Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 2,062

The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.

Beyond short snippets: Deep networks for video classification

Joe Yue-Hei Ng, Hausknecht, Matthew, Vijayanarasimhan, Sudheendra, Vinyals, Oriol, Monga, Rajat, Toderici, George·2015·2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr.2015.7299101
Open this paper in CoChat — free account

Abstract

Convolutional neural networks (CNNs) have been extensively applied for image recognition problems giving state-of-the-art results on recognition, detection, segmentation and retrieval. In this work we propose and evaluate several deep neural network architectures to combine image information across a video over longer time periods than previously attempted. We propose two methods capable of handling full length videos. The first method explores various convolutional temporal feature pooling architectures, examining the various design choices which need to be made when adapting a CNN for this task. The second proposed method explicitly models the video as an ordered sequence of frames. For this purpose we employ a recurrent neural network that uses Long Short-Term Memory (LSTM) cells which are connected to the output of the underlying CNN. Our best networks exhibit significant performance improvements over previously published results on the Sports 1 million dataset (73.1% vs. 60.9%) and the UCF-101 datasets with (88.6% vs. 88.0%) and without additional optical flow information (82.6% vs. 73.0%).

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/cvpr.2015.7299101

Cites

8 of 8 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 8 references

Research works printed but not linked: 20

  1. graves, 2008, Offline handwriting recognition with multidimensional recurrent neural networks, Proc NIPS, 545
  2. 10.1109/CVPR.2013.330 · DOI · Paper page
  3. 10.1109/TPAMI.2012.59 · DOI · Paper page
  4. 10.1109/CVPR.2008.4587756 · DOI
  5. 10.1109/ICASSP.2006.1660362 · DOI
  6. simonyan, 2014, Two-stream convolutional networks for action recognition in videos, Proc NIPS, 568
  7. zeiler, 2014, Visualizing and understanding convolutional networks, Proc ECCV, 818
  8. boureau, 2010, A theoretical analysis of feature pooling in visual recognition, Proc ICML, 111
  9. zaremba, 2014, Learning to execute, CoRR abs/1410 4615
  10. 10.1109/72.279181 · DOI · Paper page
  11. gers, 2002, Learning precise timing with LSTM recurrent networks, JMLR, 3, 115
  12. fernandez, 2008, Phoneme recognition in TIMIT with BLSTM-CTC, CoRR abs/0804 3269
  13. 10.1109/TPAMI.2008.137 · DOI · Paper page
  14. graves, 2014, Towards end-to-end speech recognition with recurrent neural networks, Proc ICML, 1764
  15. baccouche, 2011, Sequential Deep Learning for Human Action Recognition, Human Behavior Unterstanding, 29, 10.1007/978-3-642-25446-8_4 · DOI · Paper page
  16. 10.1109/ICASSP.2013.6638947 · DOI · Paper page
  17. baccouche, 2010, Action classification in soccer videos with long short-term memory recurrent neural networks, Proc ICANN, 154
  18. soomro, 2012, UCF101: A dataset of 101 human actions classes from videos in the wild, CRCV-TR-12–01
  19. 10.1109/CVPR.2011.5995407 · DOI · Paper page
  20. 10.5244/C.23.124 · DOI · Paper page

Cited by

Metadata

Authors
Ng, J. Y.-H., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., & Toderici, G.
Venue
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2015-06
Pages
4694-4702
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr.2015.7299101
OpenAlex
W1923404803
Cited by
2,062
References
8
FWCI
78.56
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.