CoChat

Text2Scene: Generating Compositional Scenes From Textual Descriptions

Open access
Tan, Fuwen, Feng, Song, Ordonez, Vicente · 2019 · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Cited by 93

The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.

Abstract

In this paper, we propose Text2Scene, a model that generates various forms of compositional scene representations from natural language descriptions. Unlike recent works, our method does NOT use Generative Adversarial Networks (GANs). Text2Scene instead learns to sequentially generate objects and their attributes (location, size, appearance, etc) at every time step by attending to different parts of the input text and the current status of the generated scene. We show that under minor modifications, the proposed framework can handle the generation of different forms of scene representations, including cartoon-like scenes, object layouts corresponding to real images, and synthetic images. Our method is not only competitive when compared with state-of-the-art GAN-based methods using automatic metrics and superior based on human judgments but also has the advantage of producing interpretable results.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr.2019.00687

Cites

11 of 11 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Show all 11 references

Research works printed but not linked: 30

  1. 10.18653/v1/P17-5003 · DOI
  2. 10.1109/CVPR.2018.00649 · DOI · Paper page
  3. xu, 2015, Show, attend and tell: Neural image caption generation with visual attention, International Conference on Machine Learning (ICML), 37, 2048
  4. 10.1109/ICCV.2015.292 · DOI · Paper page
  5. 10.18653/v1/D17-1017 · DOI
  6. 10.1109/CVPR.2017.671 · DOI · Paper page
  7. 10.18653/v1/N16-1023 · DOI
  8. holger caesar, 2018, Coco-stuff: Thing and stuff classes in context, IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  9. 10.1109/CVPR.2013.387 · DOI · Paper page
  10. 10.1109/CVPR.2018.00833 · DOI · Paper page
  11. 10.1109/CVPR.2017.632 · DOI · Paper page
  12. kim, 2017, Codraw: Visual dialog for collaborative drawing, arXiv preprint arXiv 1712 05558
  13. 10.1162/tacl_a_00188 · DOI · Paper page
  14. lin, 2004, Rouge: A package for automatic evaluation of summaries, Workshop on Text Summarization Branches Out
  15. lin, 2014, Microsoft COCO: Common objects in context, European Conference on Computer Vision (ECCV)
  16. sutskever, 2014, Sequence to sequence learning with neural networks, Advances in Neural IInformation Processing Systems
  17. 10.3115/1706543.1706571 · DOI · Paper page
  18. 10.1109/CVPR.2015.7299087 · DOI · Paper page
  19. farhadi, 2010, Every picture tells a story: Generating sentences from images, European Conference on Computer Vision (ECCV), 15
  20. goodfellow, 2014, Generative adversarial nets, Advances in Neural IInformation Processing Systems
  21. 10.1109/CVPR.2014.260 · DOI · Paper page
  22. 10.18653/v1/D17-1098 · DOI · Paper page
  23. 10.1007/978-3-030-01237-3_37 · DOI
  24. anderson, 2016, Spice: Semantic propositional image caption evaluation, European Conference on Computer Vision (ECCV), 382
  25. 10.1007/s11263-015-0840-y · DOI
  26. 10.3115/v1/P14-2097 · DOI · Paper page
  27. 10.1109/CVPR.2018.00918 · DOI · Paper page
  28. 10.1109/ICCV.2013.211 · DOI · Paper page
  29. papineni, 2002, Bleu: a method for automatic evaluation of machine translation, Annual Meeting of the Association for Computational Linguistics (ACL), 311
  30. reed, 2016, Learning what and where to draw, Advances in Neural IInformation Processing Systems

Cited by

See all 93

Metadata

Authors
Tan, F., Feng, S., & Ordonez, V.
Venue
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2019-06
Pages
6703-6712
ISSN
1063-6919 (ISSN-L)
OpenAlex
W2979672901
Cited by
93
References
11
FWCI
4.55
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: Text2Scene: Generating Compositional Scenes From Textual Descriptions. https://app.cochat.ai/papers/10.1109/cvpr.2019.00687
The paper
Tan, F., Feng, S., & Ordonez, V. (2019). Text2Scene: Generating Compositional Scenes From Textual Descriptions. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr.2019.00687

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.