CoChat

Stacked Spatio-Temporal Graph Convolutional Networks for Action Segmentation

Open access
Ghosh, Pallabi, Yao, Yi, Davis, Larry S., Divakaran, Ajay · 2020 · 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)
Cited by 88

The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.

Abstract

We propose novel Stacked Spatio-Temporal Graph Convolutional Networks (Stacked-STGCN) for action segmentation, i.e., predicting and localizing a sequence of actions over long videos. We extend the Spatio-Temporal Graph Convolutional Network (STGCN) originally proposed for skeleton-based action recognition to enable nodes with different characteristics (e.g., scene, actor, object, action), feature descriptors with varied lengths, and arbitrary temporal edge connections to account for large graph deformation commonly associated with complex activities. We further introduce the stacked hourglass architecture to STGCN to leverage the advantages of an encoder-decoder design for improved generalization performance and localization accuracy. We explore various descriptors such as frame- level VGG, segment-level I3D, RCNN-based object, etc. as node descriptors to enable action segmentation based on joint inference over comprehensive contextual information. We show results on CAD120 (which provides pre-computed node features and edge weights for fair performance comparison across algorithms) as well as a more complex real- world activity dataset, Charades. Our Stacked-STGCN in general achieves improved performance over the state-of- the-art for both CAD120 and Charades. Moreover, due to its generic design, Stacked-STGCN can be applied to a wider range of applications that require structured inference over long sequences with heterogeneous data types and varied temporal extent.

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/wacv45572.2020.9093361

Cites

16 of 16 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

Show all 16 references

Research works printed but not linked: 36

  1. 10.1109/CVPR.2018.00627 · DOI
  2. 10.1007/978-3-030-01240-3_25 · DOI · Paper page
  3. 10.1109/CVPR.2014.85 · DOI · Paper page
  4. piergiovanni, 2018, Learning latent superevents to detect multiple activities in videos, Proceedings ofthe IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 4
  5. richard, 2016, Temporal action detection using a statisticallanguage model, Conference on Computer Vision and Pattern Recognition IEEE
  6. ren, 2015, Faster r-cnn: Towards real-time object detection with region proposal networks, Advances in neural information processing systems, 91
  7. 10.1109/ICCV.2017.590 · DOI · Paper page
  8. qi, 2018, Learning human-object interactions by graph parsing neural networks, Proceedings of the European Conference on Computer Vision (ECCV), 401
  9. 10.1109/WACV.2018.00174 · DOI
  10. 10.1007/s11042-011-0858-2 · DOI
  11. atwood, 2016, Diffusion-convolutional neural networks, Advances in neural information processing systems, 1993
  12. 10.1177/0278364913478446 · DOI · Paper page
  13. 10.1109/ICCV.2017.448 · DOI · Paper page
  14. 10.1007/978-3-030-01246-5_21 · DOI · Paper page
  15. 10.1109/CVPR.2018.00675 · DOI · Paper page
  16. zhang, 2017, Deep spatio-temporal residual networks for citywide crowd flows prediction, AAAI, 1655
  17. 10.1109/CVPR.2016.597 · DOI · Paper page
  18. 10.1109/CVPRW.2017.253 · DOI · Paper page
  19. yan, 2018, Spatial temporal graph convolutional networks for skeleton-based action recognition, AAAI, 10.1609/aaai.v32i1.12328 · DOI · Paper page
  20. 10.1109/ICCV.2017.617 · DOI · Paper page
  21. 10.1109/ICIP.2018.8451364 · DOI
  22. wang, 2018, Videos as space-time region graphs, 10.1007/978-3-030-01228-1_25 · DOI · Paper page
  23. wang, 2016, Temporal segment networks: Towards good practices for deep action recognition, European Conference on Computer Vision, 20
  24. ding, 2018, Video action segmentation with hybrid temporal networks
  25. 10.1109/WI.2005.67 · DOI · Paper page
  26. 10.1007/978-3-030-01246-5_40 · DOI
  27. 10.1016/j.acha.2010.04.005 · DOI · Paper page
  28. bruna, 2017, Community detection with graph neural networks
  29. blier, 2018, The description length of deep learning models, NIPS
  30. 10.1109/UMEDIA.2017.8074105 · doi:10.1109/umedia.2017.8074105
  31. defferrard, 2016, Convolutional neural networks on graphs with fast localized spectral filtering, Advances in neural information processing systems, 3844
  32. dave, 2017, Predictivecor- rective networks for action detection, Proceedings of the Computer Vision and Pattern Recognition
  33. sigurdsson, 2016, Hollywood in homes: Crowdsourcing data collection for activity understanding, European Conference on Computer Vision
  34. 10.1109/CVPR.2018.00772 · DOI · Paper page
  35. 10.1109/CVPR.2017.599 · DOI · Paper page
  36. 10.1109/CCPR.2008.92 · doi:10.1109/ccpr.2008.92

Cited by

See all 88

Metadata

Authors
Ghosh, P., Yao, Y., Davis, L. S., & Divakaran, A.
Venue
2020 IEEE Winter Conference on Applications of Computer Vision (WACV)
Publisher
IEEE
Published
2020-03
Pages
565-574
ISSN
2472-6737 (ISSN-L)
OpenAlex
W2901213409
Cited by
88
References
16
FWCI
4.22
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: Stacked Spatio-Temporal Graph Convolutional Networks for Action Segmentation. https://app.cochat.ai/papers/10.1109/wacv45572.2020.9093361
The paper
Ghosh, P., Yao, Y., Davis, L. S., & Divakaran, A. (2020). Stacked Spatio-Temporal Graph Convolutional Networks for Action Segmentation. 2020 IEEE Winter Conference on Applications of Computer Vision (WACV). https://doi.org/10.1109/wacv45572.2020.9093361

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.