Skip to main content
SpringerLink
Log in

Is Appearance Free Action Recognition Possible?

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13664))

Included in the following conference series:

Abstract

Intuition might suggest that motion and dynamic information are key to video-based action recognition. In contrast, there is evidence that state-of-the-art deep-learning video understanding architectures are biased toward static information available in single frames. Presently, a methodology and corresponding dataset to isolate the effects of dynamic information in video are missing. Their absence makes it difficult to understand how well contemporary architectures capitalize on dynamic vs. static information. We respond with a novel Appearance Free Dataset (AFD) for action recognition. AFD is devoid of static information relevant to action recognition in a single frame. Modeling of the dynamics is necessary for solving the task, as the action is only apparent through consideration of the temporal dimension. We evaluated 11 contemporary action recognition architectures on AFD as well as its related RGB video. Our results show a notable decrease in performance for all architectures on AFD compared to RGB. We also conducted a complimentary study with humans that shows their recognition accuracy on AFD and RGB is very similar and much better than the evaluated architectures on AFD. Our results motivate a novel architecture that revives explicit recovery of optical flow, within a contemporary design for best performance on AFD and RGB.

Code & Data: f-ilic.github.io/AppearanceFreeActionRecognition.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Laying down harmonised rules on artificial intelligence (artificial intelligence act) and amending certain union legislative acts. European Commision (2021)

    Google Scholar 

  2. Regulating AI: Critical issues and choices. Law Council of Ontario (2021)

    Google Scholar 

  3. Aafaq, N., Mian, A., Liu, W., Gilani, S.Z., Shah, M.: Video description: a survey of methods, datasets, and evaluation metrics. ACM Comput. Surv. 52(6), 1–37 (2019)

    Article  Google Scholar 

  4. Baker, S., Scharstein, D., Lewis, J., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. Int. J. Comput. Vision 92(1), 1–31 (2011)

    Article  Google Scholar 

  5. Bideau, P., Learned-Miller, E.: It’s moving! A probabilistic model for causal motion segmentation in moving camera videos. In: Proceedings of the European Conference on Computer Vision (2016)

    Google Scholar 

  6. Braddick, O.J.: Low-level and high-level processes in apparent motion. Philos. Trans. R. Soc. London B Biol. Sci. 290(1038), 137–151 (1980)

    Google Scholar 

  7. Butler, D.J., Wulff, J., Stanley, G.B., Black, M.J.: A naturalistic open source movie for optical flow evaluation. In: Proceedings of the European Conference on Computer Vision (2012)

    Google Scholar 

  8. Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (2017)

    Google Scholar 

  9. Choi, J., Gao, C., Messou, C.E.J., Huang, J.B.: Why can’t I dance in the mall? Learning to mitigate scene bias in action recognition. In: Proceedings of the Conference on Advances in Neural Information Processing Systems (2019)

    Google Scholar 

  10. Dittrich, W.H.: Action categories and the perception of biological motion. Perception 22(1), 15–22 (1993)

    Article  Google Scholar 

  11. Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: Proceedings of the International Conference on Computer Vision (2015)

    Google Scholar 

  12. Fan, H., et al.: Multiscale vision transformers. In: Proceedings of the International Conference on Computer Vision (2021)

    Google Scholar 

  13. Feichtenhofer, C.: X3D: expanding architectures for efficient video recognition. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (2020)

    Google Scholar 

  14. Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. In: Proceedings of the International Conference on Computer Vision (2019)

    Google Scholar 

  15. Feichtenhofer, C., Pinz, A., Wildes, R.P.: Spatiotemporal multiplier networks for video action recognition. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (2017)

    Google Scholar 

  16. Feichtenhofer, C., Pinz, A., Wildes, R.P., Zisserman, A.: Deep insights into convolutional networks for video recognition. Int. J. Comput. Vision 128(2), 420–437 (2020)

    Article  Google Scholar 

  17. Ghodrati, A., Gavves, E., Snoek, C.G.M.: Video time: properties, encoders and evaluation. In: British Machine Vision Conference (2018)

