Skip to main content

2015 | OriginalPaper | Buchkapitel

Gaze Shifting Kernel: Engineering Perceptually- Aware Features for Scene Categorization

verfasst von : Luming Zhang, Richang Hong, Meng Wang

Erschienen in: Advances in Multimedia Information Processing -- PCM 2015

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

In this paper, we propose a novel gaze shifting kernel for scene image categorization, focusing on discovering the mechanism of humans perceiving visually/semantically salient regions in a scene. First, a weakly supervised embedding algorithm projects the local image descriptors (i.e., graphlets) into a pre-specified semantic space. Afterward, each graphlet can be represented by multiple visual features at both low-level and high-level. As humans typically attend to a small fraction of regions in a scene, a sparsity-constrained graphlet ranking algorithm is proposed to dynamically integrate both the low-level and the high-level visual cues. The top-ranked graphlets are either visually or semantically salient according to human perception. They are linked into a path to simulate human gaze shifting. Finally, we calculate the gaze shifting kernel (GSK) based on the discovered paths from a set of images. Experiments on the USC scene and the ZJU aerial image data sets demonstrate the competitiveness of our GSK, as well as the high consistency of the predicted path with real human gaze shifting path.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Guestrin, E.D., Eizenman, M.: General theory of remote gaze estimation using the pupil center and corneal reflections. IEEE T-BE 53(6), 1124–1133 (2006) Guestrin, E.D., Eizenman, M.: General theory of remote gaze estimation using the pupil center and corneal reflections. IEEE T-BE 53(6), 1124–1133 (2006)
2.
Zurück zum Zitat Jixu, C., Qiang, J.: Probabilistic gaze estimation without active personal calibration. In: Proceedings of CVPR (2011) Jixu, C., Qiang, J.: Probabilistic gaze estimation without active personal calibration. In: Proceedings of CVPR (2011)
3.
Zurück zum Zitat Nakazawa, A., Nitschke, C.: Point of gaze estimation through corneal surface reflection in an active illumination environment. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 159–172. Springer, Heidelberg (2012) CrossRef Nakazawa, A., Nitschke, C.: Point of gaze estimation through corneal surface reflection in an active illumination environment. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 159–172. Springer, Heidelberg (2012) CrossRef
4.
Zurück zum Zitat Murphy-Chutorian, E., Trivedi, M.M.: Head pose estimation in computer vision: a survey. IEEE T-PAMI 31(4), 607–626 (2009)CrossRef Murphy-Chutorian, E., Trivedi, M.M.: Head pose estimation in computer vision: a survey. IEEE T-PAMI 31(4), 607–626 (2009)CrossRef
5.
Zurück zum Zitat Cai, Q., Gallup, D., Zhang, C., Zhang, Z.: Head 3D deformable face tracking with a commodity depth camera. In: Proceeding of ECCV (2010) Cai, Q., Gallup, D., Zhang, C., Zhang, Z.: Head 3D deformable face tracking with a commodity depth camera. In: Proceeding of ECCV (2010)
6.
Zurück zum Zitat Lu, F., Okabe, T., Sugano, Y., Sato, Y.: A head pose-free approach for appearance-based gaze estimation. In: Proceedings of BMVC (2011) Lu, F., Okabe, T., Sugano, Y., Sato, Y.: A head pose-free approach for appearance-based gaze estimation. In: Proceedings of BMVC (2011)
7.
Zurück zum Zitat Mora, K.A.F., Odobez, J.-M.: Gaze estimation from multimodal kinect data. In: CVPR Workshop (2012) Mora, K.A.F., Odobez, J.-M.: Gaze estimation from multimodal kinect data. In: CVPR Workshop (2012)
8.
Zurück zum Zitat Mora, K.A.F., Odobez, J.-M.: Person independent 3D gaze estimation from remote RGB-D camera. In: Proceedings of ICIP (2013) Mora, K.A.F., Odobez, J.-M.: Person independent 3D gaze estimation from remote RGB-D camera. In: Proceedings of ICIP (2013)
9.
Zurück zum Zitat Moosmann, F., Larlus, D., Frederic, J.: Learning saliency maps for object categorization. In: ECCV Workshop (2006) Moosmann, F., Larlus, D., Frederic, J.: Learning saliency maps for object categorization. In: ECCV Workshop (2006)
10.
Zurück zum Zitat Gao, D., Vasconcelos, N.: Discriminant saliency for visual recognition from cluttered scenes. In: Proceedings of NIPS (2004) Gao, D., Vasconcelos, N.: Discriminant saliency for visual recognition from cluttered scenes. In: Proceedings of NIPS (2004)
11.
Zurück zum Zitat Gao, D., Vasconcelos, N.: Integrated learning of saliency, complex features and object detectors from cluttered scenes. In: Proceedings of CVPR (2005) Gao, D., Vasconcelos, N.: Integrated learning of saliency, complex features and object detectors from cluttered scenes. In: Proceedings of CVPR (2005)
12.
