Affective saliency map considering psychological distance

Ban, Sang-Woo; Jang, Young-Min

doi:10.1016/j.neucom.2010.07.033

Cited by 16 publications

(9 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we validate the proposed RBS method for the detection of saliency in 3D shapes using three publicly accessible databases: Ohio State University Range Image Database (OSURID) 2 , the Stuttgart Range Image Database (SRID) 3 , and the Stanford 3D Scanning Repository (S3DSR) 4 . While the bunny and david datasets were from S3DSR, the dragon dataset was from SRID, and all the remaining datasets were from OSURID.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

See 1 more Smart Citation

Region-based saliency estimation for 3D shape analysis and understanding

et al. 2016

View full text Add to dashboard Cite

This is the author accepted manuscript. The final version is available from Elsevier via http://dx.doi.org/10.1016/j.neucom.2016.01.012The detection of salient regions is an important pre-processing step for many 3D shape analysis and understanding tasks. This paper proposes a novel method for saliency detection in 3D free form shapes. Firstly, we smooth the surface normals by a bilateral filter. Such a method is capable of smoothing the surfaces and retaining the local details. Secondly, a novel method is proposed for the estimation of the saliency value of each vertex. To this end, two new features are defined: Retinex-based Importance Feature (RIF) and Relative Normal Distance (RND). They are based on the human visual perception characteristics and surface geometry respectively. Since the vertex based method cannot guarantee that the detected salient regions are semantically continuous and complete, we propose to refine such values based on surface patches. The detected saliency is finally used to guide the existing techniques for mesh simplification, interest point detection, and overlapping point cloud registration. The comparative studies based on real data from three publicly accessible databases show that the proposed method usually outperforms five selected state of the art ones both qualitatively and quantitatively for saliency detection and 3D shape analysis and understandingauthorsversionPeer reviewe

show abstract

Section: Experimental Results and Analysismentioning

confidence: 99%

“…Most of the existing saliency detection and estimation works are inspired by corresponding work on 2D images [17,14,15,13,5,31,32,3]. In this section, we will review the most related work that operate 3D data directly.…”

Section: Related Workmentioning

confidence: 99%

Region-based saliency estimation for 3D shape analysis and understanding

et al. 2016

View full text Add to dashboard Cite

show abstract

“…Spatial cues predicting the probable location of a target are commonly used as an operational manipulation of covert visual attention [2]. Human's visual selective attention is a very complex process where many factors, such as visual saliency, goals, intentions, affection, experience, etc., are involved directly and/or indirectly [8][9][10][11][12][13][14][15][16][17][18]. However, it is obvious that the human brain utilizes not only visual features of an input scene but also memorized spatial information obtained from previous experience with efficient visual search.…”

Section: Introductionmentioning

confidence: 99%

“…Many visual selective attention models have been introduced for efficient processing of complex visual scenes [9][10][11][12][13][14][15][16][17]. A big challenge is the degree to which a visual attention model agrees with biological findings [1].…”

Section: Introductionmentioning

confidence: 99%

“…Walther and Koch also proposed a top-down attention model having a bias based on features generated from a bottom-up process [13]. Ban et al proposed top-down attention reflecting a human affective factor based on a psychological distance mechanism [14]. Carmi and Itti proposed an attention model that considered seven dynamic features in MTV-style video clips [15].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation