Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 1,333

The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.

Machine Recognition of Human Activities: A Survey

Turaga, Pavan, Chellappa, Rama, Subrahmanian, V. S., Udrea, Octavian·2008·IEEE Transactions on Circuits and Systems for Video Technology
DOI 10.1109/tcsvt.2008.2005594
Open this paper in CoChat — free account

Abstract

The past decade has witnessed a rapid proliferation of video cameras in all walks of life and has resulted in a tremendous explosion of video content. Several applications such as content-based video annotation and retrieval, highlight extraction and video summarization require recognition of the activities occurring in the video. The analysis of human activities in videos is an area with increasingly important consequences from security and surveillance to entertainment and personal archiving. Several challenges at various levels of processing-robustness against errors in low-level processing, view and rate-invariant representations at midlevel processing and semantic representation of human activities at higher level processing-make this problem hard to solve. In this review paper, we present a comprehensive survey of efforts in the past couple of decades to address the problems of representation, recognition, and learning of human activities from video and related applications. We discuss the problem at two major levels of complexity: 1) "actions" and 2) "activities." "Actions" are characterized by simple motion patterns typically executed by a single human. "Activities" are more complex and involve coordinated actions among a small number of humans. We will discuss several approaches and classify them according to their ability to handle varying degrees of complexity as interpreted above. We begin with a discussion of approaches to model the simplest of action classes known as atomic or primitive actions that do not require sophisticated dynamical modeling. Then, methods to model actions with more complex dynamics are discussed. The discussion then leads naturally to methods for higher level representation of complex activities.