Zurück zum Zitat Parikh, D., Zitnick, C.L., Chen, T.: Determining patch saliency using low-level context. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 446–459. Springer, Heidelberg (2008) CrossRef Parikh, D., Zitnick, C.L., Chen, T.: Determining patch saliency using low-level context. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 446–459. Springer, Heidelberg (2008) CrossRef
13.
Zurück zum Zitat Oliva, A., Torralba, A., Castelhano, M.S., Henderson, J.M.: Top-down control of visual attention in object detection. In: Proceedings of ICCV (2009) Oliva, A., Torralba, A., Castelhano, M.S., Henderson, J.M.: Top-down control of visual attention in object detection. In: Proceedings of ICCV (2009)
14.
Zurück zum Zitat Harada, T., Ushiku, Y., Yuya Y.: Discriminative spatial pyramid. In: Proceedings of CVPR, Yasuo Kuniyoshi (2011) Harada, T., Ushiku, Y., Yuya Y.: Discriminative spatial pyramid. In: Proceedings of CVPR, Yasuo Kuniyoshi (2011)
15.
Zurück zum Zitat Yao, B., Khosla, A., Fei-Fei, L.: Combining randomization and discrimination for fine-grained image categorization. In: Proceedings of CVPR (2011) Yao, B., Khosla, A., Fei-Fei, L.: Combining randomization and discrimination for fine-grained image categorization. In: Proceedings of CVPR (2011)
16.
Zurück zum Zitat Zhang, L., Song, M., Zhao, Q., Liu, X., Bu, J., Chen, C.: Probabilistic graphlet transfer for photo cropping. IEEE T-IP 21(5), 803–815 (2013) Zhang, L., Song, M., Zhao, Q., Liu, X., Bu, J., Chen, C.: Probabilistic graphlet transfer for photo cropping. IEEE T-IP 21(5), 803–815 (2013)
17.
Zurück zum Zitat Lin, Z., Chen, M., Ma, Y.: The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices, arXiv preprint (2010). arXiv:1009.5055 Lin, Z., Chen, M., Ma, Y.: The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices, arXiv preprint (2010). arXiv:​1009.​5055
18.
Zurück zum Zitat Zhang, L., Han, Y., Yang, Y., Song, M., Yan, S., Tian, Q.: Discovering discriminative graphlets for aerial image categories recognition. IEEE T-IP 22(12), 5071–5084 (2013)MathSciNetCrossRef Zhang, L., Han, Y., Yang, Y., Song, M., Yan, S., Tian, Q.: Discovering discriminative graphlets for aerial image categories recognition. IEEE T-IP 22(12), 5071–5084 (2013)MathSciNetCrossRef
19.
Zurück zum Zitat Siagian, C., Itti, L.: Rapid biologically-inspired scene classification using features shared with visual attention. IEEE T-PAMI 29(2), 300–312 (2007)CrossRef Siagian, C., Itti, L.: Rapid biologically-inspired scene classification using features shared with visual attention. IEEE T-PAMI 29(2), 300–312 (2007)CrossRef
20.
Zurück zum Zitat Harchaoui, Z., Bach, F.: Image classification with segmentation graph kernels. In: Proceedings of ICCV (2007) Harchaoui, Z., Bach, F.: Image classification with segmentation graph kernels. In: Proceedings of ICCV (2007)
21.
Zurück zum Zitat Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of ICCV (2006) Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of ICCV (2006)
22.
Zurück zum Zitat Wang, J., Yang, J., Yu, K., Lv, F., Huang, T., Gong, Y.: Locality-constrained linear coding for image classification. In: Proceedings of CVPR (2010) Wang, J., Yang, J., Yu, K., Lv, F., Huang, T., Gong, Y.: Locality-constrained linear coding for image classification. In: Proceedings of CVPR (2010)
23.
Zurück zum Zitat Yang, J., Yu, K., Gong, Y., Huang, T.: Linear spatial pyramid matching using sparse coding for image classification. In: Proceedings of CVPR (2009) Yang, J., Yu, K., Gong, Y., Huang, T.: Linear spatial pyramid matching using sparse coding for image classification. In: Proceedings of CVPR (2009)
24.
Zurück zum Zitat Li, L.-J., Su, H., Xing, E.P., Fei-Fei, L.: Object bank: a high-level image representation for scene classification and semantic feature sparsification. In: Proceedings of NIPS (2010) Li, L.-J., Su, H., Xing, E.P., Fei-Fei, L.: Object bank: a high-level image representation for scene classification and semantic feature sparsification. In: Proceedings of NIPS (2010)
25.
Zurück zum Zitat Hou, X., Harel, J., Koch, C., Signature, I.: Highlighting sparse salient regions. IEEE T-PAMI 34(1), 194–201 (2012)CrossRef Hou, X., Harel, J., Koch, C., Signature, I.: Highlighting sparse salient regions. IEEE T-PAMI 34(1), 194–201 (2012)CrossRef
26.
Zurück zum Zitat Yao, B., Yang, X., Zhu, S.-C.: Introduction to a large scale general purpose ground truth dataset: methodology, annotation tool, and benchmarks. In: EMMCVPR (2007) Yao, B., Yang, X., Zhu, S.-C.: Introduction to a large scale general purpose ground truth dataset: methodology, annotation tool, and benchmarks. In: EMMCVPR (2007)
Metadaten
Titel
Gaze Shifting Kernel: Engineering Perceptually- Aware Features for Scene Categorization
verfasst von
Luming Zhang
Richang Hong
Meng Wang
Copyright-Jahr
2015
DOI
https://doi.org/10.1007/978-3-319-24075-6_25

Neuer Inhalt