Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 860

The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.

Recurrent Network Models for Human Dynamics

Fragkiadaki, Katerina, Levine, Sergey, Felsen, Panna, Malik, Jitendra·2015·2015 IEEE International Conference on Computer Vision (ICCV)
DOI 10.1109/iccv.2015.494
Open this paper in CoChat — free account

Abstract

We propose the Encoder-Recurrent-Decoder (ERD) model for recognition and prediction of human body pose in videos and motion capture. The ERD model is a recurrent neural network that incorporates nonlinear encoder and decoder networks before and after recurrent layers. We test instantiations of ERD architectures in the tasks of motion capture (mocap) generation, body pose labeling and body pose forecasting in videos. Our model handles mocap training data across multiple subjects and activity domains, and synthesizes novel motions while avoiding drifting for long periods of time. For human pose labeling, ERD outperforms a per frame body part detector by resolving left-right body part confusions. For video pose forecasting, ERD predicts body joint displacements across a temporal horizon of 400ms and outperforms a first order motion model based on optical flow. ERDs extend previous Long Short Term Memory (LSTM) models in the literature to jointly learn representations and their dynamics. Our experiments show such representation learning is crucial for both labeling and prediction in space-time. We find this is a distinguishing feature between the spatio-temporal visual domain in comparison to 1D text, speech or handwriting, where straightforward hard coded representations have shown excellent results when directly combined with recurrent units [31].

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.2015.494

Cites

7 of 7 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: 44

  1. 10.1109/CVPR.2006.15 · DOI · Paper page
  2. 10.1109/CVPR.2015.7298758 · DOI · Paper page
  3. 10.1145/1553374.1553505 · DOI · Paper page
  4. 10.1109/CVPR.2000.855885 · DOI
  5. sutskever, 2014, Sequence to sequence learning with neural networks, NIPS
  6. sutskever, 2011, Generating text with recurrent neural networks, ICML
  7. toshev, 2013, Deeppose: Human pose estimation via deep neural networks, CoRR abs/1312 4659
  8. tompson, 2014, Joint training of a convolutional network and a graphical model for human pose estimation, NIPS
  9. 10.1109/CVPR.2010.5540157 · DOI
  10. taylor, 2006, Modeling human motion using binary latent variables, NIPS
  11. 10.1109/CVPR.2005.132 · DOI
  12. 10.1007/s11263-011-0493-4 · DOI
  13. sutskever, 2008, The recurrent temporal restricted boltzmann machine, NIPS
  14. batra, 2012, Diverse “m”-best solutions in markov random fields, ECCV
  15. 10.1145/2159516.2159523 · DOI
  16. 10.1109/ICCV.2011.6126552 · DOI
  17. pavlovic, 2000, Learning switching linear models of human motion, NIPS
  18. 10.1080/095400999116340 · DOI
  19. ranzato, 2014, Video (language) modeling: a baseline for generative models of natural videos, CoRR abs/1412 6604
  20. 10.1109/CVPR.2011.5995607 · DOI
  21. sapp, 2013, Modec:multimodal decomposable models for human pose estimation, CVPR
  22. williams, 1995, Gradient-Based Learning Algorithms for Recurrent Networks and their Computational Complexity
  23. 10.1109/CVPR.2011.5995741 · DOI · Paper page
  24. hinton, 2006, Reducing the Dimensionality of Data with Neural Networks, Science, 313, 504, 10.1126/science.1127647 · DOI · Paper page
  25. 10.1145/1073204.1073315 · DOI · Paper page
  26. jia, 2013, Caffe An Open Source Convolutional Architecture for Fast Feature Embedding
  27. kombrink, 2011, Recurrent neural network based language modeling in meeting recognition, InterSpeech, 10.21437/Interspeech.2011-720 · DOI
  28. 10.1109/IROS.2013.6696634 · DOI
  29. lan, 2004, A unified spatio-temporal articulated model for tracking, CVPR, 1
  30. cun, 1990, Handwritten digit recognition with a back-propagation network, NIPS
  31. 10.1145/344779.344865 · DOI · Paper page
  32. donahue, 2014, Long-term recurrent convolutional networks for visual recognition and description, CoRR
  33. 10.1007/978-3-642-33765-9_12 · DOI
  34. gong, 2011, Multi-hypothesis motion planning for visual object tracking, ICCV
  35. 10.1109/MSP.2010.937999 · DOI
  36. williams, 1909, A learning algorithm for continually running fully recurrent neural networks, Neural Comput, 1
  37. graves, 2013, Generating sequences with recurrent neural networks, CoRR abs/1308 0850
  38. 10.1109/TPAMI.2007.1167 · DOI · Paper page
  39. 10.1145/1273496.1273619 · DOI
  40. 0, Lagrangian and eulerian specification of the flow field
  41. 10.1016/j.jvcir.2006.03.004 · DOI · Paper page
  42. vincent, 2010, Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion, J Mach Learn Res, 11, 3371
  43. 10.1007/978-3-642-16904-5 · DOI
  44. wang, 2006, Gaussian process dynamical models, NIPS, 1441

Cited by

See all 860

Metadata

Authors
Fragkiadaki, K., Levine, S., Felsen, P., & Malik, J.
Venue
2015 IEEE International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2015-12
Pages
4346-4354
DOI
10.1109/iccv.2015.494
OpenAlex
W1735317348
Cited by
860
References
7
FWCI
13.58
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.