Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 968

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

Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs

Open access
Shou, Zheng, Wang, Dongang, Chang, Shih-Fu·2016·2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr.2016.119
Open this paper in CoChat — free account

Abstract

We address temporal action localization in untrimmed long videos. This is important because videos in real applications are usually unconstrained and contain multiple action instances plus video content of background scenes or other activities. To address this challenging issue, we exploit the effectiveness of deep networks in temporal action localization via three segment-based 3D ConvNets: (1) a proposal network identifies candidate segments in a long video that may contain actions, (2) a classification network learns one-vs-all action classification model to serve as initialization for the localization network, and (3) a localization network fine-tunes the learned classification network to localize each action instance. We propose a novel loss function for the localization network to explicitly consider temporal overlap and achieve high temporal localization accuracy. In the end, only the proposal network and the localization network are used during prediction. On two largescale benchmarks, our approach achieves significantly superior performances compared with other state-of-the-art systems: mAP increases from 1.7% to 7.4% on MEXaction2 and increases from 15.0% to 19.0% on THUMOS 2014.

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.2016.119

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.

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

Research works printed but not linked: 38

  1. 10.1109/CVPR.2011.5995407 · DOI · Paper page
  2. van gemert, 2015, Apt: Action localization proposals from dense trajectories, BMVC
  3. 10.1109/ICCV.2015.375 · DOI
  4. simonyan, 2015, Very deep convolutional networks for large-scale image recognition, International Conference on Learning Representations
  5. simonyan, 2014, Two-stream convolutional networks for action recognition in videos, NIPS
  6. 10.1145/2733373.2806226 · DOI
  7. stoian, 2015, Fast action localization in large scale video archives, TCSVT
  8. soomro, 2012, UCF101: A dataset of 101 human actions classes from videos in the wild, CRCV-TR-12–01
  9. 10.1109/CVPR.2014.100 · DOI
  10. 10.1109/CVPR.2015.7298599 · DOI
  11. 10.1109/TPAMI.2012.59 · DOI · Paper page
  12. 10.1145/2647868.2654889 · DOI · Paper page
  13. jiang, 2014, THUMOS Challenge Action Recognition with A Large Number of Classes
  14. 10.1016/j.cviu.2012.09.008 · DOI
  15. karaman, 2014, Fast saliency based pooling of fisher encoded dense trajectories, ECCV THUMOS Workshop
  16. 10.1007/978-3-642-35749-7_17 · DOI
  17. 10.1109/CVPR.2011.5995646 · DOI
  18. oneata, 2014, The lear submission at thumos 2014, ECCV THUMOS Workshop
  19. cheng, 2015, Advances in human action recognition A Survey
  20. 10.1109/ICCV.2015.193 · DOI
  21. 10.1109/TPAMI.2013.65 · DOI
  22. 10.1109/CVPR.2015.7298676 · DOI · Paper page
  23. 10.1109/CVPR.2014.81 · DOI · Paper page
  24. 10.1145/1922649.1922653 · DOI · Paper page
  25. gorban, 2015, THUMOS Challenge Action Recognition with A Large Number of Classes
  26. 2015, Mexaction2
  27. yuan, 2015, Adsc submission at thumos challenge 2015, CVPR THUMOS Workshop
  28. 10.1109/CVPR.2015.7298735 · DOI
  29. lai, 2014, Recognizing complex events in videos by learning key static-dynamic evidences, ECCV
  30. 10.1109/ICCV.2015.285 · DOI
  31. 10.1016/j.cviu.2010.10.002 · DOI · Paper page
  32. lan, 2015, Beyond gaussian pyramid: Multi-skip feature stacking for action recognition, CVPR
  33. wang, 2014, Action recognition and detection by combining motion and appearance features, ECCV THUMOS Workshop
  34. 10.1109/CVPR.2014.288 · DOI
  35. 10.1109/CVPR.2015.7298789 · DOI · Paper page
  36. 10.1109/CVPR.2014.326 · DOI
  37. 10.1109/ICCV.2015.362 · DOI · Paper page
  38. 10.1109/ICCV.2013.228 · DOI · Paper page

Cited by

See all 968

Metadata

Authors
Shou, Z., Wang, D., & Chang, S.-F.
Venue
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2016-06
Pages
1049-1058
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr.2016.119
OpenAlex
W2964214371
Cited by
968
References
8
FWCI
33.48
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.