Stacked Spatio-Temporal Graph Convolutional Networks for Action Segmentation
Open accessThe 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.
Integrity signals
Registry
Cites
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.
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
The graph neural network model
Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M., & Monfardini, G. (2009) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2008.2005605 · Cited by 9,582 · cited 2×
“GNNs have been used in a number of different applications like situation recognition [24], human-object interaction [25], webpage ranking[39, 40], mutagenesis[39], etc.”
BackgroundMethodQuo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Carreira, J., & Zisserman, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.502 · Cited by 9,570
Two-Stream Convolutional Networks for Action Recognition in Videos
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1406.2199 · Cited by 6,756
Stacked Hourglass Networks for Human Pose Estimation
Newell, A., Yang, K., & Deng, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46484-8_29 · Cited by 5,634 · cited 2×
“They have also been shown to work well for tasks such as human pose estimation [29], facial landmark localization [57], etc.”
BackgroundModeling Relational Data with Graph Convolutional Networks
Schlichtkrull, M., Kipf, T. N., Bloem, P., van den Berg, R., Titov, I., & Welling, M. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-93417-4_38 · Cited by 5,570
A Closer Look at Spatiotemporal Convolutions for Action Recognition
Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., & Paluri, M. (2017) · arXiv · doi:10.48550/arxiv.1711.11248 · Cited by 3,664 · cited 1×
“Since the development of two-stream [47] and 3D convolution architecture, a series of works were studied, including TSN [52], ST-ResNet [59], I3D [5], P3D [35], R(1+2)D [51], T3D [9], S3D [54], TGM [31], etc.”
MethodNTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis
Shahroudy, A., Liu, J., Ng, T.-T., & Wang, G. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.115 · Cited by 3,148
Convolutional Networks on Graphs for Learning Molecular Fingerprints
Duvenaud, D., Maclaurin, D., Aguilera-Iparraguirre, J., Gómez-Bombarelli, R., Hirzel, T., Aspuru-Guzik, A., & Adams, R. P. (2015) · arXiv · doi:10.48550/arxiv.1509.09292 · Cited by 2,628
Temporal Convolutional Networks for Action Segmentation and Detection
Lea, C., Flynn, M. D., Vidal, R., Reiter, A., & Hager, G. D. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.113 · Cited by 2,238 · cited 1×
“proposed temporal convolutional networks (TCNs) [22].”
Structural-RNN: Deep Learning on Spatio-Temporal Graphs
Jain, A., Zamir, A. R., Savarese, S., & Saxena, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.573 · Cited by 1,133 · cited 11×
“Our STGCN outperforms the S-RNN by about 4 .”
MethodInfluential
Research works printed but not linked: 36
- 10.1109/CVPR.2018.00627 · DOI
- 10.1007/978-3-030-01240-3_25 · DOI · Paper page
- 10.1109/CVPR.2014.85 · DOI · Paper page
- piergiovanni, 2018, Learning latent superevents to detect multiple activities in videos, Proceedings ofthe IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 4
- richard, 2016, Temporal action detection using a statisticallanguage model, Conference on Computer Vision and Pattern Recognition IEEE
- ren, 2015, Faster r-cnn: Towards real-time object detection with region proposal networks, Advances in neural information processing systems, 91
- 10.1109/ICCV.2017.590 · DOI · Paper page
- qi, 2018, Learning human-object interactions by graph parsing neural networks, Proceedings of the European Conference on Computer Vision (ECCV), 401
- 10.1109/WACV.2018.00174 · DOI
- 10.1007/s11042-011-0858-2 · DOI
- atwood, 2016, Diffusion-convolutional neural networks, Advances in neural information processing systems, 1993
- 10.1177/0278364913478446 · DOI · Paper page
- 10.1109/ICCV.2017.448 · DOI · Paper page
- 10.1007/978-3-030-01246-5_21 · DOI · Paper page
- 10.1109/CVPR.2018.00675 · DOI · Paper page
- zhang, 2017, Deep spatio-temporal residual networks for citywide crowd flows prediction, AAAI, 1655
- 10.1109/CVPR.2016.597 · DOI · Paper page
- 10.1109/CVPRW.2017.253 · DOI · Paper page
- yan, 2018, Spatial temporal graph convolutional networks for skeleton-based action recognition, AAAI, 10.1609/aaai.v32i1.12328 · DOI · Paper page
- 10.1109/ICCV.2017.617 · DOI · Paper page
- 10.1109/ICIP.2018.8451364 · DOI
- wang, 2018, Videos as space-time region graphs, 10.1007/978-3-030-01228-1_25 · DOI · Paper page
- wang, 2016, Temporal segment networks: Towards good practices for deep action recognition, European Conference on Computer Vision, 20
- ding, 2018, Video action segmentation with hybrid temporal networks
- 10.1109/WI.2005.67 · DOI · Paper page
- 10.1007/978-3-030-01246-5_40 · DOI
- 10.1016/j.acha.2010.04.005 · DOI · Paper page
- bruna, 2017, Community detection with graph neural networks
- blier, 2018, The description length of deep learning models, NIPS
- 10.1109/UMEDIA.2017.8074105 · doi:10.1109/umedia.2017.8074105
- defferrard, 2016, Convolutional neural networks on graphs with fast localized spectral filtering, Advances in neural information processing systems, 3844
- dave, 2017, Predictivecor- rective networks for action detection, Proceedings of the Computer Vision and Pattern Recognition
- sigurdsson, 2016, Hollywood in homes: Crowdsourcing data collection for activity understanding, European Conference on Computer Vision
- 10.1109/CVPR.2018.00772 · DOI · Paper page
- 10.1109/CVPR.2017.599 · DOI · Paper page
- 10.1109/CCPR.2008.92 · doi:10.1109/ccpr.2008.92
Cited by
Multi-Stage Progressive Image Restoration
Zamir, S. W., Arora, A., Khan, S., Hayat, M., Khan, F. S., Yang, M.-H., & Shao, L. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01458 · Cited by 2,095
Representation learning for dynamic graphs: A survey
Kazemi, S. M., Goel, R., Jain, K., Kobyzev, I., Sethi, A., Forsyth, P., & Poupart, P. (2019) · arXiv · doi:10.48550/arxiv.1905.11485 · Cited by 338
“While Li et al. [144] only use human pose features, Ghosh et al. [79] also leverage additional contextual cues such as object features, functional relationships, etc.”
BackgroundSpatio-Temporal Graph for Video Captioning With Knowledge Distillation
Pan, B., Cai, H., Huang, D.-A., Lee, K.-H., Gaidon, A., Adeli, E., & Niebles, J. C. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01088 · Cited by 281
Ryoo, M. S., Gopalakrishnan, K., Kahatapitiya, K., Xiao, T., Rao, K., Stone, A., Lu, Y., Ibarz, J., & Arnab, A. (2022) · arXiv · doi:10.48550/arxiv.2211.09119 · Cited by 21
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.