Abstract
Despite all recent progress in computer vision, humans are still far superior to machines when it comes to the high-level understanding of complex dynamic scenes. The apparent ease of human perception and action cannot be explained by sheer neural computation power alone: Estimates put the transmission rate of the optic nerve at only about 10 MBit/s. One particular effective strategy to reduce the computational burden of vision in biological systems is the combination of attention with space-variant processing, where only subsets of the visual scene are processed in full detail at any one time. Here, we report on experiments that mimic eye movements and attention as a preprocessing step for state-of-the-art computer vision algorithms.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Agtzidis, I., Startsev, M., Dorr, M.: Smooth pursuit detection based on multiple observers. In: Proceedings of the Ninth Biennial ACM Symposium on Eye Tracking Research & Applications, ETRA’16, pp. 303–306. ACM, New York (2016)
Borji, A., Itti, L.: State-of-the-art in visual attention modeling. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 185–207 (2013)
Buso, V., Benois-Pineau, J., González-DÃaz, I.: Object recognition in egocentric videos with saliency-based non uniform sampling and variable resolution space for features selection. In: CVPR 2014 Egocentric (First-Person) Vision Workshop (2014)
Bylinskii, Z., Judd, T., Borji, A., Itti, L., Durand, F., Oliva, A., Torralba, A.: MIT Saliency Benchmark (2016). http://saliency.mit.edu
Bylinskii, Z., Judd, T., Oliva, A., Torralba, A., Durand, F.: What do different evaluation metrics tell us about saliency models? arXiv preprint arXiv:1604.03605 (2016)
Castelhano, M.S., Mack, M.L., Henderson, J.M.: Viewing task influences eye movement control during active scene perception. J. Vis. 9(3), 6 (2009)
Cerf, M., Frady, P., Koch, C.: Faces and text attract gaze independent of the task: experimental data and computer model. J. Vis. 9(12:10), 1–15 (2009)
Chaabouni, S., Benois-Pineau, J., Zemmari, A., Amar, C.B.: Deep saliency: prediction of interestingness in video with CNN. In: Benois-Pineau, J., Le Callet, P. (eds.) Visual Content Indexing and Retrieval with Psycho-Visual Models. Springer, Cham (2017)
Ciregan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3642–3649 (2012)
Donahue, J., Anne Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2625–2634 (2015)
Dorr, M., Martinetz, T., Gegenfurtner, K., Barth, E.: Variability of eye movements when viewing dynamic natural scenes. J. Vis. 10(10), 1–17 (2010)
de Souza, C.R., Gaidon, A., Vig, E., López, A.M.: Sympathy for the details: Dense trajectories and hybrid classification architectures for action recognition. In: Proceedings of the European Conference on Computer Vision, pp. 697–716. Springer, Cham (2016)
Ester, M., Kriegel, H.P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: KDD Proceedings, vol. 96, pp. 226–231 (1996)
Feichtenhofer, C., Pinz, A., Wildes, R.P.: Dynamically encoded actions based on spacetime saliency. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2755–2764 (2015)
Goldstein, R.B., Woods, R.L., Peli, E.: Where people look when watching movies: Do all viewers look at the same place? Comput. Biol. Med. 3(7), 957–64 (2007)
Harel, J., Koch, C., Perona, P., et al.: Graph-based visual saliency. In: Advances in Neural Information Processing Systems, vol. 1, p. 5 (2006)
Hasson, U., Landesman, O., Knappmeyer, B., Vallines, I., Rubin, N., Heeger, D.J.: Neurocinematics: the neuroscience of film. Projections 2(1), 1–26 (2008)
Hooge, I., Holmqvist, K., Nyström, M.: The pupil is faster than the corneal reflection (CR): are video based pupil-CR eye trackers suitable for studying detailed dynamics of eye movements? Vis. Res. 128, 6–18 (2016)
Judd, T., Ehinger, K., Durand, F., Torralba, A.: Learning to predict where humans look. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), pp. 2106–2113 (2009)
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 IEEE Conference on Computer Vision and Pattern Recognition (2014)
Koch, K., McLean, J., Segev, R., Freed, M.A., II, M.J.B., Balasubramanian, V., Sterling, P.: How much the eye tells the brain. Curr. Biol. 16, 1428–34 (2006)
Lan, Z., Lin, M., Li, X., Hauptmann, A.G., Raj, B.: Beyond Gaussian Pyramid: Multi-skip feature stacking for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 204–212 (2015)
Marat, S., Rahman, A., Pellerin, D., Guyader, N., Houzet, D.: Improving visual saliency by adding ‘face feature map’ and ‘center bias’. Cogn. Comput. 5(1), 63–75 (2013)
Marszalek, M., Laptev, I., Schmid, C.: Actions in context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2929–2936 (2009)
Mathe, S., Sminchisescu, C.: Dynamic eye movement datasets and learnt saliency models for visual action recognition. In: Proceedings of the European Conference on Computer Vision, pp. 842–856. Springer, Berlin (2012)
