Hinweis
Dieser Eintrag wurde automatisch aus einem Altsystem migriert. Die Daten wurden nicht überprüft und entsprechen eventuell nicht den Qualitätskriterien des vorliegenden Systems.
Weibel, J.-B., Li Tan, H., & Lu, S. (2017). An Integrated Approach To Visual Attention Modelling Using Spatial-Temporal Saliency And Objectness. In Ieee Icip 2017 (p. 5). http://hdl.handle.net/20.500.12708/75806
E376 - Institut für Automatisierungs- und Regelungstechnik
-
Erschienen in:
Ieee Icip 2017
-
Datum (veröffentlicht):
2017
-
Veranstaltungsname:
IEEE Int. Conference on Image Processing (ICIP)
-
Veranstaltungszeitraum:
26-Sep-2010 - 29-Sep-2010
-
Veranstaltungsort:
Hong Kong, Außerhalb der EU
-
Umfang:
5
-
Peer Reviewed:
Nein
-
Abstract:
Visual attention modelling is an important research
topic with a wide range of applications in visual tracking,
perceptual quality assessment, re-targeting, video summarization,
etc. In this paper, we propose a visual attention model that
captures both bottom-up spatial-temporal saliency and topdown
objectness. Leveraging on co-occurrence histograms, the
proposed model captures a number of l...
Visual attention modelling is an important research
topic with a wide range of applications in visual tracking,
perceptual quality assessment, re-targeting, video summarization,
etc. In this paper, we propose a visual attention model that
captures both bottom-up spatial-temporal saliency and topdown
objectness. Leveraging on co-occurrence histograms, the
proposed model captures a number of low-level cues including
contrast, gradient, as well as, magnitude and gradient of optical
flow. Additionally, the proposed model incorporates mid-level
objectness cue which helps to boost the modelling performance
greatly. The proposed model obtained superior AUC-ROCs when
evaluated over the ASCMN dataset and the UCF Sports Action
dataset.
