Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 185

The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.

What do 15,000 object categories tell us about classifying and localizing actions?

Open access
Jain, Mihir, van Gemert, Jan C., Snoek, Cees G. M.·2015·2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Abstract

This paper contributes to automatic classification and localization of human actions in video. Whereas motion is the key ingredient in modern approaches, we assess the benefits of having objects in the video representation. Rather than considering a handful of carefully selected and localized objects, we conduct an empirical study on the benefit of encoding 15,000 object categories for action using 6 datasets totaling more than 200 hours of video and covering 180 action classes. Our key contributions are i) the first in-depth study of encoding objects for actions, ii) we show that objects matter for actions, and are often semantically relevant as well. iii) We establish that actions have object preferences. Rather than using all objects, selection is advantageous for action recognition. iv)We reveal that object-action relations are generic, which allows to transferring these relationships from the one domain to the other. And, v) objects, when combined with motion, improve the state-of-the-art for both action classification and localization.

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.2015.7298599

Cites

4 of 4 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 4 references

Research works printed but not linked: 55

  1. 10.1109/ICPR.2004.1334462 · DOI · Paper page
  2. 10.1109/CVPR.2012.6247806 · DOI · Paper page
  3. peng, 2014, Action recognition with stacked fisher vectors, ECCV
  4. peng, 2014, Boosting vlad with supervised dictionary learning and high-order statistics, ECCV
  5. oneata, 2014, The LEAR submission at Thumos 2014, ECCV workshop
  6. 10.1109/ICCV.2013.228 · DOI · Paper page
  7. 10.1109/CVPR.2008.4587727 · DOI · Paper page
  8. ramanan, 2003, Automatic annotation of everyday movements, NIPS
  9. 10.1109/TPAMI.2011.158 · DOI · Paper page
  10. perronnin, 2010, Improving the fisher kernel for large-scale image classification, ECCV
  11. 10.1109/ICCV.2013.442 · DOI
  12. 10.1109/ICCVW.2009.5457659 · DOI · Paper page
  13. 10.1109/CVPR.2009.5206557 · DOI · Paper page
  14. oneata, 2014, Spatiotemporal object detection proposals, ECCV
  15. 10.1109/CVPR.2010.5539875 · DOI · Paper page
  16. 10.1109/CVPR.2014.83 · DOI · Paper page
  17. lan, 2011, Discriminative figure-centric models for joint action localization and recognition, ICCV
  18. 10.1109/CVPR.2008.4587756 · DOI · Paper page
  19. 10.1109/ICCV.2003.1238378 · DOI · Paper page
  20. 10.1109/CVPR.2011.5995353 · DOI · Paper page
  21. li, 2012, Recognizing activities by attribute dynamics, NIPS
  22. 10.1109/CVPR.2011.5995407 · DOI · Paper page
  23. zeiler, 2014, Visualizing and understanding convolutional networks, ECCV
  24. 10.1109/ICCV.2011.6126386 · DOI · Paper page
  25. 10.1109/CVPR.2010.5540235 · DOI · Paper page
  26. 10.1109/CVPR.2011.5995624 · DOI · Paper page
  27. 10.1109/CVPR.2014.330 · DOI
  28. willems, 2008, An efficient dense and scale-invariant spatio-temporal interest point detector, ECCV
  29. 10.1109/ICCV.2013.333 · DOI
  30. wang, 2013, LEAR-INRIA submission for the THUMOS workshop, ICCV Workshop
  31. 10.1109/CVPR.2007.383331 · DOI · Paper page
  32. han, 2009, Selection and context for action recognition, ICCV
  33. 10.1109/CVPR.2013.335 · DOI
  34. hoai, 2014, Improving human action recognition using score distribution and ranking, ACCV
  35. ikizler-cinbis, 2010, Object, scene and actions: Combining multiple features for human action recognition, ECCV
  36. 10.1109/CVPR.2013.330 · DOI · Paper page
  37. 10.1109/CVPR.2014.100 · DOI · Paper page
  38. jain, 2014, University of Amsterdam at THUMOS Challenge 2014, ECCV workshop
  39. jiang, 2012, Trajectory-based modeling of human actions with motion reference points, ECCV
  40. khiser, 2008, A spatio-temporal descriptor based on 3d-gradients, BMVC
  41. dalal, 0, Human detection using oriented histograms of flow and appearance, ECCV 2006
  42. chatfield, 2014, Return of the devil in the details: Delving deep into convolutional nets, BMVC
  43. deng, 2010, What does classifying more than 10,000 image categories tell us, ECCV
  44. 10.1109/CVPR.2015.7299176 · DOI · Paper page
  45. 10.1109/TIP.2014.2302677 · DOI
  46. 10.1007/978-3-319-10602-1_28 · DOI
  47. 10.5244/C.26.30 · DOI
  48. 10.5244/C.24.95 · DOI
  49. 10.5244/C.22.30 · DOI
  50. vig, 2012, Space-variant descriptor sampling for action recognition based on saliency and eye movements, ECCV
  51. varol, 0, Extreme Learning Machine for Large-Scale Action Recognition, ECCV workshop 2014
  52. 10.1007/978-3-319-10599-4_27 · DOI
  53. soomro, 2012, UCF 101: A dataset of 101 human actions classes from videos in the wild, CoRR
  54. 10.1109/CVPR.2013.341 · DOI · Paper page
  55. 10.1109/ICCV.2013.453 · DOI

Cited by

See all 185

Metadata

Authors
Jain, M., van Gemert, J. C., & Snoek, C. G. M.
Venue
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2015-06
Pages
46-55
ISSN
1063-6919 (ISSN-L)
OpenAlex
W2095242101
Cited by
185
References
4
FWCI
16.49
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: What do 15,000 object categories tell us about classifying and localizing actions? https://app.cochat.ai/papers/10.1109/cvpr.2015.7298599
The paper
Jain, M., van Gemert, J. C., & Snoek, C. G. M. (2015). What do 15,000 object categories tell us about classifying and localizing actions? 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr.2015.7298599

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.