Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 189

The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.

Unsupervised Learning of Long-Term Motion Dynamics for Videos

Open access
Luo, Zelun, Peng, Boya, Huang, De-An, Alahi, Alexandre, Fei-Fei, Li·2017·2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr.2017.751
Open this paper in CoChat — free account

Abstract

We present an unsupervised representation learning approach that compactly encodes the motion dependencies in videos. Given a pair of images from a video clip, our framework learns to predict the long-term 3D motions. To reduce the complexity of the learning framework, we propose to describe the motion as a sequence of atomic 3D flows computed with RGB-D modality. We use a Recurrent Neural Network based Encoder-Decoder framework to predict these sequences of flows. We argue that in order for the decoder to reconstruct these sequences, the encoder must learn a robust video representation that captures long-term motion dependencies and spatial-temporal relations. We demonstrate the effectiveness of our learned temporal representations on activity classification across multiple modalities and datasets such as NTU RGB+D and MSR Daily Activity 3D. Our framework is generic to any input modality, i.e., RGB, depth, and RGB-D videos.

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.2017.751

Cites

10 of 10 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

Research works printed but not linked: 43

  1. 10.1109/CVPR.2012.6247813 · DOI · Paper page
  2. sung, 2011, Human activity detection from rgbd images, Plan Activity and Intent Recognition, 64
  3. soomro, 2012, Ucf101 A Dataset of 101 Human Actions Classes from Videos in the Wild
  4. 10.1109/ICCV.2015.281 · DOI · Paper page
  5. vondrick, 2016, Generating videos with scene dynamics
  6. 10.1109/CVPR.2014.82 · DOI · Paper page
  7. sutskever, 2014, Sequence to sequence learning with neural networks, Advances in Neural Information Processing Systems 27, 3104
  8. simonyan, 2014, Two-stream convolutional networks for action recognition in videos, Advances in neural information processing systems, 568
  9. 10.1109/CVPR.2016.115 · DOI · Paper page
  10. simonyan, 2014, Very Deep Convolutional Networks for Large-scale Image Recognition
  11. du, 2015, Hierarchical recurrent neural network for skeleton based action recognition, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1110
  12. 10.1109/CVPR.2013.98 · DOI · Paper page
  13. 10.1109/CVPR.2016.167 · DOI · Paper page
  14. 10.1007/978-3-319-10605-2_48 · DOI · Paper page
  15. 10.1007/s11263-015-0816-y · DOI · Paper page
  16. ranzato, 2014, Video (language) modeling a baseline for generative models of natural videos
  17. sermanet, 2013, Pedestrian detection with unsupervised multi-stage feature learning, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3626, 10.1109/CVPR.2013.465 · DOI · Paper page
  18. yu, 2014, Discriminative orderlet mining for real-time recognition of human-object interaction, Asian Conference on Computer Vision, 50
  19. 10.1109/CVPR.2015.7299101 · DOI · Paper page
  20. zou, 2012, Deep learning of invariant features via simulated fixations in video, Advances in neural information processing systems, 3212
  21. zhang, 2016, Colorful image colorization, abs 1603 8511
  22. 10.1109/ICIP.2014.7025848 · DOI
  23. 10.1109/ICCV.2013.333 · DOI
  24. koppula, 2013, Learning spatio-temporal structure from rgb-d videos for human activity detection and anticipation, ICML, 792
  25. lan, 2015, Beyond gaussian pyramid: Multi-skip feature stacking for action recognition, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 204
  26. 10.1109/CVPRW.2010.5543273 · DOI · Paper page
  27. 10.1109/CVPR.2014.104 · DOI
  28. 10.1109/ICCV.2013.227 · DOI · Paper page
  29. müller, 2006, Motion templates for automatic classification and retrieval of motion capture data, Proceedings of the 2006 ACM SIGGRAPH/Eurographics Symposium on Computer Animation, 137
  30. 10.1109/CVPRW.2013.76 · DOI · Paper page
  31. 10.1109/CVPR.2016.138 · DOI · Paper page
  32. 10.1109/ICPR.2014.772 · DOI · Paper page
  33. 10.1109/CVPR.2015.7299172 · DOI · Paper page
  34. 10.1007/978-3-319-46448-0_10 · DOI · Paper page
  35. 10.1109/ICRA.2015.7138986 · doi:10.1109/icra.2015.7138986
  36. ioffe, 2015, Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift, abs 1502 3167
  37. 10.1109/TPAMI.2012.253 · DOI
  38. kim, 1992, Side match and overlap match vector quantizers for images, 170
  39. 10.1109/CVPR.2013.365 · DOI · Paper page
  40. 10.1109/CVPR.2015.7299065 · DOI
  41. 10.1109/CVPR.2014.108 · DOI · Paper page
  42. wang, 2015, Towards good practices for very deep two-stream convnets
  43. wang, 2015, Towards good practices for very deep two-stream convnets, abs 1507 2159

Cited by

See all 189

Metadata

Authors
Luo, Z., Peng, B., Huang, D.-A., Alahi, A., & Fei-Fei, L.
Venue
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2017-07
Pages
7101-7110
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr.2017.751
OpenAlex
W2578257192
Cited by
189
References
10
FWCI
8.90
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.