Deep Learning Approaches on Image Captioning: A Review
Open accessThe DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index.
Abstract
Image captioning is a research area of immense importance, aiming to generate natural language descriptions for visual content in the form of still images. The advent of deep learning and more recently vision-language pre-training techniques has revolutionized the field, leading to more sophisticated methods and improved performance. In this survey article, we provide a structured review of deep learning methods in image captioning by presenting a comprehensive taxonomy and discussing each method category in detail. Additionally, we examine the datasets commonly employed in image captioning research, as well as the evaluation metrics used to assess the performance of different captioning models. We address the challenges faced in this field by emphasizing issues such as object hallucination, missing context, illumination conditions, contextual understanding, and referring expressions. We rank different deep learning methods’ performance according to widely used evaluation metrics, giving insight into the current state-of-the-art. Furthermore, we identify several potential future directions for research in this area, which include tackling the information misalignment problem between image and text modalities, mitigating dataset bias, incorporating vision-language pre-training methods to enhance caption generation, and developing improved evaluation tools to accurately measure the quality of image captions.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545 · cited 2×
“While the middle component contains LSTM [ 51 ] or GRU [ 19 ] units in other methods, masked convolutions are used in the proposed approach.”
MethodUnpaired image-to-image translation using cycle-consistent adversarial networks
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.244 · Cited by 23,602
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · arXiv · doi:10.48550/arxiv.2005.12872 · Cited by 18,253
The graph neural network model
Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M., & Monfardini, G. (2009) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2008.2005605 · Cited by 9,582
Conditional Generative Adversarial Nets
Mirza, M., & Osindero, S. (2014) · arXiv · doi:10.48550/arxiv.1411.1784 · Cited by 8,863
Show and tell: A neural image caption generator
Vinyals, O., Toshev, A., Bengio, S., & Erhan, D. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298935 · Cited by 6,318 · cited 2×
“Vinyals et al. [ 119 ] have been the first to incorporate deep learning-based encoder-decoder framework for image captioning.”
BackgroundMethodDeformable DETR: Deformable Transformers for End-to-End Object Detection
Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020) · arXiv · doi:10.48550/arxiv.2010.04159 · Cited by 6,027 · cited 4×
“To overcome this problem and to reduce their high computation cost, Nguyen et al. employ the Deformable DETR [ 149 ] and replace the CNN backbone in the original design with Swin Transformer.”
MethodInfluentialVisual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., Chen, S., Kalantidis, Y., Li, L.-J., Shamma, D. A., et al. (2017) · International Journal of Computer Vision · doi:10.1007/s11263-016-0981-7 · Cited by 5,107
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
Zheng, S., Lu, J., Zhao, H., Zhu, X., Luo, Z., Wang, Y., Fu, Y., Feng, J., Xiang, T., Torr, P. H. S., et al. (2020) · arXiv · doi:10.48550/arxiv.2012.15840 · Cited by 4,004
Kuznetsova, A., Rom, H., Alldrin, N., Uijlings, J., Krasin, I., Pont-Tuset, J., Kamali, S., Popov, S., Malloci, M., Kolesnikov, A., et al. (2018) · arXiv · doi:10.48550/arxiv.1811.00982 · Cited by 3,653
Learning internal representations by error propagation
RUMELHART, D. E., HINTON, G. E., & WILLIAMS, R. J. (1988) · Readings in Cognitive Science · doi:10.1016/b978-1-4832-1446-7.50035-2 · Cited by 3,002
Convolutional Sequence to Sequence Learning
Gehring, J., Auli, M., Grangier, D., Yarats, D., & Dauphin, Y. N. (2017) · arXiv · doi:10.48550/arxiv.1705.03122 · Cited by 2,850 · cited 1×
“Thanks to the recent advances in convolutional architectures on other sequence-to-sequence tasks such as convolutional image generation [ 90 ] and machine translation [ 36 , 37 ], it is possible to consider CNNs as an effective solution to many vision-language tasks.”