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/tcsvt.2008.2005594

Cites

4 of 4 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 4 references

Research works printed but not linked: 141

  1. 10.1109/CVPR.2004.1315230 · DOI · Paper page
  2. 10.1006/cviu.1998.0726 · DOI · Paper page
  3. 10.1109/CVPR.2005.58 · DOI · Paper page
  4. 10.1109/EVENT.2001.938868 · DOI
  5. 10.1098/rstb.1997.0108 · DOI · Paper page
  6. 10.1109/34.910878 · DOI · Paper page
  7. belkin, 2001, Advances in neural information processing systems, 585
  8. roweis, 2000, nonlinear dimensionality reduction by locally linear embedding, Science, 290, 2323, 10.1126/science.290.5500.2323 · DOI · Paper page
  9. 10.1109/TPAMI.2007.70711 · DOI · Paper page
  10. 10.1109/VSPETS.2005.1570899 · DOI · Paper page
  11. 10.1007/s11263-005-1838-7 · DOI · Paper page
  12. 10.1023/A:1007975200487 · DOI
  13. roy-chowdhury, 2003, a factorization approach to activity recognition, Proc CVPR Workshop Event Mining, 41
  14. 10.1109/TIT.1962.1057692 · DOI · Paper page
  15. elgammal, 2000, non-parametric model for background subtraction, Proc IEEE Eur Conf Comput Vis, 751
  16. 10.1112/blms/16.2.81 · DOI · Paper page
  17. 10.1109/TEC.1961.5219197 · DOI
  18. 10.1007/978-94-011-5014-9 · DOI · Paper page
  19. bissacco, 2004, gait recognition using dynamic affine invariants, Int Symp Math Theory Netw Syst
  20. 10.1109/CVPR.2007.383331 · DOI
  21. 10.1016/0031-3203(78)90025-0 · DOI
  22. 10.1007/s11263-006-0009-9 · DOI · Paper page
  23. 10.1109/CVPR.2007.383332 · DOI
  24. 10.1109/CVPR.2007.383137 · DOI · Paper page
  25. 10.1109/ICPR.2002.1047975 · DOI
  26. 10.1109/CVPR.2007.383512 · DOI
  27. 10.1109/ICCV.2005.85 · DOI · Paper page
  28. 10.1023/B:VISI.0000013087.49260.fb · DOI · Paper page
  29. 10.1109/CVPR.2005.328 · DOI · Paper page
  30. 10.1109/CVPR.2007.383132 · DOI · Paper page
  31. 10.1109/TPAMI.2003.1206511 · DOI
  32. 10.1109/ICCV.2003.1238658 · DOI
  33. 10.1006/cviu.1998.0716 · DOI · Paper page
  34. 10.1016/0262-8856(95)93154-K · DOI · Paper page
  35. 10.1145/1177352.1177355 · DOI · Paper page
  36. 10.1016/j.cviu.2006.08.002 · DOI · Paper page
  37. georis, 2004, a video interpretation platform applied to bank agency monitoring, Intelligent Distributed Surveillance Systems (IDSS-04), 46, 10.1049/ic:20040097 · DOI
  38. 10.1109/ICCV.2007.4409049 · DOI
  39. 10.1109/TPAMI.2005.246 · DOI · Paper page
  40. 10.1109/TIP.2005.852197 · DOI
  41. 10.5244/C.20.127 · DOI · Paper page
  42. 10.1109/CVPR.2001.990935 · DOI · Paper page
  43. 10.1109/WMVC.2008.4544068 · DOI
  44. 10.1109/ICPR.2004.1334462 · DOI · Paper page
  45. 10.1163/156856801753253582 · DOI
  46. 10.1364/JOSAA.7.000923 · DOI · Paper page
  47. 10.1109/CVPR.1999.784616 · DOI
  48. 10.1109/ICCV.2007.4408988 · DOI · Paper page
  49. 10.1109/ICPR.2004.1333743 · DOI
  50. 10.1145/1026711.1026757 · DOI
  51. tran, 2008, visual event modeling and recognition using markov logic networks, IEEE Eur Conf Comput Vis
  52. 10.1109/AVSS.2005.1577271 · DOI
  53. 10.1109/TPAMI.2005.210 · DOI
  54. 10.1109/CVPR.2001.990924 · DOI
  55. hobbs, 2004, an ontology for video event representation, Proc IEEE Workshop Event Detect Recog, 119
  56. 10.1155/2007/65989 · DOI
  57. guler, 0, An ontology of video events in the physical security and surveillance domain
  58. 10.1109/ICCV.2003.1238661 · DOI
  59. 10.1109/CVPR.2007.382996 · DOI
  60. 10.1109/MMUL.2005.87 · DOI
  61. 10.1111/j.1467-9892.1982.tb00349.x · DOI · Paper page
  62. 10.1109/CVPR.2007.383135 · DOI
  63. 10.1109/CVPR.2001.990925 · DOI · Paper page
  64. 10.1109/ICCV.2005.90 · DOI
  65. 10.1109/34.546259 · DOI
  66. 10.1109/34.868681 · DOI · Paper page
  67. 10.1016/0005-1098(93)90061-W · DOI
  68. 10.1109/ICCV.2003.1238420 · DOI · Paper page
  69. ghahramani, 1996, Parameter Estimation for Linear Dynamical Systems
  70. 10.1023/A:1020350100748 · DOI · Paper page
  71. 10.1023/A:1007928103394 · DOI
  72. 10.1016/j.cviu.2006.07.013 · DOI · Paper page
  73. 10.1007/s11263-005-3671-4 · DOI
  74. 10.1109/CVPR.2007.383099 · DOI
  75. 10.1109/MNRAO.1994.346259 · DOI
  76. 10.1109/5.18626 · DOI · Paper page
  77. 10.1109/ACV.1994.341308 · DOI
  78. 10.1109/ISCV.1995.477006 · DOI
  79. 10.1023/A:1008118801668 · DOI
