Guided Open Vocabulary Image Captioning with Constrained Beam Search
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Existing image captioning models do not generalize well to out-of-domain images containing novel scenes or objects.This limitation severely hinders the use of these models in real world applications dealing with images in the wild.We address this problem using a flexible approach that enables existing deep captioning architectures to take advantage of image taggers at test time, without re-training.Our method uses constrained beam search to force the inclusion of selected tag words in the output, and fixed, pretrained word embeddings to facilitate vocabulary expansion to previously unseen tag words.Using this approach we achieve state of the art results for out-of-domain captioning on MSCOCO (and improved results for in-domain captioning).Perhaps surprisingly, our results significantly outperform approaches that incorporate the same tag predictions into the learning algorithm.We also show that we can significantly improve the quality of generated ImageNet captions by leveraging ground-truth labels.
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
Caffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077
Long-term recurrent convolutional networks for visual recognition and description
Donahue, J., Hendricks, L. A., Guadarrama, S., Rohrbach, M., Venugopalan, S., Darrell, T., & Saenko, K. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298878 · Cited by 5,228
CIDEr: Consensus-based image description evaluation
Vedantam, R., Zitnick, C. L., & Parikh, D. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299087 · Cited by 4,845
SPICE: 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
Self-citationMicrosoft COCO Captions: Data Collection and Evaluation Server
Chen, X., Fang, H., Lin, T.-Y., Vedantam, R., Gupta, S., Dollar, P., & Zitnick, C. L. (2015) · arXiv · doi:10.48550/arxiv.1504.00325 · Cited by 1,614 · cited 15×
“For both tasks, the user interface and question phrasing was identical to the MSCOCO collection process.”
MethodInfluentialLong-Term Recurrent Convolutional Networks for Visual Recognition and Description
Donahue, J., Hendricks, L. A., Rohrbach, M., Venugopalan, S., Guadarrama, S., Saenko, K., & Darrell, T. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2599174 · Cited by 1,547
Deep 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
Cited by
Meshed-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
Justifying Recommendations using Distantly-Labeled Reviews and Fine-Grained Aspects
Ni, J., Li, J., & McAuley, J. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1018 · Cited by 1,200
Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts
Changpinyo, S., Sharma, P., Ding, N., & Soricut, R. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00356 · Cited by 612
Lu, J., Yang, J., Batra, D., & Parikh, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00754 · Cited by 411
From Show to Tell: A Survey on Deep Learning-Based Image Captioning
Stefanini, M., Cornia, M., Baraldi, L., Cascianelli, S., Fiameni, G., & Cucchiara, R. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3148210 · Cited by 373
“[182] devised the Constrained Beam Search algorithm to”
MethodA Survey of Controllable Text Generation Using Transformer-based Pre-trained Language Models
Zhang, H., Song, H., Li, S., Zhou, M., & Song, D. (2024) · ACM Computing Surveys · doi:10.1145/3617680 · Cited by 317
nocaps: novel object captioning at scale
Agrawal, H., Desai, K., Wang, Y., Chen, X., Jain, R., Johnson, M., Batra, D., Parikh, D., Lee, S., & Anderson, P. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00904 · Cited by 312
Self-citationToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection
Hartvigsen, T., Gabriel, S., Palangi, H., Sap, M., Ray, D., & Kamar, E. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.234 · Cited by 279
Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions
Cornia, M., Baraldi, L., & Cucchiara, R. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00850 · Cited by 205
“Some works have extended the beam-search algorithm to sample multiple captions from the same distribution [41, 1], while different GAN-based approaches have also appeared [8, 39, 45].”
BackgroundConstrained Language Models Yield Few-Shot Semantic Parsers
Shin, R., Lin, C., Thomson, S., Chen, C., Roy, S., Platanios, E. A., Pauls, A., Klein, D., Eisner, J., & Van Durme, B. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.608 · Cited by 139
“…in the output of a text generation system, researchers have explored increasingly more efficient approaches to restricting valid paths in beam search such that they satisfy externally provided constraints (e.g., Hokamp and Liu, 2017; Anderson et al., 2017; Post and Vilar, 2018; Hu et al., 2019).”
BackgroundTowards Unsupervised Image Captioning With Shared Multimodal Embeddings
Laina, I., Rupprecht, C., & Navab, N. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00751 · Cited by 111
Unsupervised Paraphrasing by Simulated Annealing
Liu, X., Mou, L., Meng, F., Zhou, H., Zhou, J., & Song, S. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.28 · Cited by 75
Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning
Geng, S., Josifoski, M., Peyrard, M., & West, R. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.674 · Cited by 74
Self-Supervised and Controlled Multi-Document Opinion Summarization
Elsahar, H., Coavoux, M., Gallé, M., & Rozen, J. (2020) · arXiv · doi:10.48550/arxiv.2004.14754 · Cited by 40
“Constrained beam search (Anderson et al., 2017; Hokamp & Liu, 2017; Post & Vilar, 2018) is slower, requires in practice very large beam sizes, and does not enable soft constraints.”
BackgroundEvaluating Large Language Models on Controlled Generation Tasks
Sun, J., Tian, Y., Zhou, W., Xu, N., Hu, Q., Gupta, R., Wieting, J., Peng, N., & Ma, X. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.190 · Cited by 29
Decider: A Dual-System Rule-Controllable Decoding Framework for Language Generation
Xu, C., Lan, T., Ji, Y., Yu, C., Wang, W., Gao, J., Dong, Q., Qian, K., Li, P., Bi, W., et al. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3554819 · Cited by 2
“With the popularity of pre-trained language models (PLMs), researchers are working on developing decoding methods that directly guide a pre-trained base model toward target keywords while keeping the text quality as much as possible without training [2], [25], [26], [27], [28], [29].”
Evaluating Large Language Models on Controlled Generation Tasks
Sun, J., Tian, Y., Zhou, W., Xu, N., Hu, Q., Gupta, R., Wieting, J. F., Peng, N., & Ma, X. (2023) · arXiv · doi:10.48550/arxiv.2310.14542 · Cited by 1
Metadata
- Authors
- Anderson, P., Fernando, B., Johnson, M., & Gould, S.
- Venue
- Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
- Published
- 2017
- Pages
- 936-945
- OpenAlex
- W2560207749
- Cited by
- 193
- References
- 7
- FWCI
- 5.82
- Type
- conference paper
- Language
- en
- Open access
- hybrid
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.