Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Cited by 173

The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.

A Survey on Deep Learning Based Approaches for Action and Gesture Recognition in Image Sequences

Open access
Asadi-Aghbolaghi, Maryam, Clapes, Albert, Bellantonio, Marco, Escalante, Hugo Jair, Ponce-Lopez, Victor, Baro, Xavier, Guyon, Isabelle, Kasaei, Shohreh, Escalera, Sergio · 2017 · 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017)

Abstract

The interest in action and gesture recognition has grown considerably in the last years. In this paper, we present a survey on current deep learning methodologies for action and gesture recognition in image sequences. We introduce a taxonomy that summarizes important aspects of deep learning for approaching both tasks. We review the details of the proposed architectures, fusion strategies, main datasets, and competitions. We summarize and discuss the main works proposed so far with particular interest on how they treat the temporal dimension of data, discussing their main features and identify opportunities and challenges for future research.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/fg.2017.150

Cites

19 of 19 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.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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 19 references

Research works printed but not linked: 121

  1. hochreiter, 1991, Untersuchungen zu dynamischen neuronalen netzen, Diplomarbeit Technischen Universität München, 91
  2. gers, 2002, Learning precise timing with 1stm recurrent networks, JMLR, 115
  3. 10.1109/CVPR.2016.213 · DOI · Paper page
  4. feichtenhofer, 2016, Spatiotemporal residual networks for video action recognition, NIPS, 3468
  5. 10.1007/978-3-319-46487-9_47 · DOI · Paper page
  6. 10.5244/C.29.50 · DOI
  7. han, 2016, Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding, Proc ICLR
  8. 10.1016/j.neucom.2016.08.032 · doi:10.1016/j.neucom.2016.08.032
  9. gkioxari, 2014, Finding action tubes, CoRR
  10. 10.1016/j.patrec.2016.01.013 · DOI
  11. escalante, 2015, Principal motion components for gesture recognition using a single example, PAA
  12. 10.1109/ICPR.2016.7899609 · DOI
  13. diba, 2016, Gool. Deepcamp: Deep convolutional action and attribute mid-level patterns, CVPR
  14. du, 2015, Hierarchical recurrent neural network for skeleton based action recognition, CVPR, 1110
  15. 10.1109/CVPR.2015.7298878 · DOI · Paper page
  16. 10.1007/978-3-319-51811-4_30 · DOI
  17. duan, 2016, Multi-modality fusion based on consensus-voting and 3d convolution for isolated gesture recognition, arXiv preprint arXiv 1611 06689
  18. sultani, 2016, Automatic action annotation in weakly labeled videos, CoRR abs/1605 08125
  19. 10.1016/0364-0213(90)90002-E · doi:10.1016/0364-0213(90)90002-e · Paper page
  20. 10.1109/ICCV.2015.375 · DOI
  21. eleni, 2015, Gesture recognition with a convolutional long short term memory recurrent neural network, ESANN
  22. karaman, 2013, L1-regularized logistic regression stacking and transductive crf smoothing for action recognition in video, ICCV Workshops
  23. 10.1109/ICCV.2013.227 · DOI · Paper page
  24. 10.1016/j.imavis.2016.04.004 · DOI
  25. liu, 2016, Spatio-temporal with trust gates for 3d human action recognition, ECCV, 816
  26. 10.1109/TPAMI.2016.2537337 · DOI · Paper page
  27. 10.1109/CVPR.2016.215 · DOI
  28. 10.1109/ICCV.2015.326 · DOI · Paper page
  29. konecny, 2014, One-shot-learning gesture recognition using hog-hof features, JMLR, 15, 2513
  30. 10.1016/j.cviu.2016.10.004 · DOI
  31. aliakbarian, 2016, Deep action-and context-aware sequence learning for activity recognition and anticipation, arXiv preprint arXiv 1611 05520
  32. al-rfou, 2016, Theano: A python framework for fast computation of mathematical expressions, arXiv 1605 02688
  33. 10.1109/ICIP.2015.7351168 · doi:10.1109/icip.2015.7351168
  34. 10.1109/ICCV.2013.171 · DOI
  35. 10.1145/2522848.2532592 · DOI
  36. 10.1145/2647868.2654889 · DOI · Paper page
  37. baccouche, 2011, Sequential deep learning for human action recognition, HBU, 29
  38. 10.1109/CVPR.2015.7298599 · DOI · Paper page
  39. ji, 2010, 3D convolutional neural networks for human action recognition, ICML, 495
  40. ibrahim, 2015, A hierarchical deep temporal model for group activity recognition, arXiv preprint arXiv 1511 05271
  41. 10.1109/ICME.2015.7177428 · DOI · Paper page
  42. jain, 2014, University of amsterdam at thumos challenge 2014, ECCV THUMOS Challenge 2014 Zürich Switzerland
  43. 10.1007/978-3-319-46475-6_22 · DOI
  44. 10.1109/CVPRW.2016.21 · DOI
  45. 10.1145/2522848.2532589 · DOI
  46. 10.1109/TPAMI.2016.2537340 · DOI · Paper page
  47. 10.1109/CVPR.2011.5995586 · DOI · Paper page
  48. 10.1109/CVPRW.2016.142 · DOI
  49. xu, 2015, Uts-cmu at THUMOS 2015, CVPR THUMOS challenge
  50. ni, 2013, Integrating multi-stage depth-induced contextual information for human action recognition and localization, FG, 1
  51. 10.1109/CVPR.2014.299 · DOI · Paper page
  52. 10.1109/TITS.2014.2337331 · DOI · Paper page
  53. oneata, 2014, The LEAR submission at Thumos 2014
  54. 10.1109/CVPR.2015.7299101 · DOI · Paper page
  55. 10.1109/CVPR.2016.297 · DOI · Paper page
  56. yu, 2014, An introduction to computational networks and the computational network toolkit, MSR Technical Report
  57. peng, 2015, Encoding feature maps of cnns for action recognition, CVPR
  58. 10.1109/CVPR.2016.337 · DOI · Paper page
  59. peng, 2016, Multi-region two-stream r-cnn for action detection, ECCV, 744
  60. 10.1016/j.neucom.2016.04.007 · DOI
  61. zhao, 2015, Pooling the convolutional layers in deep convnets for action recognition, arXiv preprint arXiv 1511 05271
  62. 10.1109/CVPR.2016.219 · DOI · Paper page
  63. 10.1109/CVPR.2015.7298953 · DOI
  64. 10.1109/CVPR.2016.333 · DOI · Paper page
  65. zhu, 2016, Co-occurrence feature learning for skeleton based action recognition using regularized deep lstm networks, reprint arXiv 1603 07772
  66. 10.1007/978-3-319-46454-1_27 · DOI
  67. mansimov, 2015, Initialization strategies of spatio-temporal convolutional neural networks, CoRR abs/1503 07274
  68. 10.1109/CVPRW.2015.7301342 · DOI · Paper page
  69. 10.1109/CVPR.2016.456 · DOI · Paper page
  70. montes, 2016, Nieto. Temporal activity detection in untrimmed videos with recurrent neural networks, arXiv preprint arXiv 1608 08128
  71. nasrollahi, 2015, Deep learning based super-resolution for improved action recognition, Ipta, 67
  72. 10.1109/ICCVW.2013.69 · DOI · Paper page
  73. neverova, 2014, Multi-scale deep learning for gesture detection and localization, ECCVW, 8925, 474
  74. abu-ei-haija, 2016, Youtube-8m A large-scale video classification benchmark CoRR abs/1609 08675
  75. abadi, 2015, TensorFlow Large-Scale Machine Learning on Heterogeneous Systems
  76. wang, 2015, A robust and efficient video representation for action recognition, IJCV, 1
  77. 10.1109/CVPR.2016.119 · DOI · Paper page
  78. 10.1016/B978-0-08-051584-7.50037-1 · DOI · Paper page
  79. 10.1007/s11263-015-0861-6 · DOI
  80. vondrick, 2011, Video annotation and tracking with active learning, NIPS
  81. shahroudy, 2016, Deep multimodal feature analysis for action recognition in rgb+ d videos, arXiv preprint arXiv 1603 02895
  82. 10.1109/ICCV.2015.460 · DOI · Paper page
  83. 10.1109/CVPR.2016.115 · DOI · Paper page
  84. varol, 2016, Long-term temporal convolutions for action recognition, CoRR abs/1604 04494
