mlsanityData to 7 Oct 2026

Image-text Retrieval: A Survey on Recent Research and Development

arXiv 2203.14713 ↗First posted 28 Mar 2022cs.IR cs.AIcited by 55

Not on the map. Why?

Cited by 20 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In the past few years, cross-modal image-text retrieval (ITR) has experienced increased interest in the research community due to its excellent research value and broad real-world application. It is designed for the scenarios where the queries are from one modality and the retrieval galleries from another modality. This paper presents a comprehensive and up-to-date survey on the ITR approaches from four perspectives. By dissecting an ITR system into two processes: feature extraction and feature alignment, we summarize the recent advance of the ITR approaches from these two perspectives. On top of this, the efficiency-focused study on the ITR system is introduced as the third perspective. To keep pace with the times, we also provide a pioneering overview of the cross-modal pre-training ITR approaches as the fourth perspective. Finally, we outline the common benchmark datasets and valuation metric for ITR, and conduct the accuracy comparison among the representative ITR approaches. Some critical yet less studied issues are discussed at the end of the paper.

Key facts. Cited by 55 papers in the map (data through 7 Oct 2026). Builds on 43 of its 62 references that are in the map. First posted on arXiv 28 Mar 2022.

Builds on

43 of 62 references.

References · 43

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  3. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,219
  4. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,612
  5. 2019VisualBERT: A Simple and Performant Baseline for Vision and Languagecited by 1,291
  6. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,224
  7. 2020Oscar: Object-Semantics Aligned Pre-training for Vision-Language Taskscited by 1,213
  8. 2017Multimodal Machine Learning: A Survey and Taxonomycited by 1,004
  9. 2021FILIP: Fine-grained Interactive Language-Image Pre-Trainingcited by 626
  10. 2019Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-trainingcited by 451
  11. 2018Stacked Cross Attention for Image-Text Matchingcited by 414
  12. 2020Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformerscited by 288
31 more
  1. 2021An Empirical Study of Training End-to-End Vision-and-Language Transformerscited by 271
  2. 2020UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learningcited by 239
  3. 2020ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graphcited by 211
  4. 2021Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learningcited by 187
  5. 2019Visual Semantic Reasoning for Image-Text Matchingcited by 185
  6. 2021Probabilistic Embeddings for Cross-Modal Retrievalcited by 150
  7. 2017Dual-Path Convolutional Image-Text Embeddings with Instance Losscited by 145
  8. 2020ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Datacited by 136
  9. 2021Similarity Reasoning and Filtration for Image-Text Matchingcited by 121
  10. 2017Learning Two-Branch Neural Networks for Image-Text Matching Taskscited by 119
  11. 2020IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrievalcited by 115
  12. 2019CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrievalcited by 110
  13. 2021Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformerscited by 93
  14. 2021WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Trainingcited by 84
  15. 2021E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learningcited by 84
  16. 2019Polysemous Visual-Semantic Embedding for Cross-Modal Retrievalcited by 83
  17. 2021Kaleido-BERT: Vision-Language Pre-training on Fashion Domaincited by 67
  18. 2021Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-trainingcited by 67
  19. 2019Adversarial Representation Learning for Text-to-Image Matchingcited by 65
  20. 2020Consensus-Aware Visual-Semantic Embedding for Image-Text Matchingcited by 59
  21. 2020FashionBERT: Text and Image Matching with Adaptive Loss for Cross-modal Retrievalcited by 55
  22. 2019Focus Your Attention: A Bidirectional Focal Attention Network for Image-Text Matchingcited by 49
  23. 2021Playing Lottery Tickets with Vision and Languagecited by 45
  24. 2021ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integrationcited by 31
  25. 2018Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrievalcited by 29
  26. 2021Step-Wise Hierarchical Alignment Network for Image-Text Matchingcited by 26
  27. 2021KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillationcited by 23
  28. 2019Saliency-Guided Attention Network for Image-Sentence Matchingcited by 21
  29. 2021Learning Relation Alignment for Calibrated Cross-modal Retrievalcited by 21
  30. 2020Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal Hashingcited by 15
  31. 2020StacMR: Scene-Text Aware Cross-Modal Retrievalcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 17; 2024: 15; 2025: 13; 2026: 7.

55 papers.