  80. 10.1109/34.735811 · DOI · Paper page
  81. 10.1109/CVPR.2006.304 · DOI
  82. 10.1109/TIP.2004.832865 · DOI · Paper page
  83. 10.1109/ICPR.2004.1334410 · DOI
  84. 10.1109/TPAMI.2006.122 · DOI · Paper page
  85. 10.1109/CVPR.2001.990977 · DOI
  86. 10.1109/CVPR.1997.609450 · DOI · Paper page
  87. 10.1109/TMM.2007.893340 · DOI
  88. 10.1006/cviu.1998.0744 · DOI · Paper page
  89. 10.1109/ICCV.1999.791201 · DOI · Paper page
  90. 10.3758/BF03212378 · DOI · Paper page
  91. 10.1109/CVPR.1998.698711 · DOI
  92. 10.1007/s00530-004-0148-1 · DOI
  93. 10.1109/TMM.2008.2001369 · DOI
  94. 10.1109/ICCV.1998.710817 · DOI
  95. 10.1109/CVPR.2004.430 · DOI
  96. 10.1016/0004-3702(95)00041-0 · DOI
  97. castel, 1996, what is going on? a high-level interpretation of a sequence of images, Proc ECCV Workshop Conceptual Descriptions Images, 13
  98. pearl, 1988, Probabilistic Reasoning in Intelligent Systems Networks of Plausible Inference
  99. 10.1109/5.24143 · DOI · Paper page
  100. oh, 2005, data-driven mcmc for learning and inference in switching linear dynamic systems, Proc Nat Conf Artif Intell, 944
  101. david, 1994, petri nets for modeling of dynamic systems a survey, Automatica, 30, 175, 10.1016/0005-1098(94)90024-8 · DOI
  102. 10.1109/CVPR.2000.855901 · DOI
  103. petri, 1966, Communication with automata
  104. 10.1023/A:1020249912095 · DOI · Paper page
  105. 10.1109/CVPR.2006.174 · DOI
  106. 10.1109/ICCV.2007.4408894 · DOI
  107. shi, 2004, propagation networks for recognizing partially ordered sequential action, Proc IEEE Conf Comput Vis Pattern Recognit, 2, 862
  108. 10.1109/TAC.1977.1101594 · DOI
  109. 10.1214/aos/1176344136 · DOI · Paper page
  110. intille, 1999, a framework for recognizing multi-agent action from visual evidence, Proc Nat Conf Artif Intell, 518
  111. gong, 2003, recognition of group activities using dynamic probabilistic networks, Proc IEEE Int Conf Comput Vis, 742, 10.1109/ICCV.2003.1238423 · DOI · Paper page
  112. 10.1006/jvci.1999.0413 · DOI · Paper page
  113. 10.1109/93.998041 · DOI
  114. zhong, 2004, detecting unusual activity in video, Proc IEEE Conf Comput Vis Pattern Recognit, 819
  115. 10.1109/34.868677 · DOI · Paper page
  116. 10.1109/TSMCB.2004.826829 · DOI
  117. 10.1109/34.868686 · DOI · Paper page
  118. 10.1109/ICPR.1998.711845 · DOI
  119. 10.1109/ICCV.2007.4408847 · DOI
  120. higuera, 2000, current trends in grammatical inference, Proc Joint IAPR Int Workshops Adv Pattern Recognit, 28
  121. 10.1561/0600000005 · DOI
  122. 10.1109/78.827549 · DOI
  123. 10.1145/212094.212141 · DOI · Paper page
  124. 10.1109/CVPR.2007.383333 · DOI
  125. moore, 2002, recognizing multitasked activities from video using stochastic context-free grammar, Proc 18th Nat Conf Artif Intell, 770
  126. huang, 1994, automatic symbolic traffic scene analysis using belief networks, Proc Nat Conf Artif Intell, 966
  127. 10.1007/s11263-006-9352-0 · DOI
  128. 10.1109/CVPR.2006.242 · DOI
  129. 10.1109/AFGR.1996.557249 · DOI
  130. aho, 1972, The Theory of Parsing Translation and Compiling Volume 1 Parsing
  131. 10.1016/S0167-6911(02)00135-4 · DOI
  132. 10.1145/362007.362035 · DOI
  133. 10.1109/ICIP.2006.313035 · DOI
  134. pavlovic, 2000, Advances in neural information processing systems, 981
  135. rota, 2000, activity recognition from video sequences using declarative models, Proc 14th Eur Conf Artif Intell, 673
  136. 10.1109/34.946990 · DOI · Paper page
  137. 10.1016/j.cviu.2004.02.005 · DOI · Paper page
  138. 10.1109/CVPR.2008.4587733 · DOI
  139. 10.1023/A:1021669406132 · DOI · Paper page
  140. 10.1109/CVPR.1997.609382 · DOI · Paper page
  141. 10.1109/34.877523 · DOI

Cited by

Metadata

Authors
Turaga, P., Chellappa, R., Subrahmanian, V. S., & Udrea, O.
Venue
IEEE Transactions on Circuits and Systems for Video Technology
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2008-11
Volume
18
Issue
11
Pages
1473-1488
ISSN
  • 1051-8215 (ISSN-L)
  • 1558-2205
DOI
10.1109/tcsvt.2008.2005594
OpenAlex
W2155268664
Cited by
1,333
References
4
FWCI
107.87
Type
journal article
Language
en
Open access
closed
Licence
ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html (vor)

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.