Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Cited by 167

The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.

Encouraging LSTMs to Anticipate Actions Very Early

Open access
Aliakbarian, Mohammad Sadegh, Saleh, Fatemeh Sadat, Salzmann, Mathieu, Fernando, Basura, Petersson, Lars, Andersson, Lars · 2017 · 2017 IEEE International Conference on Computer Vision (ICCV)

Abstract

In contrast to the widely studied problem of recognizing an action given a complete sequence, action anticipation aims to identify the action from only partially available videos. As such, it is therefore key to the success of computer vision applications requiring to react as early as possible, such as autonomous navigation. In this paper, we propose a new action anticipation method that achieves high prediction accuracy even in the presence of a very small percentage of a video sequence. To this end, we develop a multi-stage LSTM architecture that leverages context-aware and action-aware features, and introduce a novel loss function that encourages the model to predict the correct class as early as possible. Our experiments on standard benchmark datasets evidence the benefits of our approach; We outperform the state-of-the-art action anticipation methods for early prediction by a relative increase in accuracy of 22.0% on JHMDB-21, 14.0% on UT-Interaction and 49.9% on UCF-101.

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/iccv.2017.39

Cites

8 of 8 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

Research works printed but not linked: 40

  1. 10.1109/CVPR.2016.290 · DOI
  2. soomro, 2016, Online localization and prediction of actions and interactions
  3. 10.1109/CVPR.2016.216 · DOI · Paper page
  4. 10.1109/CVPR.2016.18 · DOI · Paper page
  5. van den bergh, 2013, Online video seeds for temporal window objectness, Proceedings of the IEEE International Conference on Computer Vision, 377
  6. soomro, 2012, Ucf101 A Dataset of 101 Human Actions Classes from Videos in the Wild
  7. fernando, 2016, Rank pooling for action recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence
  8. 10.1109/CVPR.2016.296 · DOI
  9. 10.1109/CVPR.2014.100 · DOI · Paper page
  10. 10.1109/ICCV.2013.396 · DOI · Paper page
  11. kong, 2014, A discriminative model with multiple temporal scales for action prediction, European Conference on Computer Vision, 596
  12. 10.1007/s11263-005-1838-7 · DOI · Paper page
  13. laviers, 0, Improving offensive performance through opponent modeling, Proc AAAI Conf Artif Intell Interactive Digit Entertain, 58
  14. 10.1109/CVPR.2016.215 · DOI
  15. lin, 2013, Network in Network
  16. simonyan, 2014, Two-stream convolutional networks for action recognition in videos, Advances in neural information processing systems, 568
  17. saleh, 2016, Built-in foreground/background prior for weakly-supervised semantic segmentation, European Conference on Computer Vision, 413
  18. 10.1109/CVPR.2014.101 · DOI
  19. 10.1109/CVPR.2016.387 · DOI
  20. simonyan, 2014, Very Deep Convolutional Networks for Large-scale Image Recognition
  21. chollet, 2015, Keras
  22. 10.1109/CVPR.2016.213 · DOI · Paper page
  23. 10.1109/CVPR.2015.7298878 · DOI · Paper page
  24. 10.1109/CVPR.2016.331 · DOI · Paper page
  25. 10.1109/CVPR.2016.212 · DOI
  26. 10.1109/CVPR.2015.7299067 · DOI · Paper page
  27. zeiler, 2014, Visualizing and understanding convolutional networks, European Conference on Computer Vision, 818
  28. liu, 2016, Spatio-temporal lstm with trust gates for 3d human action recognition, European Conference on Computer Vision, 816
  29. 10.1145/2393347.2396380 · doi:10.1145/2393347.2396380
  30. 10.1109/CVPR.2016.319 · DOI · Paper page
  31. oneata, 2014, Spatiotemporal object detection proposals, European Conference on Computer Vision, 737
  32. 10.1145/2502081.2502103 · DOI
  33. 10.1109/CVPR.2016.214 · DOI · Paper page
  34. 10.1109/CVPR.2016.291 · DOI · Paper page
  35. ryoo, 2010, An overview of contest on semantic description of human activities (sdha) 2010, Recognizing Patterns in Signals Speech Images and Videos, 270, 10.1007/978-3-642-17711-8_28 · DOI · Paper page
  36. wang, 2016, Temporal segment networks: towards good practices for deep action recognition, European Conference on Computer Vision, 20
  37. 10.1109/CVPR.2015.7298735 · DOI · Paper page
  38. 10.1109/ICCV.2009.5459361 · DOI · Paper page
  39. wu, 2015, Deep image Scaling up image recognition, 7
  40. 10.1109/ICCV.2011.6126349 · DOI · Paper page

Cited by

See all 167

Metadata

Authors
Aliakbarian, M. S., Saleh, F. S., Salzmann, M., Fernando, B., Petersson, L., & Andersson, L.
Venue
2017 IEEE International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2017-10
Pages
280-289
OpenAlex
W2605300166
Cited by
167
References
8
FWCI
5.66
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

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.