Cross-Modal Self-Attention with Multi-Task Pre-Training for Medical Visual Question Answering
Open accessThe DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
Due to the severe lack of labeled data, existing methods of medical visual question answering usually rely on transfer learning to obtain effective image feature representation and use cross-modal fusion of visual and linguistic features to achieve question-related answer prediction. These two phases are performed independently and without considering the compatibility and applicability of the pre-trained features for cross-modal fusion. Thus, we reformulate image feature pre-training as a multi-task learning paradigm and witness its extraordinary superiority, forcing it to take into account the applicability of features for the specific image comprehension task. Furthermore, we introduce a cross-modal self-attention~(CMSA) module to selectively capture the long-range contextual relevance for more effective fusion of visual and linguistic features. Experimental results demonstrate that the proposed method outperforms existing state-of-the-art methods. Our code and models are available at https://github.com/haifangong/CMSA-MTPT-4-MedicalVQA.
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
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
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
Wang, X., Girshick, R., Gupta, A., & He, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00813 · Cited by 11,596
BioBERT: a pre-trained biomedical language representation model for biomedical text mining
Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C. H., & Kang, J. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btz682 · Cited by 7,218
Multimodal 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 2×
“With the prosperity of deep learning, VQA has received extensive attention in recent years and has made great progress, mainly benefiting from the strong bottom-up feature representation based on deep CNNs[4] and the cross-modal feature alignment and fusion techniques[4, 8, 13, 26, 28].”
BackgroundMethodBioWordVec, improving biomedical word embeddings with subword information and MeSH
Zhang, Y., Chen, Q., Yang, Z., Lin, H., & Lu, Z. (2019) · Scientific Data · doi:10.1038/s41597-019-0055-0 · Cited by 455
Cited by
The multi-modal fusion in visual question answering: a review of attention mechanisms
Lu, S., Liu, M., Yin, L., Yin, Z., Liu, X., & Zheng, W. (2023) · PeerJ Computer Science · doi:10.7717/peerj-cs.1400 · Cited by 477
A scoping review on multimodal deep learning in biomedical images and texts
Sun, Z., Lin, M., Zhu, Q., Xie, Q., Wang, F., Lu, Z., & Peng, Y. (2023) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2023.104482 · Cited by 69
Multi-task paired masking with alignment modeling for medical vision-language pre-training
Zhang, K., Yang, Y., Yu, J., Jiang, H., Fan, J., Huang, Q., & Han, W. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3325965 · Cited by 51
“, M3AE [4], MMBERT [51] and MTPT [50], as well as non-pre-training methods such as VQAMix [35], BAN-MEVF+SEADA [33], BAN-MEVF+DAVQA [31] and CMSA-MTPT [34], etc.”
MethodCai, L., Fang, H., & Li, Z. (2023) · The Journal of Supercomputing · doi:10.1007/s11227-023-05195-2 · Cited by 8
“Another work [15] reformulated image features pre-training as a multitask learning paradigm and evaluated their model on VQA-RAD [21].”
BackgroundMethod
Metadata
- Authors
- Gong, H., Chen, G., Liu, S., Yu, Y., & Li, G.
- Venue
- Proceedings of the 2021 International Conference on Multimedia Retrieval
- Publisher
- ACM
- Published
- 2021-08-24
- Pages
- 456-460
- OpenAlex
- W3198570286
- Cited by
- 104
- References
- 8
- FWCI
- 5.46
- Type
- conference paper
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Cross-Modal Self-Attention with Multi-Task Pre-Training for Medical Visual Question Answering. https://app.cochat.ai/papers/10.1145/3460426.3463584
- The paper
- Gong, H., Chen, G., Liu, S., Yu, Y., & Li, G. (2021). Cross-Modal Self-Attention with Multi-Task Pre-Training for Medical Visual Question Answering. Proceedings of the 2021 International Conference on Multimedia Retrieval. https://doi.org/10.1145/3460426.3463584
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.