    Google Scholar 

  18. Goodale, M.A., Milner, A.D.: Separate visual pathways for perception and action. Trends Neurosci. 15(1), 20–25 (1992)

    Article  Google Scholar 

  19. Goyal, R., et al.: The “something something” video database for learning and evaluating visual common sense. In: Proceedings of the International Conference on Computer Vision (2017)

    Google Scholar 

  20. Gu, C., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (2018)

    Google Scholar 

  21. Hadji, I., Wildes, R.P.: A new large scale dynamic texture dataset with application to convnet understanding. In: Proceedings of the European Conference on Computer Vision (2018)

    Google Scholar 

  22. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (2016)

    Google Scholar 

  23. He, Y., Shirakabe, S., Satoh, Y., Kataoka, H.: Human action recognition without human. In: Proceedings of the European Conference on Computer Vision (2016)

    Google Scholar 

  24. Hiley, L., Preece, A., Hicks, Y.: Explainable deep learning for video recognition tasks: a framework & recommendations. arXiv preprint arXiv:1909.05667 (2019)

  25. Hubel, D.H., Wiesel, T.N.: Receptive fields of single neurones in the cat’s striate cortex. J. Physiol. 148(3), 574–591 (1959)

    Article  Google Scholar 

  26. Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and \(<\) 0.5 mb model size. arXiv preprint arXiv:1602.07360 (2016)

  27. Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221–231 (2012)

    Article  Google Scholar 

  28. Johansson, G.: Visual perception of biological motion and a model for its analysis. Percept. Psychophysics 14(2), 201–211 (1973)

    Article  Google Scholar 

  29. Julesz, B.: Foundations of Cyclopean Perception. U. Chicago Press, Chicago (1971)

    Google Scholar 

  30. Kang, S.M., Wildes, R.P.: Review of action recognition and detection methods. arXiv preprint arXiv:1610.06906 (2016)

  31. Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (2014)

    Google Scholar 

  32. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)

  33. Kong, Y., Jia, Y., Fu, Y.: Interactive phrases: semantic descriptions for human interaction recognition. IEEE Trans. Pattern Anal. Mach. Intell. 36(9), 1775–1788 (2014)

    Article  Google Scholar 

  34. Kowal, M., Siam, M., Islam, A., Bruce, N.D.B., Wildes, R.P., Derpanis, K.G.: A deeper dive into what deep spatiotemporal networks encode: Quantifying static vs. dynamic information. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (2022)

    Google Scholar 

  35. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Proceedings of the Advances in Neural Information Processing Systems (2012)

    Google Scholar 

  36. Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: Proceedings of the International Conference on Computer Vision (2011)

    Google Scholar 

  37. Lamdouar, H., Yang, C., Xie, W., Zisserman, A.: Betrayed by motion: camouflaged object discovery via motion segmentation. In: Proceedings of the Asian Conference on Computer Vision (2020)

    Google Scholar 

  38. Li, Y., Li, Y., Vasconcelos, N.: Diving48 dataset. https://www.svcl.ucsd.edu/projects/resound/dataset.html

  39. Li, Y., Li, Y., Vasconcelos, N.: Resound: towards action recognition without representation bias. In: Proceedings of the European Conference on Computer Vision (2018)

    Google Scholar 

  40. Mahmood, N., Ghorbani, N., Troje, N., Pons-Moll, G., Black, M.: AMASS: archive of motion capture as surface Shapes. In: Proceedings of the International Conference on Computer Vision (2019)

    Google Scholar 

  41. Manttari, J., Broomé, S., Folkesson, J., Kjellstrom, H.: Interpreting video features: a comparison of 3d convolutional networks and convolutional LSTM networks. In: Proceedings of the Asian Conference on Computer Vision (2020)

    Google Scholar 

  42. Mayer, N., et al.: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (2016)

    Google Scholar 

  43. Miller, G.A.: The magical number seven, plus or minus two: Some limits on our capacity for processing information. Psychol. Rev. 63(2), 81 (1956)

    Article  Google Scholar 

  44. Nishida, S., Kawabe, T., Sawayama, M., Fukiage, T.: Motion perception: from detection to interpretation. Ann. Rev. Vis. Sci. 4, 501–523 (2018)

