiv)

Visual appearance is considered to be the most important cue to understand images for cross-modal retrieval, while sometimes the scene text appearing in images can provide valuable information to understand the visual semantics. Most of existing cross-modal retrieval approaches ignore the usage of scene text information and directly adding this information may lead to performance degradation in scene text free scenarios. To address this issue, we propose a full transformer architecture to unify these cross-modal retrieval scenarios in a single Vision and Scene Text Aggregation framework (ViSTA). Specifically, ViSTA utilizes transformer blocks to directly encode image patches and fuse scene text embedding to learn an aggregated visual representation for cross-modal retrieval. To tackle the modality missing problem of scene text, we propose a novel fusion token based transformer aggregation approach to exchange the necessary scene text information only through the fusion token and concentrate on the most important features in each modality. To further strengthen the visual modality, we develop dual contrastive learning losses to embed both image-text pairs and fusion-text pairs into a common cross-modal space. Compared to existing methods, ViSTA enables to aggregate relevant scene text semantics with visual appearance, and hence improve results under both scene text free and scene text aware scenarios. Experimental results show that ViSTA outperforms other methods by at least bf8.4% at Recall@1 for scene text aware retrieval task. Compared with state-of-the-art scene text free retrieval methods, ViSTA can achieve better accuracy on Flicker30K and MSCOCO while running at least three times faster during the inference stage, which validates the effectiveness of the proposed framework.