Sort:

By area:

  1. 2023Vision-Language Models for Vision Tasks: A Surveycited by 834
  2. 2023BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learningcited by 112
  3. 2024Number it: Temporal Grounding Videos like Flipping Mangacited by 65
  4. 2023RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Searchcited by 53
  5. 2022Data Poisoning Attacks Against Multimodal Encoderscited by 41
  6. 2023OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimizationcited by 36
  7. 2024Accelerating Transformers with Spectrum-Preserving Token Mergingcited by 35
  8. 2023Mitigating Test-Time Bias for Fair Image Retrievalcited by 20
  9. 2023Text-based Person Search without Parallel Image-Text Datacited by 17
  10. 2023State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understandingcited by 17
  11. 2023Exploring Transferability of Multimodal Adversarial Samples for Vision-Language Pre-training Models with Contrastive Learningcited by 16
  12. 2025Image Quality Assessment: From Human to Machine Preferencecited by 12
38 more
  1. 2025Mimic In-Context Learning for Multimodal Taskscited by 12
  2. 2024A Survey of Medical Vision-and-Language Applications and Their Techniquescited by 11
  3. 2024BEV-TSR: Text-Scene Retrieval in BEV Space for Autonomous Drivingcited by 10
  4. 2024The Phantom Menace: Unmasking Privacy Leakages in Vision-Language Modelscited by 8
  5. 2025CoIDO: Efficient Data Selection for Visual Instruction Tuning via Coupled Importance-Diversity Optimizationcited by 8
  6. 2022Improving Commonsense in Vision-Language Models via Knowledge Graph Riddlescited by 7
  7. 2024Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interactioncited by 7
  8. 2025Supervised Fine-Tuning or Contrastive Learning? Towards Better Multimodal LLM Rerankingcited by 6
  9. 2026TSEmbed: Unlocking Task Scaling in Universal Multimodal Embeddingscited by 6
  10. 2023Vision Meets Definitions: Unsupervised Visual Word Sense Disambiguation Incorporating Gloss Informationcited by 5
  11. 2024A Survey of Route Recommendations: Methods, Applications, and Opportunitiescited by 5
  12. 2024Benchmark Granularity and Model Robustness for Image-Text Retrievalcited by 5
  13. 2023IIITD-20K: Dense captioning for Text-Image ReIDcited by 4
  14. 2023A Survey on Image-text Multimodal Modelscited by 4
  15. 2024Semi-supervised Text-based Person Searchcited by 4
  16. 2025Robust Duality Learning for Unsupervised Visible-Infrared Person Re-Identificationcited by 4
  17. 2025Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hyperspherecited by 4
  18. 2024Object-Aware Query Perturbation for Cross-Modal Image-Text Retrievalcited by 3
  19. 2024Open-Vocabulary Mobile Manipulation Based on Double Relaxed Contrastive Learning with Dense Labelingcited by 3
  20. 2023Selectively Hard Negative Mining for Alleviating Gradient Vanishing in Image-Text Matchingcited by 2
  21. 2023Interpreting Vision and Language Generative Models with Semantic Visual Priorscited by 2
  22. 2023Parameter-Efficient Cross-lingual Transfer of Vision and Language Models via Translation-based Alignmentcited by 2
  23. 2023Progressive Feature Mining and External Knowledge-Assisted Text-Pedestrian Image Retrievalcited by 2
  24. 2024MMIS: Multimodal Dataset for Interior Scene Visual Generation and Recognitioncited by 2
  25. 2024Robust image classification with multi-modal large language modelscited by 2
  26. 2025Large Vision-Language Models for Knowledge-Grounded Data Annotation of Memescited by 2
  27. 2023FArMARe: a Furniture-Aware Multi-task methodology for Recommending Apartments based on the user interestscited by 1
  28. 2025Adding simple structure at inference improves Vision-Language Compositionalitycited by 1
  29. 2026Revisiting Compositionality in Dual-Encoder Vision-Language Models: The Role of Inferencecited by 1
  30. 2026Prune Once: Retraining-Free Task-Agnostic Pruning for Vision-Language Modelscited by 1
  31. 2022Test-time Training for Data-efficient UCDRcited by 0
  32. 2023Efficient Image-Text Retrieval via Keyword-Guided Pre-Screeningcited by 0
  33. 2024DEMO: A Statistical Perspective for Efficient Image-Text Matchingcited by 0
  34. 2024Generative Visual Communication in the Era of Vision-Language Modelscited by 0
  35. 2025Deep Contrastive Learning for Feature Alignment: Insights from Housing-Household Relationship Inferencecited by 0
  36. 2025Anatomy-Aware Conditional Image-Text Retrievalcited by 0
  37. 2025MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrievalcited by 0
  38. 2025Improving Adversarial Robustness of Zero-Shot CLIP with Confidence-Aware Weightingcited by 0

50 most cited of 55 All 55 (JSON)