Contextual Influences on Saliency
This article describes a model for including scene/context priors in attention guidance. In the proposed scheme, visual context information can be available early in the visual processing chain, in order to modulate the saliency of image regions and to provide an efficient short cut for object detec...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2005
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/30460 |
| _version_ | 1811093907956563968 |
|---|---|
| author | Torralba, Antonio |
| author_facet | Torralba, Antonio |
| author_sort | Torralba, Antonio |
| collection | MIT |
| description | This article describes a model for including scene/context priors in attention guidance. In the proposed scheme, visual context information can be available early in the visual processing chain, in order to modulate the saliency of image regions and to provide an efficient short cut for object detection and recognition. The scene is represented by means of a low-dimensional global description obtained from low-level features. The global scene features are then used to predict the probability of presence of the target object in the scene, and its location and scale, before exploring the image. Scene information can then be used to modulate the saliency of image regions early during the visual processing in order to provide an efficient short cut for object detection and recognition. |
| first_indexed | 2024-09-23T15:52:36Z |
| id | mit-1721.1/30460 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T15:52:36Z |
| publishDate | 2005 |
| record_format | dspace |
| spelling | mit-1721.1/304602019-04-12T08:37:44Z Contextual Influences on Saliency Torralba, Antonio AI Attention context saliency scene recognition object detection This article describes a model for including scene/context priors in attention guidance. In the proposed scheme, visual context information can be available early in the visual processing chain, in order to modulate the saliency of image regions and to provide an efficient short cut for object detection and recognition. The scene is represented by means of a low-dimensional global description obtained from low-level features. The global scene features are then used to predict the probability of presence of the target object in the scene, and its location and scale, before exploring the image. Scene information can then be used to modulate the saliency of image regions early during the visual processing in order to provide an efficient short cut for object detection and recognition. 2005-12-22T01:26:54Z 2005-12-22T01:26:54Z 2004-04-14 MIT-CSAIL-TR-2004-020 AIM-2004-009 http://hdl.handle.net/1721.1/30460 en_US Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory 12 p. 18377938 bytes 597436 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | AI Attention context saliency scene recognition object detection Torralba, Antonio Contextual Influences on Saliency |
| title | Contextual Influences on Saliency |
| title_full | Contextual Influences on Saliency |
| title_fullStr | Contextual Influences on Saliency |
| title_full_unstemmed | Contextual Influences on Saliency |
| title_short | Contextual Influences on Saliency |
| title_sort | contextual influences on saliency |
| topic | AI Attention context saliency scene recognition object detection |
| url | http://hdl.handle.net/1721.1/30460 |
| work_keys_str_mv | AT torralbaantonio contextualinfluencesonsaliency |