    Article  Google Scholar 

  45. Richter, S.R., Hayder, Z., Koltun, V.: Playing for benchmarks. In: Proceedings of the International Conference on Computer Vision (2017)

    Google Scholar 

  46. Ros, G., Sellart, L., Materzynska, J., Vazquez, D., Lopez, A.M.: The SYNTHIA dataset: a large collection of synthetic images for semantic segmentation of urban scenes. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (2016)

    Google Scholar 

  47. Sevilla-Lara, L., Liao, Y., Güney, F., Jampani, V., Geiger, A., Black, M.J.: On the integration of optical flow and action recognition. In: Brox, T., Bruhn, A., Fritz, M. (eds.) GCPR 2018. LNCS, vol. 11269, pp. 281–297. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-12939-2_20

    Chapter  Google Scholar 

  48. Sevilla-Lara, L., Zha, S., Yan, Z., Goswami, V., Feiszli, M., Torresani, L.: Only time can tell: discovering temporal data for temporal modeling. In: Proceedings of the Winter Conference on Applications of Computer Vision (2021)

    Google Scholar 

  49. Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Proceedings of the Conference on Advances in Neural Information Processing Systems (2014)

    Google Scholar 

  50. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)

  51. Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)

  52. Sriastava, N., Manisomov, E., Salakhutdinov, R.: Unsupervised learning of video representations using LSTMs. In: Proceedings of the International Conference on Machine Learning (2015)

    Google Scholar 

  53. Teed, Z., Deng, J.: RAFT: recurrent all-pairs field transforms for optical flow. In: Proceedings of the European Conference on Computer Vision (2020)

    Google Scholar 

  54. Thoma, M.: Analysis and Optimization of Convolutional Neural Network Architectures. Master’s thesis, University of the State of Baden-Wuerttemberg (2017)

    Google Scholar 

  55. Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the International Conference on Computer Vision (2015)

    Google Scholar 

  56. Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (2018)

    Google Scholar 

  57. Troje, N.F.: Decomposing biological motion: a framework for analysis and synthesis of human gait patterns. J. Vision 2(5), 2 (2002)

    Article  Google Scholar 

  58. Ullman, S.: The Interpretation of Visual Motion. MIT Press, Cambridge (1979)

    Google Scholar 

  59. Vu, T.H., Olsson, C., Laptev, I., Oliva, A., Sivic, J.: Predicting actions from static scenes. In: Proceedings of the European Conference on Computer Vision (2014)

    Google Scholar 

  60. Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (2018)

    Google Scholar 

  61. Zhao, H., Wildes, R.P.: Interpretable deep feature propagation for early action recognition. arXiv preprint arXiv:2107.05122 (2021)

  62. Zhou, B., Tang, X., Wang, X.: Coherent filtering: detecting coherent motions from crowd clutters. In: Proceedings of the European Conference on Computer Vision (2012)

    Google Scholar 

  63. Zhu, Y., et al.: A comprehensive study of deep video action recognition. arXiv preprint arXiv:2012.06567 (2020)

Download references

Author information

Authors and Affiliations

  1. Graz University of Technology, Graz, Austria

    Filip Ilic & Thomas Pock

  2. York University, Toronto, Canada

    Richard P. Wildes

Authors
  1. Filip Ilic
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Thomas Pock
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Richard P. Wildes
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Filip Ilic .

Editor information

Editors and Affiliations

  1. Tel Aviv University, Tel Aviv, Israel

    Shai Avidan

  2. University College London, London, UK

    Gabriel Brostow

  3. Google AI, Accra, Ghana

    Moustapha Cissé

  4. University of Catania, Catania, Italy

    Giovanni Maria Farinella

  5. Facebook (United States), Menlo Park, CA, USA

    Tal Hassner

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Ilic, F., Pock, T., Wildes, R.P. (2022). Is Appearance Free Action Recognition Possible?. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13664. Springer, Cham. https://doi.org/10.1007/978-3-031-19772-7_10

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19772-7_10

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19771-0

  • Online ISBN: 978-3-031-19772-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation