CoChat

Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization

Liu, Daochang, Jiang, Tingting, Wang, Yizhou · 2019 · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Cited by 247

The DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.

Abstract

Temporal action localization is crucial for understanding untrimmed videos. In this work, we first identify two underexplored problems posed by the weak supervision for temporal action localization, namely action completeness modeling and action-context separation. Then by presenting a novel network architecture and its training strategy, the two problems are explicitly looked into. Specifically, to model the completeness of actions, we propose a multi-branch neural network in which branches are enforced to discover distinctive action parts. Complete actions can be therefore localized by fusing activations from different branches. And to separate action instances from their surrounding context, we generate hard negative data for training using the prior that motionless video clips are unlikely to be actions. Experiments performed on datasets THUMOS'14 and ActivityNet show that our framework outperforms state-of-the-art methods. In particular, the average mAP on ActivityNet v1.2 is significantly improved from 18.0% to 22.4%. Our code will be released soon.

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.2019.00139

Cites

15 of 15 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: 39

  1. 10.1109/CVPR.2016.119 · DOI · Paper page
  2. 10.1007/978-3-030-01270-0_10 · DOI · Paper page
  3. 10.1109/CVPR.2018.00706 · DOI · Paper page
  4. 10.1007/978-3-030-01225-0_1 · DOI · Paper page
  5. 10.1145/3123266.3123343 · DOI · Paper page
  6. 10.1109/CVPR.2017.155 · DOI · Paper page
  7. paul, 2018, WTALC: Weakly-supervised temporal activity localization and classification, the European Conference on Computer Vision (ECCV)
  8. paszke, 2017, Automatic differentiation in PyTorch, NIPS-W
  9. 10.1109/ICCV.2013.228 · DOI · Paper page
  10. lee, 2012, Discovering important people and objects for egocentric video summarization, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1346
  11. li, 2018, Diversity regularized spatiotemporal attention for videobased person re-identification, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 10.1007/978-3-030-03398-9 · doi:10.1007/978-3-030-03398-9
  12. 10.1007/978-3-030-01240-3_16 · DOI
  13. 10.1145/1922649.1922653 · DOI · Paper page
  14. hou, 2017, Real-time temporal action localization in untrimmed videos by subaction discovery, Proceedings of the British Machine Vision Conference (BMVC), 2, 7
  15. kang, 2016, Review of action recognition and detection methods, arXiv preprint arXiv 1610 09756
  16. 10.1016/j.cviu.2016.10.018 · DOI · Paper page
  17. 10.1007/s11263-005-1838-7 · DOI · Paper page
  18. zhou, 2004, Multi-instance learning: A survey Department of Computer Science & Technology, Nanjing University, Tech Rep
  19. zhou, 2018, Temporal relational reasoning in videos, the European Conference on Computer Vision (ECCV)
  20. 10.1145/3240508.3240511 · DOI
  21. simonyan, 2014, Two-stream convolutional networks for action recognition in videos, Advances in Neural Information Processing Systems (NIPS), 568
  22. 10.1109/CVPR.2015.7298878 · DOI · Paper page
  23. 10.1109/ICCV.2009.5459279 · DOI · Paper page
  24. 10.1007/978-3-319-46487-9_52 · DOI
  25. gao, 2017, Cascaded boundary regression for temporal action detection, Proceedings of the British Machine Vision Conference (BMVC)
  26. gao, 2014, JHU-ISI gesture and skill assessment working set (JIGSAWS): A surgical activity dataset for human motion modeling, MICCAI Workshop M2CAI, 3, 3
  27. 10.1109/CVPR.2015.7298676 · DOI · Paper page
  28. goodfellow, 2014, Generative adversarial nets, Advances in Neural Information Processing Systems (NIPS), 2672
  29. 10.1016/j.imavis.2017.01.010 · DOI · Paper page
  30. 10.1109/FG.2017.150 · DOI · Paper page
  31. 10.1109/CVPR.2017.338 · DOI
  32. 10.1109/CVPR.2018.00124 · DOI · Paper page
  33. 10.1109/CVPR.2017.342 · DOI
  34. 10.1109/ICCV.2017.610 · DOI · Paper page
  35. wang, 2016, Temporal segment networks: Towards good practices for deep action recognition, the European Conference on Computer Vision (ECCV), 20
  36. 10.1109/CVPR.2017.678 · DOI · Paper page
  37. 10.1109/ICCV.2017.617 · DOI · Paper page
  38. 10.1007/s00371-012-0752-6 · DOI · Paper page
  39. 10.1109/CVPR.2018.00155 · DOI · Paper page

Cited by

See all 247

Metadata

Authors
Liu, D., Jiang, T., & Wang, Y.
Venue
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2019-06
Pages
1298-1307
ISSN
1063-6919 (ISSN-L)
OpenAlex
W2948229620
Cited by
247
References
15
FWCI
12.82
Type
conference paper
Language
en
Open access
closed

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.