Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 551

The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.

Graph Convolutional Networks for Temporal Action Localization

Open access
Zeng, Runhao, Huang, Wenbing, Gan, Chuang, Tan, Mingkui, Rong, Yu, Zhao, Peilin, Huang, Junzhou·2019·2019 IEEE/CVF International Conference on Computer Vision (ICCV)
DOI 10.1109/iccv.2019.00719
Open this paper in CoChat — free account

Abstract

Most state-of-the-art action localization systems process each action proposal individually, without explicitly exploiting their relations during learning. However, the relations between proposals actually play an important role in action localization, since a meaningful action always consists of multiple proposals in a video. In this paper, we propose to exploit the proposal-proposal relations using GraphConvolutional Networks (GCNs). First, we construct an action proposal graph, where each proposal is represented as a node and their relations between two proposals as an edge. Here, we use two types of relations, one for capturing the context information for each proposal and the other one for characterizing the correlations between distinct actions. Then we apply the GCNs over the graph to model the relations among different proposals and learn powerful representations for the action classification and localization. Experimental results show that our approach significantly outperforms the state-of-the-art on THUMOS14(49.1% versus 42.8%). Moreover, augmentation experiments on ActivityNet also verify the efficacy of modeling action proposal relationships.

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/iccv.2019.00719

Cites

13 of 13 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

Show all 13 references

Research works printed but not linked: 40

  1. vaswani, 2017, Attention is all you need, Advances in neural information processing systems, 5998
  2. 10.1109/CVPR.2017.155 · DOI · Paper page
  3. shen, 2018, Person re-identification with deep similarity-guided graph neural network, The European Conference on Computer Vision
  4. 10.1109/CVPR.2015.7299037 · DOI
  5. singh, 2016, Untrimmed video classification for activity detection: submission to activitynet challenge, ActivityNet Large Scale Activity Recognition Challenge
  6. simonyan, 2014, Two-stream convolutional networks for action recognition in videos, Advances in neural information processing systems, 568
  7. 10.1109/CVPR.2016.119 · DOI · Paper page
  8. montes, 2016, Temporal activity detection in untrimmed videos with recurrent neural networks, 1st NIPS Workshop on Large Scale Computer Vision Systems
  9. lin, 0, Bsn: Boundary sensitive network for temporal action proposal generation, The European Conference on Computer Vision
  10. 10.1109/CVPR.2017.675 · DOI · Paper page
  11. 10.1109/CVPR.2018.00378 · DOI · Paper page
  12. hou, 2017, Real-time temporal action localization in untrimmed videos by subaction discovery, BMVC
  13. huang, 2018, Adaptive sampling towards fast graph representation learning, Advances in neural information processing systems, 4558
  14. 10.1145/3123266.3123343 · DOI · Paper page
  15. kipf, 2017, Semi-supervised classification with graph convolutional networks, International Conference on Learning Representations
  16. 10.1109/CVPR.2017.342 · DOI
  17. 10.1109/TIP.2019.2922108 · DOI
  18. zhuang, 2018, Discrimination-aware channel pruning for deep neural networks, Advances in neural information processing systems, 875
  19. 10.1109/ICCV.2017.317 · DOI · Paper page
  20. duan, 2018, Weakly supervised dense event captioning in videos, Advances in neural information processing systems, 3059
  21. escorcia, 2016, Daps: Deep action proposals for action understanding, Proceedings of the European Conference on Computer Vision, 768
  22. wang, 2014, Action recognition and detection by combining motion and appearance features, THUMOS14 Action Recognition Challenge, 1, 2
  23. 10.1109/CVPR.2018.00630 · DOI
  24. 10.1109/CVPR.2018.00586 · DOI
  25. 10.1109/CVPR.2015.7298872 · DOI · Paper page
  26. 10.1007/s11263-016-0893-6 · DOI
  27. 10.1109/CVPR.2016.106 · DOI
  28. gao, 2017, Cascaded boundary regression for temporal action detection, BMVC
  29. 10.1109/TMM.2019.2908352 · DOI
  30. 10.1109/CVPR.2016.211 · DOI · Paper page
  31. 10.1109/CVPR.2018.00124 · DOI · Paper page
  32. 10.1109/ICCV.2017.610 · DOI · Paper page
  33. chen, 2018, Fastgcn: fast learning with graph convolutional networks via importance sampling, International Conference on Learning Representations
  34. 10.1109/CVPR.2016.337 · DOI
  35. 10.1109/CVPR.2018.00808 · DOI
  36. 10.1109/ICCV.2017.617 · DOI · Paper page
  37. wang, 2018, Videos as space-time region graphs, The European Conference on Computer Vision
  38. wang, 2016, Temporal segment networks: Towards good practices for deep action recognition, Proceedings of the European Conference on Computer Vision, 20
  39. 10.1109/CVPR.2017.678 · DOI · Paper page
  40. wang, 2016, Uts at activitynet 2016, ActivityNet Large Scale Activity Recognition Challenge

Cited by

Metadata

Authors
Zeng, R., Huang, W., Gan, C., Tan, M., Rong, Y., Zhao, P., & Huang, J.
Venue
2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2019-10
Pages
7093-7102
DOI
10.1109/iccv.2019.00719
OpenAlex
W2986407524
Cited by
551
References
13
FWCI
25.13
Type
conference paper
Language
en
Open access
green
Licence

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.