Modeling global scene factors in attention

被引:182
作者
Torralba, A [1 ]
机构
[1] MIT, Artificial Intelligence Lab, Cambridge, MA 02115 USA
关键词
D O I
10.1364/JOSAA.20.001407
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
Models of visual attention have focused predominantly on bottom-up approaches that ignored structured contextual and scene information. I propose a model of contextual cueing for attention guidance based on the global scene configuration. It is shown that the statistics of low-level features across the whole image can be used to prime the presence or absence of objects in the scene and to predict their location, scale, and appearance before exploring the image. In this scheme, visual context information can become available early in the visual processing chain, which allows modulation of the saliency of image regions and provides an efficient shortcut for object detection and recognition. (C) 2003 Optical Society of America.
引用
收藏
页码:1407 / 1418
页数:12
相关论文
共 53 条
[1]  
[Anonymous], 1998, ATTENTION
[2]  
ARSENIO H, 2002, J VISION, V2, pA733
[3]   SCENE PERCEPTION - DETECTING AND JUDGING OBJECTS UNDERGOING RELATIONAL VIOLATIONS [J].
BIEDERMAN, I ;
MEZZANOTTE, RJ ;
RABINOWITZ, JC .
COGNITIVE PSYCHOLOGY, 1982, 14 (02) :143-177
[4]   Region-based image querying [J].
Carson, C ;
Belongie, S ;
Greenspan, H ;
Malik, J .
IEEE WORKSHOP ON CONTENT-BASED ACCESS OF IMAGE AND VIDEO LIBRARIES, PROCEEDINGS, 1997, :42-49
[5]   Top-down guided eye movements [J].
Chernyak, DA ;
Stark, LW .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2001, 31 (04) :514-522
[6]   Contextual cueing: Implicit learning and memory of visual context guides spatial attention [J].
Chun, MM ;
Jian, YH .
COGNITIVE PSYCHOLOGY, 1998, 36 (01) :28-71
[7]   PERCEPTUAL EFFECTS OF SCENE CONTEXT ON OBJECT IDENTIFICATION [J].
DEGRAEF, P ;
CHRISTIAENS, D ;
DYDEWALLE, G .
PSYCHOLOGICAL RESEARCH-PSYCHOLOGISCHE FORSCHUNG, 1990, 52 (04) :317-329
[8]   MAXIMUM LIKELIHOOD FROM INCOMPLETE DATA VIA EM ALGORITHM [J].
DEMPSTER, AP ;
LAIRD, NM ;
RUBIN, DB .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL, 1977, 39 (01) :1-38
[9]   Visual signal detection in structured backgrounds .1. Effect of number of possible spatial locations and signal contrast [J].
Eckstein, MP ;
Whiting, JS .
JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 1996, 13 (09) :1777-1787
[10]   Computational theories of object recognition [J].
Edelman, Shimon .
TRENDS IN COGNITIVE SCIENCES, 1997, 1 (08) :296-304