References

• 1. 1)
     • [20]. Chen, L. C., Papandreou, G., Kokkinos, I., et al: ‘Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution’, arXiv preprint arXiv: 1606.00915, 2016.
  2. 2)
     • [35]. Garcia-Diaz, A., Fdez-Vidal, X. R., Pardo, X. M., et al: ‘Saliency from hierarchical adaptation through decorrelation and variance normalization’, Image Vis. Comput., 2012, 30, (1), pp. 51–64 (doi: 10.1016/j.imavis.2011.11.007).
  3. 3)
     • [32]. Zhang, L., Tong, M. H., Marks, T. K., et al: ‘SUN: a Bayesian framework for saliency using natural statistic’, J. Vis., 2008, 8, (7), p. 32 (doi: 10.1167/8.7.32).
  4. 4)
     • [25]. Kümmerer, M., Wallis, T. S., Bethge, M.: ‘Deepgaze II: reading fixations from deep features trained on object recognition’, arXiv preprint arXiv: 1610.01563, 2016.
  5. 5)
     • [5]. Sitzmann, V., Serrano, A., Pavel, A., et al: ‘Saliency in VR: How do people explore virtual environments?’, IEEE Trans. Vis. Comput. Graph., 2018, 99, pp. 1633–1642 (doi: 10.1109/TVCG.2018.2793599).
  6. 6)
     • 18. Hou, X., Harel, J., Koch, C.: ‘Image signature: highlighting sparse salient regions’, IEEE Trans. Pattern Anal. Mach. Intell., 2012, 34, (1), pp. 194–201 (doi: 10.1109/TPAMI.2011.146).
  7. 7)
     • [9]. He, K., Zhang, X., Ren, S., et al: ‘Deep residual learning for image recognition’. Conf. on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016.
  8. 8)
     • [51]. Tatler, B. W., Baddeley, R. J., Gilchrist, I. D.: ‘Visual correlates of fixation selection: effects of scale and time’, Vis. Res., 2005, 45, (5), pp. 643–659 (doi: 10.1016/j.visres.2004.09.017).
  9. 9)
     • [49]. Judd, T., Ehinger, K., Durand, F., et al: ‘Learning to predict where humans look’. Int. Conf. on Computer Vision, Kyoto, Japan, 2009.
  10. 10)
      • [23]. Huang, X., Shen, C., Boix, X., et al: ‘Salicon: reducing the semantic gap in saliency prediction by adapting deep neural networks’. Int. Conf. on Computer Vision, Santiago, Chile, 2015.
  11. 11)
      • [50]. Bylinskii, Z., Judd, T., Oliva, A., et al: ‘What do different evaluation metrics tell us about saliency models?’, arXiv preprint arXiv:1604.03605, 2016.
  12. 12)
      • [19]. Yu, F., Koltun, V.: ‘Multi-scale context aggregation by dilated convolutions’. Int. Conf. on Learning Representation, San Juan, Puerto Rico, 2016.
  13. 13)
      • [8]. Simonyan, K., Zisserman, A.: ‘Very deep convolutional networks for large-scale image recognition’. Int. Conf. on Learning Representations, San Diego, USA, 2015.
  14. 14)
      • [53]. Jost, T., Ouerhani, N., Wartburg, R., et al: ‘Assessing the contribution of color in visual attention’, Comput. Vis. Image Underst., 2005, 100, (1), pp. 107–123 (doi: 10.1016/j.cviu.2004.10.009).
  15. 15)
      • [55]. ‘Torchvision’. Available at https://github.com/pytorch/vision.
  16. 16)
      • [43]. Maas, A. L., Hannun, A. Y., Ng, A. Y.: ‘Rectifier nonlinearities improve neural network acoustic models’. Int. Conf. on Machine Learning, Atlanta, USA, 2013.
  17. 17)
      • 11. Li, J., Tian, Y.H., Huang, T.J.: ‘Visual saliency with statistical priors’, Int. J. Comput. Vis., 2014, 107, (3), pp. 239–253 (doi: 10.1007/s11263-013-0678-0).
  18. 18)
      • [31]. Harel, J., Koch, C., Perona, P.: ‘Graph-based visual saliency’, Adv. Neural. Inf. Process. Syst., 2007, 19, pp. 545–552.