  85. 10.5244/C.30.58 · DOI · Paper page
  86. 10.1109/CVPR.2008.4587733 · DOI · Paper page
  87. 10.1109/ICSMC.2011.6083628 · DOI
  88. 10.1109/ICCV.2015.522 · DOI · Paper page
  89. wang, 2014, Action recognition and detection by combining motion and appearance features, THUMOS Action Recognition challenge, 1
  90. 10.1109/ICIP.2016.7532632 · doi:10.1109/icip.2016.7532632
  91. 10.1109/CVPR.2016.287 · DOI · Paper page
  92. shu, 2015, Action Detection with Improved Dense Trajectories and Sliding Window, 541
  93. simonyan, 2014, Two-stream convolutional networks for action recognition in videos, NIPS, 568
  94. 10.1109/CVPR.2016.331 · DOI · Paper page
  95. carngoz, 2016, Using convolutional 3d neural networks for user-independent continuous gesture recognition, ICPR W
  96. cao, 0, Action recognition with joints-pooled 3d deep convolutional descriptors
  97. 10.1109/ICPR.2016.7899603 · DOI
  98. chaudhry, 2013, Bioinspired dynamic 3d discriminative skeletal features for human action recognition, cvprw, 471
  99. 10.1109/ICSMC.2011.6084090 · DOI
  100. 10.1109/ICPR.2016.7899600 · DOI
  101. chen, 2016, Action recognition from depth sequences using weighted fusion of 2d and 3d auto-correlation of gradients features, Multimedia Tools and Applications, 1
  102. peng, 2014, Action recognition with stacked fisher vectors, ECCV, 581
  103. wang, 2017, Large-scale isolated gesture recognition using convolutional neural networks, arXiv preprint arXiv 1701 03308
  104. 10.1109/ICCV.2015.377 · DOI
  105. peng, 2013, Hybrid super vector with improved dense trajectories for action recognition, ICCV Workshops, 13
  106. qiu, 2015, Msr asia msm at thumos challenge 2015, CVPR Workshop, 8
  107. wang, 2015, Actions - transformations, CoRR abs/1512 00795
  108. deng, 2015, Deep structured models for group activity recognition, arXiv preprint arXiv 1506 01070
  109. wang, 2015, CUHK&SIAT submission for thumos15 action recognition challenge, THUMOS Action Recognition challenge, 1
  110. 10.1109/CVPR.2016.296 · DOI
  111. wang, 2015, Deep convolutional neural networks for action recognition using depth map sequences, CoRR abs/1501 04686
  112. peng, 2015, Action and Gesture Temporal Spotting with Super Vector Representation, 518
  113. wang, 2016, Gool. Temporal Segment Networks: Towards Good Practices for Deep Action Recognition, ECCV
  114. 10.1109/CVPR.2016.295 · DOI
  115. 10.1109/PERCOMW.2011.5766860 · DOI
  116. wang, 2015, Exploring fisher vector and deep networks for action spotting, cvprw, 10
  117. 10.1109/ICCV.2015.362 · DOI · Paper page
  118. 10.1016/j.cviu.2014.06.014 · DOI
  119. 10.1109/CVPR.2016.167 · DOI · Paper page
  120. 10.1109/CVPR.2015.7298860 · DOI
  121. 10.1109/CVPR.2016.69 · DOI

Cited by

See all 173

Metadata

Authors
Asadi-Aghbolaghi, M., Clapes, A., Bellantonio, M., Escalante, H. J., Ponce-Lopez, V., Baro, X., Guyon, I., Kasaei, S., & Escalera, S.
Venue
2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017)
Publisher
IEEE
Published
2017-05
Pages
476-483
ISSN
1541-5058 (ISSN-L)
OpenAlex
W2728972335
Cited by
173
References
19
FWCI
8.17
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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: A Survey on Deep Learning Based Approaches for Action and Gesture Recognition in Image Sequences. https://app.cochat.ai/papers/10.1109/fg.2017.150
The paper
Asadi-Aghbolaghi, M., Clapes, A., Bellantonio, M., Escalante, H. J., Ponce-Lopez, V., Baro, X., Guyon, I., Kasaei, S., & Escalera, S. (2017). A Survey on Deep Learning Based Approaches for Action and Gesture Recognition in Image Sequences. 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017). https://doi.org/10.1109/fg.2017.150

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.