BackgroundPrefix-Tuning: Optimizing Continuous Prompts for Generation
Li, X. L., & Liang, P. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.353 · Cited by 2,473
Pre-Trained Image Processing Transformer
Chen, H., Wang, Y., Guo, T., Xu, C., Deng, Y., Liu, Z., Ma, S., Xu, C., Xu, C., & Gao, W. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01212 · Cited by 2,308 · cited 1×
“Transformers have been the center of attention in the computer vision field as well, with models such as DETR [ 14 ], ViT [ 28 ], SETR [ 144 ], and IPT [ 16 ].”
MethodSPICE: Semantic Propositional Image Caption Evaluation
Anderson, P., Fernando, B., Johnson, M., & Gould, S. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46454-1_24 · Cited by 1,986
Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning
Sharma, P., Ding, N., Goodman, S., & Soricut, R. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1238 · Cited by 1,879 · cited 2×
“…375,000 8.4 - 1 Flickr30K [ 139 ] 31,000 - - 5 FlickrStyle10K [ 33 ] 10,000 - - 2 OpenImagesV6:L.N. [ 98 ] 849,000 - - 1 SentiCap [ 86 ] 3171 - - 6 TextCaps [ 110 ] 28,408 - - 5 VizWiz-Captions [ 46 ] 39,181 - - 5 nocaps [ 1 ] 15,100 - 680 11 Conceptual Captions [ 106 ] 3 mil - - 1 Details (R.D.”
MethodInfluentialMultimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
Fukui, A., Park, D. H., Yang, D., Rohrbach, A., Darrell, T., & Rohrbach, M. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1044 · Cited by 1,582 · cited 1×
“…complexities, attracting a significant amount of work with extensive applications across various domains such as human-computer interaction [ 32 , 71 , 143 ], medical image captioning and prescription [ 9 , 58 , 96 ], traffic data analysis [ 69 ], quality control in industry [ 83 ], and…”
BackgroundFlamingo: a Visual Language Model for Few-Shot Learning
Alayrac, J.-B., Donahue, J., Luc, P., Miech, A., Barr, I., Hasson, Y., Lenc, K., Mensch, A., Millican, K., Reynolds, M., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.14198 · Cited by 1,555
Relation Networks for Object Detection
Hu, H., Gu, J., Zhang, Z., Dai, J., & Wei, Y. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00378 · Cited by 1,524
Scene Graph Generation by Iterative Message Passing
Xu, D., Zhu, Y., Choy, C. B., & Fei-Fei, L. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.330 · Cited by 1,271 · cited 2×
“First, the scene graph for the input image is generated using the method proposed in Reference [ 127 ].”
MethodMeshed-Memory Transformer for Image Captioning
Cornia, M., Stefanini, M., Baraldi, L., & Cucchiara, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01059 · Cited by 1,259
Attention on Attention for Image Captioning
Huang, L., Wang, W., Chen, J., & Wei, X.-Y. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00473 · Cited by 1,092 · cited 4×
“Huang et al. [ 59 ] have introduced a new attention-based structure containing one more level of attention.”
BackgroundMethodInfluentialDeep Visual-Semantic Alignments for Generating Image Descriptions
Karpathy, A., & Fei-Fei, L. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2598339 · Cited by 1,048
Li, J., Li, D., Savarese, S., & Hoi, S. (2023) · arXiv · doi:10.48550/arxiv.2301.12597 · Cited by 908 · cited 1×
“Considering the recent advancements in generative artificial intelligence such as large language models (LLMs) [103] and multimodal language models (MLLMs) [102, 66, 5, 78], the need for representation methods capable of handling such data types will become more and more visible and felt in near future.”
