Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 783

The DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.

R-C3D: Region Convolutional 3D Network for Temporal Activity Detection

Open access
Xu, Huijuan, Das, Abir, Saenko, Kate·2017·2017 IEEE International Conference on Computer Vision (ICCV)
DOI 10.1109/iccv.2017.617
Open this paper in CoChat — free account

Abstract

We address the problem of activity detection in continuous, untrimmed video streams. This is a difficult task that requires extracting meaningful spatio-temporal features to capture activities, accurately localizing the start and end times of each activity. We introduce a new model, Region Convolutional 3D Network (R-C3D), which encodes the video streams using a three-dimensional fully convolutional network, then generates candidate temporal regions containing activities, and finally classifies selected regions into specific activities. Computation is saved due to the sharing of convolutional features between the proposal and the classification pipelines. The entire model is trained end-to-end with jointly optimized localization and classification losses. R-C3D is faster than existing methods (569 frames per second on a single Titan X Maxwell GPU) and achieves state-of-the-art results on THUMOS'14. We further demonstrate that our model is a general activity detection framework that does not rely on assumptions about particular dataset properties by evaluating our approach on ActivityNet and Charades. Our code is available at http://ai.bu.edu/r-c3d/.

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.2017.617

Cites

12 of 12 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 12 references

Research works printed but not linked: 32

  1. 10.1109/ICCV.2015.362 · DOI · Paper page
  2. szegedy, 2013, Deep Neural Networks for Object Detection, Neural Information Processing Systems, 2553
  3. singh, 2016, Untrimmed video classification for activity detection submission to activitynet challenge
  4. wang, 2014, Action Recognition and Detection's by Combining Motion and Appearance Features, ECCV THUMOS Workshop
  5. 10.1109/CVPR.2017.678 · DOI · Paper page
  6. wang, 2016, Actionness Estimation using Hybrid's Fully Convolutional Networks, IEEE Conference on Computer Vision and Pattern Recognition, 2708
  7. wang, 2014, Video Action Detection with Relational Dynamic-Poselets, European Conference on Computer Vision, 565
  8. 10.1109/CVPR.2016.211 · DOI · Paper page
  9. 10.1109/CVPR.2015.7298735 · DOI
  10. 10.1109/TPAMI.2012.59 · DOI · Paper page
  11. jiang, 2014, THUMOS Challenge Action Recognition with A Large Number of Classes
  12. karaman, 2014, Fast Saliency Based Pooling of Fisher Encoded Dense Trajectories, ECCV THUMOS Workshop
  13. 10.1109/CVPR.2008.4587756 · DOI
  14. liu, 2016, SSD: Single Shot MultiBox Detector, European Conference on Computer Vision, 21
  15. 10.1109/CVPR.2016.214 · DOI · Paper page
  16. montes, 2016, Temporal activity detection in untrimmed videos with recurrent neural networks
  17. ng, 2015, Beyond Short Snippets: Deep Networks for Video Classification, IEEE Conference on Computer Vision and Pattern Recognition, 4694
  18. simonyan, 2015, Very Deep Convolutional Networks for Large-scale Image Recognition, IEEE Conference on Learning Representations
  19. 10.1007/978-3-319-46487-9_47 · DOI · Paper page
  20. simonyan, 2014, Two-stream Convolutional Networks for Action Recognition in Videos, Neural Information Processing Systems, 568
  21. dai, 2016, R-FCN: Object Detection via Region-based Fully Convolutional Networks, Neural Information Processing Systems, 379
  22. girshick fast r-cn, 2015, IEEE International Conference on Computer Vision, 1440
  23. 10.1109/CVPR.2014.81 · DOI · Paper page
  24. 10.1109/TPAMI.2011.231 · DOI · Paper page
  25. 2016, ActivitNet Large Scale Activity Recognition Challenge
  26. oneata, 2014, The LEAR submission at Thumos 2014, ECCV THUMOS Workshop
  27. 10.1109/TIP.2016.2548242 · DOI
  28. 10.1109/CVPR.2016.119 · DOI · Paper page
  29. 10.1109/CVPR.2016.337 · DOI
  30. 10.1109/CVPR.2017.155 · DOI · Paper page
  31. 10.1007/978-3-319-46448-0_31 · DOI · Paper page
  32. sigurdsson, 0, Asynchronous temporal fields for action recognition

Cited by

Metadata

Authors
Xu, H., Das, A., & Saenko, K.
Venue
2017 IEEE International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2017-10
Pages
5794-5803
DOI
10.1109/iccv.2017.617
OpenAlex
W2963247196
Cited by
783
References
12
FWCI
24.83
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.