  19. 19)
      • 1. Itti, L., Koch, C., Niebur, E.: ‘A model of saliency-based visual attention for rapid scene analysis’, IEEE Trans. Pattern Anal. Mach. Intell., 1998, 20, (11), pp. 1254–1259 (doi: 10.1109/34.730558).
  20. 20)
      • [47]. Li, Y., Hou, X., Koch, C., et al: ‘The secrets of salient object segmentation’. Conf. on Computer Vision and Pattern Recognition, Columbus, USA, 2014.
  21. 21)
      • [14]. Chen, Y., Li, J., Xiao, H., et al: ‘Dual path networks’, Adv. Neural. Inf. Process. Syst., 2017, 30, pp. 4467–4475.
  22. 22)
      • [24]. Kruthiventi, S. S. S., Ayush, K., Babu, R. V.: ‘Deepfix: a fully convolutional neural network for predicting human eye fixations’, arXiv preprint arXiv: 1510.02927, 2015.
  23. 23)
      • [56]. Tieleman, T., Hinton, G.: ‘Torchvision’, COURSERA: Neural Networks for Machine Learning, 2012.
  24. 24)
      • [15]. Girshick, R., Donahue, J., Darrell, T., et al: ‘Rich feature hierarchies for accurate object detection and semantic segmentation’. Conf. on Computer Vision and Pattern Recognition, Columbus, USA, 2014.
  25. 25)
      • [17]. Redmon, J., Divvala, S., Girshick, R., et al: ‘You only look once: unified, real-time object detection’. Conf. on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016.
  26. 26)
      • [25]. Hochreiter, S., Schmidhuber, J.: ‘Long short-term memory’, Neural Comput., 1997, 9, (8), pp. 1735–1780 (doi: 10.1162/neco.1997.9.8.1735).
  27. 27)
      • [13]. Pleiss, G., Chen, D., Huang, G., et al: ‘Memory-efficient implementation of densenets’, arXiv preprint arXiv:1707.06990, 2017.
  28. 28)
      • [52]. Peters, R. J., Iyer, A., Itti, L., et al: ‘Components of bottom-up gaze allocation in natural images’, Vis. Res., 2005, 45, (18), pp. 2397–2416 (doi: 10.1016/j.visres.2005.03.019).
  29. 29)
      • [26]. Liu, N., Han, J.: ‘A deep spatial contextual long-term recurrent convolutional network for saliency detection’, arXiv preprint arXiv: 1610.01708, 2016.
  30. 30)
      • [10]. Iandola, F. N., Han, S., Moskewicz, M. W., et al: ‘SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size’, arXiv preprint arXiv:1602.07360, 2016.
  31. 31)
      • [16]. Ren, S., He, K., Girshick, R., et al: ‘Faster R-CNN: towards real-time object detection with region proposal networks’, Adv. Neural. Inf. Process. Syst., 2015, 28, pp. 91–99.
  32. 32)
      • [39]. Bylinskii, Z., Judd, T., Borji, A., et al: ‘MIT saliency benchmark’. Available at http://saliency.mit.edu.
  33. 33)
      • [21]. Vig, E., Dorr, M., Cox, D.: ‘Large-scale optimization of hierarchical features for saliency prediction in natural images’. Conf. on Computer Vision and Pattern Recognition, Columbus, USA, 2014.
  34. 34)
      • [54]. Judd, T., Durand, F., Torralba, A.: ‘A benchmark of computational models of saliency to predict human fixations’. MIT Technical Report, 2012.
  35. 35)
      • [33]. Hou, X., Zhang, L.: ‘Dynamic visual attention: searching for coding length increments’, Adv. Neural. Inf. Process. Syst., 2009, 21, pp. 681–688.
  36. 36)
      • [4]. Ardizzone, E., Bruno, A., Mazzola, G.: ‘Saliency based image cropping’. Int. Conf. on Image Analysis and Processing, Naples, Italy, 2013, pp. 773–782.
  37. 37)
      • [12]. Xie, S., Girshick, R., Dollár, P., et al: ‘Aggregated residual transformations for deep neural networks’. Conf. on Computer Vision and Pattern Recognition, Honolulu, USA, 2017, pp. 5987–5995.
  38. 38)
      • [44]. Ioffe, S., Szegedy, C.: ‘Batch normalization: accelerating deep network training by reducing internal covariate shift’. Int. Conf. on Machine Learning, Lille, France, 2015.