BackgroundA Comprehensive Survey of Deep Learning for Image Captioning
Hossain, M. Z., Sohel, F., Shiratuddin, M. F., & Laga, H. (2019) · ACM Computing Surveys · doi:10.1145/3295748 · Cited by 879 · cited 2×
“However, instead of a pairwise comparison like in [58], we have organized our paper to feature a separate section for each method category and follow the same order of category in our discussion (section 5).”
BackgroundMethodUnified Vision-Language Pre-Training for Image Captioning and VQA
Zhou, L., Palangi, H., Zhang, L., Hu, H., Corso, J., & Gao, J. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.7005 · Cited by 864
X-Linear Attention Networks for Image Captioning
Pan, Y., Yao, T., Li, Y., & Mei, T. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01098 · Cited by 720
Visual Translation Embedding Network for Visual Relation Detection
Zhang, H., Kyaw, Z., Chang, S.-F., & Chua, T.-S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.331 · Cited by 586 · cited 1×
“To utilize graphs in caption generation, two types of graph extraction are usually used: scene graph extraction from images [ 24 , 44 , 73 , 114 , 127 , 132 , 142 ] and scene graph extraction from textual data [ 6 , 124 ].”
MethodImproved Image Captioning via Policy Gradient optimization of SPIDEr
Liu, S., Zhu, Z., Ye, N., Guadarrama, S., & Murphy, K. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.100 · Cited by 430 · cited 1×
“…confronted with a set of problems, some of which commonly experienced in many artificial intelligence tasks such as the exposure bias problem [ 101 ], the loss-evaluation mismatch problem [ 41 , 79 , 103 , 130 ], the vanishing gradient problem [ 50 ], and the exploding gradient problem [ 39 , 95 ].”
BackgroundObject Hallucination in Image Captioning
Rohrbach, A., Hendricks, L. A., Burns, K., Darrell, T., & Saenko, K. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1437 · Cited by 420 · cited 2×
“Object hallucination [ 104 ] is a persistent problem for image captioning models, wherein the model detects objects that are not present in the input image.”
BackgroundUnderstanding Blind People's Experiences with Computer-Generated Captions of Social Media Images
MacLeod, H., Bennett, C. L., Morris, M. R., & Cutrell, E. (2017) · Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3025453.3025814 · Cited by 200 · cited 1×
“According to a study by MacLeod et al. [ 84 ], for many visually impaired people who prefer correctness over coverage, hallucination is a severe disadvantage for a captioning model and an obvious concern.”
MethodXGPT: Cross-modal Generative Pre-Training for Image Captioning
Xia, Q., Huang, H., Duan, N., Zhang, D., Ji, L., Sui, Z., Cui, E., Bharti, T., & Zhou, M. (2021) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-88480-2_63 · Cited by 70
Cited by
Image captioning by diffusion models: a survey
Daneshfar, F., Bartani, A., & Lotfi, P. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109288 · Cited by 49
Abdulgalil, H. D., & Basir, O. A. (2025) · Natural Language Processing Journal · doi:10.1016/j.nlp.2025.100159 · Cited by 20
Facklam, D., Sweeney, S. J., Majumdar, S., & Dmello Kamath, R. N. (2026) · The Electronic Library · doi:10.1108/el-06-2025-0270 · Cited by 5
‘We can see a savage’: a case study of the colonial gaze in generative AI algorithms
Alenichev, A., Shaffer, J. D., Kingori, P., Grietens, K. P., Muldoon, J., & Rocher, L. (2026) · AI & SOCIETY · doi:10.1007/s00146-025-02685-0 · Cited by 3
“Combining machine learning techniques in computer vision with natural language processing, image captioning generates a textual description of the most essential information in a given image (Sharma et al. 2018; Ghandi et al. 2024).”
Metadata
- Authors
- Ghandi, T., Pourreza, H., & Mahyar, H.
- Venue
- ACM Computing Surveys
- Published
- 2023-10-05
- Volume
- 56
- Issue
- 3
- Pages
- 1-39
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W4386162736
- Cited by
- 194
- References
- 37
- FWCI
- 17.55
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.