Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 1,277

The DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.

COCO-Stuff: Thing and Stuff Classes in Context

Open access
Caesar, Holger, Uijlings, Jasper, Ferrari, Vittorio·2018·2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
DOI 10.1109/cvpr.2018.00132
Open this paper in CoChat — free account

Abstract

Semantic classes can be either things (objects with a well-defined shape, e.g. car, person) or stuff (amorphous background regions, e.g. grass, sky). While lots of classification and detection works focus on thing classes, less attention has been given to stuff classes. Nonetheless, stuff classes are important as they allow to explain important aspects of an image, including (1) scene type; (2) which thing classes are likely to be present and their location (through contextual reasoning); (3) physical attributes, material types and geometric properties of the scene. To understand stuff and things in context we introduce COCO-Stuff1, which augments all 164K images of the COCO 2017 dataset with pixel-wise annotations for 91 stuff classes. We introduce an efficient stuff annotation protocol based on superpixels, which leverages the original thing annotations. We quantify the speed versus quality trade-off of our protocol and explore the relation between annotation time and boundary complexity. Furthermore, we use COCO-Stuff to analyze: (a) the importance of stuff and thing classes in terms of their surface cover and how frequently they are mentioned in image captions; (b) the spatial relations between stuff and things, highlighting the rich contextual relations that make our dataset unique; (c) the performance of a modern semantic segmentation method on stuff and thing classes, and whether stuff is easier to segment than things.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.1109/cvpr.2018.00132

Cites

12 of 12 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.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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 12 references

Research works printed but not linked: 51

  1. 10.1109/CVPR.2013.404 · DOI
  2. krähenbühl, 2011, Efficient inference in fully connected CRFs with gaussian edge potentials, NIPS, 109
  3. 10.1007/s11263-008-0202-0 · DOI · Paper page
  4. 10.1007/978-3-642-33885-4_30 · DOI
  5. jain, 2016, Click carving: Segmenting objects in video with point clicks, Proceedings of the Fourth AAAI Conference on Human Computation and Crowdsourcing, 10.1609/hcomp.v4i1.13288 · DOI
  6. 10.1109/CVPR.2015.7298965 · DOI · Paper page
  7. 10.1109/TPAMI.2011.131 · DOI · Paper page
  8. lin, 2014, Microsoft COCO: Common objects in context, ECCV
  9. 10.1109/TPAMI.2005.151 · DOI · Paper page
  10. 10.1109/CVPR.2015.7299002 · DOI
  11. 10.1109/ICRA.2015.7139439 · DOI
  12. 10.1109/CVPR.2012.6248101 · DOI · Paper page
  13. 10.1109/CVPR.2017.544 · DOI · Paper page
  14. ion, 2011, Probabilistic joint image segmentation and labeling, NIPS, 1827
  15. heitz, 2008, Learning spatial context: Using stuff to find things, ECCV
  16. ionescu, 2015, Training deep networks with structured layers by matrix backpropagation, ICCV
  17. adelson, 2001, On seeing stuff: The perception of materials by humans and machines, SPIE Proceedings Series, 1
  18. 10.1109/TPAMI.2012.120 · DOI · Paper page
  19. 10.1023/B:VISI.0000022288.19776.77 · DOI · Paper page
  20. galasso, 2012, Video segmentation with superpixels, ACCV
  21. forsyth, 1996, Finding pictures of objects in large collections of images, Int Workshop on Object Representations for Computer Vision, 10.1007/3-540-61750-7_36 · DOI
  22. 10.1109/ICCV.2009.5459211 · DOI · Paper page
  23. hariharan, 2014, Simultaneous detection and segmentation, ECCV
  24. tighe, 2010, Superparsing: Scalable nonparametric image parsing with superpixels, ECCV
  25. 10.1109/CVPR.2013.386 · DOI
  26. xiao, 2014, SUN database: Exploring a large collection of scene categories, IJCV, 1
  27. 10.1016/j.cviu.2013.10.013 · DOI
  28. 10.1109/CVPR.2015.7298788 · DOI
  29. 10.1007/s11263-013-0620-5 · DOI · Paper page
  30. 10.3115/1073445.1073478 · DOI · Paper page
  31. 10.1109/CVPR.2014.479 · DOI
  32. 10.1007/s11263-012-0574-z · DOI
  33. 10.1109/CVPR.2017.477 · DOI · Paper page
  34. pont-tuset, 2015, Semiautomatic video object segmentation by advanced manipulation of segmentation hierarchies, International Workshop on Content-Based Multimedia Indexing
  35. 10.1109/CVPR.2015.7299025 · DOI · Paper page
  36. dana, 1999, Reflectance and texture of real-world surfaces, ACM Transactions on Graphics (TOG), 18, 1, 10.1145/300776.300778 · DOI · Paper page
  37. 10.1109/ICCV.2015.304 · DOI · Paper page
  38. 10.1109/TPAMI.2013.122 · DOI
  39. bell, 2013, OpenSur-faces: A richly annotated catalog of surface appearance, SIGGRAPH, 10.1145/2461912.2462002 · DOI
  40. bearman, 2016, What's the point: Semantic segmentation with point supervision, ECCV
  41. brodatz, 1966, Textures A Photographic Album for Artists and Designers
  42. caesar, 2016, Region-based semantic segmentation with end-to-end training, ECCV
  43. 10.1016/j.patrec.2008.04.005 · DOI · Paper page
  44. 10.1109/ICCV.2017.97 · DOI · Paper page
  45. 10.1016/j.imavis.2009.05.005 · DOI
  46. shotton, 2006, Texton-Boost: Joint appearance, shape and context modeling for multi-class object recognition and segmentation, ECCV
  47. 10.1109/ICCV.2017.366 · DOI
  48. simonyan, 2015, Very deep convolutional networks for large-scale image recognition, ICLRE
  49. 10.1145/1186562.1015720 · DOI · Paper page
  50. 10.1109/ICCV.2007.4408986 · DOI · Paper page
  51. sharan, 2014, Material perception: What can you see in a brief glance?, Journal of Vision, 14

Cited by

See all 1,277

Metadata

Authors
Caesar, H., Uijlings, J., & Ferrari, V.
Venue
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Publisher
IEEE
Published
2018-06
Pages
1209-1218
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr.2018.00132
OpenAlex
W2561196672
Cited by
1,277
References
12
FWCI
29.08
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: COCO-Stuff: Thing and Stuff Classes in Context. https://app.cochat.ai/papers/10.1109/cvpr.2018.00132
The paper
Caesar, H., Uijlings, J., & Ferrari, V. (2018). COCO-Stuff: Thing and Stuff Classes in Context. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. https://doi.org/10.1109/cvpr.2018.00132

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.