  39. 39)
      • [2]. Feng, Y., Cheung, G., Tan, W. T., et al: ‘Gaze-driven video streaming with saliency-based dual-stream switching’, Vis. Commun. Image Process., San Diego, USA, 2012, pp. 1–6.
  40. 40)
      • [28]. Taiki, O., Takao, Y.: ‘Fully convolutional DenseNet for saliency-map prediction’. Asian Conf. on Pattern Recognition, Nanjing, China, 2017.
  41. 41)
      • [7]. Krizhevsky, A., Sutskever, I., Hinton, G. E.: ‘ImageNet classification with deep convolutional neural networks’, Adv. Neural. Inf. Process. Syst., 2012, 25, pp. 1097–1105.
  42. 42)
      • [57]. ‘Pytorch’. Available at https://github.com/pytorch/pytorch.
  43. 43)
      • [1]. Zünd, F., Pritch, Y., Sorkine-Hornung, A., et al: ‘Content-aware compression using saliency-driven image retargeting’, IEEE Int. Conf. Image Process., Melbourne, Australia, 2013, pp. 1845–1849.
  44. 44)
      • [3]. Panozzo, D., Weber, O., Sorkine, O.: ‘Robust image retargeting via axis-aligned deformation’, Comput. Graph. Forum, 2012, 31, pp. 229–236 (doi: 10.1111/j.1467-8659.2012.03001.x).
  45. 45)
      • [18]. Long, J., Shelhamer, E., Darrell, T.: ‘Fully convolutional networks for semantic segmentation’. Conf. on Computer Vision and Pattern Recognition, Boston, USA, 2015.
  46. 46)
      • [30]. Bruce, N., Tsotsos, J.: ‘Saliency based on information maximization’, Adv. Neural. Inf. Process. Syst., 2005, 18, pp. 155–162.
  47. 47)
      • [27]. Cornia, M., Baraldi, L., Serra, G., et al: ‘Predicting human eye fixations via an LSTM-based saliency attentive model’, arXiv preprint arXiv: 1611.09571, 2016.
  48. 48)
      • [48]. Everingham, M., Winn, J.: ‘The PASCAL visual object classes challenge 2010 (VOC2010) development kit’, 2010.
  49. 49)
      • [11]. Huang, G., Liu, Z., Weinberger, K. Q.: ‘Densely connected convolutional networks’. Conf. on Computer Vision and Pattern Recognition, Honolulu, USA, 2017, vol. 1, p. 3.
  50. 50)
      • [45]. Jiang, M., Huang, S., Duan, J., et al: ‘Salicon: saliency in context’. Conf. on Computer Vision and Pattern Recognition, Boston, USA, 2015.
  51. 51)
      • [42]. Shi, W., Caballero, J., Huszar, F., et al: ‘Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network’. Conf. on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016.
  52. 52)
      • [41]. Zeiler, M. D., Taylor, G. W., Fergus, R.: ‘Adaptive deconvolutional networks for mid and high level feature learning’. Int. Conf. on Computer Vision, Barcelona, Spain, 2011, pp. 1735–1780.
  53. 53)
      • [46]. Xu, J., Jiang, M., Wang, S., et al: ‘Predicting human gaze beyond pixels’, J. Vis., 2014, 14, (1), pp. 1–20 (doi: 10.1167/14.1.28).
  54. 54)
      • 22. Itti, L., Koch, C.: ‘Computational modelling of visual attention’, Nat. Rev. Neurosci., 2001, 2, (3), pp. 194–203 (doi: 10.1038/35058500).
  55. 55)
      • [38]. Deng, J., Dong, W., Socher, R., et al: ‘ImageNet: a large-scale hierarchical image database’. Conf. on Computer Vision and Pattern Recognition, Miami, USA, 2009.
  56. 56)
      • [58]. Bylinskii, Z., Recasens, A., Borji, A., et al: ‘Where should saliency models look next?’. European Conf. on Computer Vision, 2016.
  57. 57)
      • [22]. Kümmerer, M., Theis, L., Bethge, M.: ‘Deep gaze I: boosting saliency prediction with feature maps trained on ImageNet’. Int. Conf. on Learning Representation, San Diego, USA, 2015.
  58. 58)
      • [36]. Borji, A., Tanner, J.: ‘Reconciling saliency and object center-bias hypotheses in explaining free-viewing fixations’, IEEE Trans. Neural Netw. Learn. Syst., 2016, 24, (6), pp. 1214–1226 (doi: 10.1109/TNNLS.2015.2480683).