Fine-Grained Visual Textual Alignment for Cross-Modal Retrieval Using Transformer Encoders
Open accessThe DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
Despite the evolution of deep-learning-based visual-textual processing systems, precise multi-modal matching remains a challenging task. In this work, we tackle the task of cross-modal retrieval through image-sentence matching based on word-region alignments, using supervision only at the global image-sentence level. Specifically, we present a novel approach called Transformer Encoder Reasoning and Alignment Network (TERAN). TERAN enforces a fine-grained match between the underlying components of images and sentences (i.e., image regions and words, respectively) to preserve the informative richness of both modalities. TERAN obtains state-of-the-art results on the image retrieval task on both MS-COCO and Flickr30k datasets. Moreover, on MS-COCO, it also outperforms current approaches on the sentence retrieval task. Focusing on scalable cross-modal information retrieval, TERAN is designed to keep the visual and textual data pipelines well separated. Cross-attention links invalidate any chance to separately extract visual and textual features needed for the online search and the offline indexing steps in large-scale retrieval systems. In this respect, TERAN merges the information from the two domains only during the final alignment phase, immediately before the loss computation. We argue that the fine-grained alignments produced by TERAN pave the way toward the research for effective and efficient methods for large-scale cross-modal information retrieval. We compare the effectiveness of our approach against relevant state-of-the-art methods. On the MS-COCO 1K test set, we obtain an improvement of 5.7% and 3.5% respectively on the image and the sentence retrieval tasks on the Recall@1 metric. The code used for the experiments is publicly available on GitHub at https://github.com/mesnico/TERAN .
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Visual 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
Deep visual-semantic alignments for generating image descriptions
Karpathy, A., & Fei-Fei, L. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298932 · Cited by 4,902
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
Lu, J., Batra, D., Parikh, D., & Lee, S. (2019) · arXiv · doi:10.48550/arxiv.1908.02265 · Cited by 2,109
UNITER: UNiversal Image-TExt Representation Learning
Chen, Y.-C., Li, L., Yu, L., El Kholy, A., Ahmed, F., Gan, Z., Cheng, Y., & Liu, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58577-8_7 · Cited by 2,055
Stacked Cross Attention for Image-Text Matching
Lee, K.-H., Chen, X., Hua, G., Hu, H., & He, X. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01225-0_13 · Cited by 1,402
A simple neural network module for relational reasoning
Santoro, A., Raposo, D., Barrett, D. G. T., Malinowski, M., Pascanu, R., Battaglia, P., & Lillicrap, T. (2017) · arXiv · doi:10.48550/arxiv.1706.01427 · Cited by 1,281 · cited 1×
“sentence level. High-level Reasoning Another branch of research from which this work draws inspiration is focused on the study of relational reasoning models for high-level understanding. The work in [41] proposes an architecture that separates perception from reasoning. They tackle the problem of Visual Question Answ…”
BackgroundAttention 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 1×
“Recently, many attempts to merge the two worlds have been explored, and state-of-the-art results have been obtained in many of these tasks, including visual question answering [2, 12, 42], image captioning [6, 14, 40, 49] and image-text matching [5, 10, 22, 33].”
BackgroundUnified 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
Cited by
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
Jia, C., Yang, Y., Xia, Y., Chen, Y.-T., Parekh, Z., Pham, H., Le, Q. V., Sung, Y., Li, Z., & Duerig, T. (2021) · arXiv · doi:10.48550/arxiv.2102.05918 · Cited by 1,977
“, leveraging object detectors, dense feature maps, or multi-attention layers) (Socher et al., 2014; Karpathy et al., 2014; Kiros et al.; Nam et al., 2017; Li et al., 2019; Messina et al., 2020; Chen et al., 2020a) have been proposed.”
BackgroundCombining EfficientNet and Vision Transformers for Video Deepfake Detection
Coccomini, D. A., Messina, N., Gennaro, C., & Falchi, F. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-06433-3_19 · Cited by 296
Self-citationEnhanced deepfake detection with densenet and cross-vit
Siddiqui, F., Yang, J., Xiao, S., & Fahad, M. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.126150 · Cited by 62
Bidirectional Transformer GAN for Long-term Human Motion Prediction
Zhao, M., Tang, H., Xie, P., Dai, S., Sebe, N., & Wang, W. (2023) · ACM Transactions on Multimedia Computing, Communications, and Applications · doi:10.1145/3579359 · Cited by 38
Grasp Stability Assessment Through Spatio-Temporal Attention Mechanism and Adaptive Gate Fusion
Li, S., Sun, W., Liang, Q., Sun, J., & Liu, C. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3493117 · Cited by 13
Metadata
- Authors
- Messina, N., Amato, G., Esuli, A., Falchi, F., Gennaro, C., & Marchand-Maillet, S.
- Venue
- ACM Transactions on Multimedia Computing, Communications, and Applications
- Published
- 2021-11-12
- Volume
- 17
- Issue
- 4
- Pages
- 1-23
- ISSN
- 1551-6857 (ISSN-L)
- 1551-6865
- OpenAlex
- W3048782180
- Cited by
- 149
- References
- 9
- FWCI
- 10.23
- Type
- journal article
- Language
- en
- Open access
- green
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.