Skip to main content
SpringerLink
Log in

Eclectic domain mixing for effective adaptation in action spaces

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Although videos appear to be very high-dimensional in terms of duration × frame-rate × resolution, temporal smoothness constraints ensure that the intrinsic dimensionality for videos is much lower. In this paper, we use this idea for investigating Domain Adaptation (DA) in videos, an area that remains under-explored. An approach that has worked well for the image DA is based on the subspace modeling of the source and target domains, which works under the assumption that the two domains share a latent subspace where the domain shift can be reduced or eliminated. In this paper, first we extend three subspace based image DA techniques for human action recognition and then combine it with our proposed Eclectic Domain Mixing (EDM) approach to improve the effectiveness of the DA. Further, we use discrepancy measures such as Symmetrized KL Divergence and Target Density Around Source for empirical study of the proposed EDM approach. While, this work mainly focuses on Domain Adaptation in videos, for completeness of the study, we comprehensively evaluate our approach using both object and action datasets. In this paper, we have achieved consistent improvements over chosen baselines and obtained some state-of-the-art results for the datasets.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. Aljundi R, Emonet R, Muselet D, Sebban M (2015) Landmarks-based kernelized subspace alignment for unsupervised domain adaptation. In: CVPR

  2. Baktashmotlagh M, Harandi M, Lovell B, Salzmann M (2013) Unsupervised domain adaptation by domain invariant projection. In: ICCV

  3. Baktashmotlagh M, Harandi MT, Lovell BC, Salzmann M (2014) Domain adaptation on the statistical manifold. In: CVPR

  4. Ben-David S, Blitzer J, Crammer K, Pereira F (2007) Analysis of representations for domain adaptation. In: NIPS, pp 137–144

  5. Bergamo A, Torresani L (2010) Exploiting weakly-labeled web images to improve object classification: a domain adaptation approach. In: NIPS

  6. Blitzer J, McDonald R, Pereira F (2006) Domain adaptation with structural correspondence learning. In: Proc of EMNLP, pp 120–128

  7. Caseiro R, Henriques JF, Martins P, Batista J (2015) Beyond the shortest path Unsupervised domain adaptation by Sampling Subspaces along the Spline Flow. In: CVPR

  8. Cross-Dataset Setup: https://sites.google.com/site/crossdataset/

  9. Csurka G (2017) Domain adaptation for visual applications: a comprehensive survey. In: Arxiv

  10. Daume IIIH (2007) Frustratingly easy domain adaptation. In: Proc of ACL, pp 256–263

  11. Daume IIIH, Kumar A, Saha A (2010) Co-regularization based semi-supervised domain adaptation. In: NIPS

  12. Daume IIIH, Marcu D (2006) Domain adaptation for statistical classifiers. JAIR

  13. Donahue J, Hendricks LA, Guadarrama S, Rohrbach M, Venugopalan S, Saenko K, Darrell T (2015) Long-term recurrent convolutional networks for visual recognition and description. In: CVPR

  14. Duan L, Tsang I, Xu D, Chua T (2009) Domain adaptation from multiple sources via auxiliary classifiers. In: ICML

  15. Duan L, Tsang I, Xu D, Maybank S (2009) Domain transfer SVM for video concept detection. In: CVPR

  16. Duan L, Xu D, Tsang IW (2012) Domain adaptation from multiple Sources: a Domain-Dependent regularization approach. In: IEEE Transactions on neural networks and learning systems

  17. Duan L, Xu D, Tsang IW, Luo J (2012) Visual event recognition in videos by learning from web data. In: IEEE Transactions on pattern analysis and machine intelligence

  18. Faraji Davar N, deCampos TE, Windridge D, Kittler J, Christmas W (2011) Domain adaptation in the context of sport video action recognition. In: Domain adaptation workshop in conjunction with NIPS

  19. Feichtenhofer C, Pinz A, Zisserman A (2016) Convolutional two-stream network fusion for video action recognition. In: Arxiv

  20. Fernando B, Gavves EM, Jos O, Ghodrati A, Tuytelaars T (2015) Modeling video evolution for action recognition. In: CVPR

  21. Fernando B, Habrard A, Sebban M, Tuytelaars T (2013) Unsupervised visual domain adaptation using subspace alignment. In: ICCV

  22. Ganin Y, Lempitsky VS (2015) Unsupervised domain adaptation by backpropagation. In: ICML

  23. Gong B, Grauman K, Sha F (2013) Connecting the dots with landmarks discriminatively learning domain-invariant features for unsupervised domain adaptation. In: ICML

  24. Gong B, Shi Y, Sha F, Grauman K (2012) Geodesic flow kernel for unsupervised domain adaptation. In: CVPR

  25. Gopalan R, Li R, Chellappa R (2014) Unsupervised adaptation across domain shifts by generating intermediate data representations. In: IEEE Trans on pattern anal Mach Intell

  26. Gopalan R, Li R, Patel V, Chellappa R (2015) Domain adaptation for visual recognition. In: Found Trends Comput Graph Vis

  27. Hoffman J, Kulis B, Darrell T, Saenko K (2012) Discovering latent domains for multi-source domain adaptation. In: ECCV

  28. Jiang F, Zhang S, Wu S, Gao Y, Zhao D (2015) Multi-layered gesture recognition with Kinect. J Mach Learn Res 16:227–254

    MathSciNet  MATH  Google Scholar 

  29. KTH and MSR Action II Dataset: http://www.cs.utexas.edu/~chaoyeh/web_action_data/dataset_list.html

  30. Kuhne H, Jhuang H, Garrote E, Poggio T, Serre T (2011) HMDB a large video database for human motion recognition. In: ICCV

  31. Kulis B, Saenko K, Darrell T (2011) What you saw is not what you get Domain adaptation using asymmetric kernel transforms. In: Proc of CVPR, pp 1785–1792

  32. Li Ruonan (2012) Discriminative virtual views for cross-view action recognition. In: CVPR

  33. Long M, Cao Y, Wang J, Jordan MI (2015) Learning transferable features with deep adaptation networks. In: ICML

  34. Long M, Wang J, Jordan MI (2016) Unsupervised domain adaptation with residual transfer networks. In: Arxiv

  35. Long M, Zhu H, Wang J, Jordan MI (2017) Deep transfer learning with joint adaptation networks. In: Arxiv

  36. Ni J, Qiu Q, Chellappa R (2013) Subspace interpolation via dictionary learning for unsupervised domain adaptation. In: CVPR

  37. Niebles JC, Chen C-W, Fei-Fei L (2010) Modeling temporal structure of decomposable motion segments for activity classification. In: ECCV

  38. Pan S, Tsang I, Kwok J, Yang Q (2009) Domain adaptation via transfer component analysis. IEEE Trans Neural Nets 99:1–12

    Google Scholar 

  39. Qiu Q, Patel V, Turaga P, Chellappa R (2012) Domain adaptive dictionary learning. In: ECCV

  40. Reddy KK, Shah M (2013) Recognizing 50 human action categories of web videos. In: Mach Vision appl

  41. Saenko K, Kulis B, Fritz M, Darrell T (2010) Adapting visual category models to new domains. In: ECCV

  42. Simonyan K, Zisserman A (2014) Two-Stream Convolutional networks for action rec. In: NIPS

  43. Smola A, Gretton A, Song L, Schölkopf B (2007) A Hilbert space embedding for distributions. In: Algorithmic learning theory

  44. Sultani W, Saleemi I (2014) Human action recognition across datasets by Foreground-Weighted histogram decomposition. In: CVPR

  45. Sun B, Feng J, Saenko K (2016) Return of frustratingly easy domain adaptation. In: Conference on artificial intelligence

  46. Sun B, Saenko K (2015) Subspace distribution alignment for unsupervised domain adaptation. In: BMVC

  47. Tommasi T, Tuytelaars T (2014) A testbed for cross-dataset analysis. In: ECCV

  48. Tran D u, Bourdev LD, Fergus R, Torresani L, Paluri M (2015) Learning Spatio-temporal features with 3D convolutional networks. In: ICCV

  49. Tzeng E, Hoffman T, Darrell J, Saenko K (2015) Simultaneous deep transfer across domains and tasks. In: Arxiv

  50. Wang H, Schmid C (2013) Action recognition with improved trajectories. In: Proc. ICCV, pp 3551–3558

  51. Zhang S, Yao H, Sun X, Wang K, Zhang J, Lu X, Zhang Y (2014) Action recognition based on overcomplete independent components analysis. Inf Sci 281:635–647

    Article  Google Scholar 

  52. Zhang Z, Wang C, Xiao B, Zhou W, Liu S, Shi C (2013) Cross-View Action recognition via a continuous virtual path. In: CVPR

Download references

Acknowledgments

The authors would like to thank Director, Centre for AI & Robotics, Bangalore for permitting the publication of research work.

Author information

Author notes

  1. Arshad Jamal

    Present address: Centre for AI and Robotics, Bangalore, India

Authors and Affiliations

  1. Indian Institute of Technology, Kanpur, India

    Arshad Jamal, Vinay Namboodiri & K S Venkatesh

  2. Centre for AI and Robotics, Bangalore, India

    Dipti Deodhare

Authors
  1. Arshad Jamal
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Dipti Deodhare
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Vinay Namboodiri
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. K S Venkatesh
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Arshad Jamal.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jamal, A., Deodhare, D., Namboodiri, V. et al. Eclectic domain mixing for effective adaptation in action spaces. Multimed Tools Appl 77, 29949–29969 (2018). https://doi.org/10.1007/s11042-018-6179-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-018-6179-y

Keywords

Search

Navigation