Mathe, S., Sminchisescu, C.: Actions in the eye: dynamic gaze datasets and learnt saliency models for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(7), 1408–1424 (2015)
Mital, P.K., Smith, T.J., Hill, R., Henderson, J.M.: Clustering of gaze during dynamic scene viewing is predicted by motion. Cogn. Comput. 3(1), 5–24 (2011)
Peng, X., Wang, L., Wang, X., Qiao, Y.: Bag of visual words and fusion methods for action recognition. Comput. Vis. Image Underst. 150(C), 109–125 (2016)
Peters, R.J., Iyer, A., Itti, L., Koch, C.: Components of bottom-up gaze allocation in natural images. Vis. Res. 45(8), 2397–2416 (2005)
Prest, A., Schmid, C., Ferrari, V.: Weakly supervised learning of interactions between humans and objects. IEEE Trans. Pattern Anal. Mach. Intell. 34(3), 601–614 (2012)
Sapienza, M., Cuzzolin, F., Torr, P.H.: Learning discriminative space-time actions from weakly labelled videos. In: Proceedings of the British Machine Vision Conference, vol. 2, p. 3 (2012)
Sapienza, M., Cuzzolin, F., Torr, P.H.: Learning discriminative space–time action parts from weakly labelled videos. Int. J. Comput. Vis. 110(1), 30–47 (2014)
Shapovalova, N., Raptis, M., Sigal, L., Mori, G.: Action is in the eye of the beholder: eye-gaze driven model for spatio-temporal action localization. In: Advances in Neural Information Processing Systems, pp. 2409–2417 (2013)
Shi, F., Petriu, E., Laganiere, R.: Sampling strategies for real-time action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2595–2602 (2013)
Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568–576 (2014)
Smith, T.J., Mital, P.K.: Attentional synchrony and the influence of viewing task on gaze behavior in static and dynamic scenes. J. Vis. 13(8), 16–16 (2013)
Spering, M., Schütz, A.C., Braun, D.I., Gegenfurtner, K.R.: Keep your eyes on the ball: smooth pursuit eye movements enhance prediction of visual motion. J. Neurophysiol. 105(4), 1756–1767 (2011)
Sultani, W., Saleemi, I.: Human action recognition across datasets by foreground-weighted histogram decomposition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 764–771 (2014)
Tatler, B.W.: The central fixation bias in scene viewing: Selecting an optimal viewing position independently of motor biases and image feature distributions. J. Vis. 7(14), 1–17 (2007). http://journalofvision.org/7/14/4/
Tseng, P.H., Carmi, R., Cameron, I.G.M., Munoz, D.P., Itti, L.: Quantifying center bias of observers in free viewing of dynamic natural scenes. J. Vis. 9(7), 1–16 (2009). http://journalofvision.org/9/7/4/
Vig, E., Dorr, M., Cox, D.D.: Saliency-based selection of sparse descriptors for action recognition. In: Proceedings of International Conference on Image Processing, pp. 1405–1408 (2012)
Vig, E., Dorr, M., Cox, D.D.: Space-variant descriptor sampling for action recognition based on saliency and eye movements. In: Proceedings of the European Conference on Computer Vision. LNCS, vol. 7578, pp. 84–97 (2012)
Vig, E., Dorr, M., Martinetz, T., Barth, E.: Intrinsic dimensionality predicts the saliency of natural dynamic scenes. IEEE Trans. Pattern Anal. Mach. Intell. 34(6), 1080–1091 (2012)
Vrigkas, M., Nikou, C., Kakadiaris, I.A.: A review of human activity recognition methods. Front. Robot. AI 2, 28 (2015)
Wang, H., Schmid, C.: Action recognition with improved trajectories. In: Proceedings of the IEEE International Conference on Computer Vision (2013)
Wang, H., Kläser, A., Schmid, C., Liu, C.L.: Action recognition by dense trajectories. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3169–3176. IEEE, New York (2011)
Wang, L., Qiao, Y., Tang, X.: Action recognition with trajectory-pooled deep-convolutional descriptors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4305–4314 (2015)
Wang, H., Oneata, D., Verbeek, J., Schmid, C.: A robust and efficient video representation for action recognition. Int. J. Comput. Vis. 119, 219–38 (2016)
von Wartburg, R., Wurtz, P., Pflugshaupt, T., Nyffeler, T., Lüthi, M., Müri, R.: Size matters: Saccades during scene perception. Perception 36, 355–65 (2007)
Zhou, Y., Yu, H., Wang, S.: Feature sampling strategies for action recognition. arXiv preprint arXiv:1501.06993 (2015)
Zitnick, L., Dollar, P.: Edge boxes: locating object proposals from edges. In: Proceedings of the European Conference on Computer Vision (2014)
Acknowledgements
Our research was supported by the Elite Network Bavaria, funded by the Bavarian State Ministry for Research and Education.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this chapter
Cite this chapter
Dorr, M., Vig, E. (2017). Saliency Prediction for Action Recognition. In: Benois-Pineau, J., Le Callet, P. (eds) Visual Content Indexing and Retrieval with Psycho-Visual Models. Multimedia Systems and Applications. Springer, Cham. https://doi.org/10.1007/978-3-319-57687-9_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-57687-9_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-57686-2
Online ISBN: 978-3-319-57687-9
eBook Packages: Computer ScienceComputer Science (R0)