Modeling the influence of task on attention.

@article{navalpak05, abstract = {We propose a computational model for the task-specific guidance of visual attention in real-world scenes. Our model emphasizes four aspects that are important in biological vision: determining task-relevance of an entity, biasing attention for the low-level visual features of desired targets, recognizing these targets using the same low-level features, and incrementally building a visual map of task-relevance at every scene location. Given a task definition in the form of keywords, the model first determines and stores the task-relevant entities in working memory, using prior knowledge stored in long-term memory. It attempts to detect the most relevant entity by biasing its visual attention system with the entity's learned low-level features. It attends to the most salient location in the scene, and attempts to recognize the attended object through hierarchical matching against object representations stored in long-term memory. It updates its working memory with the task-relevance of the recognized entity and updates a topographic task-relevance map with the location and relevance of the recognized entity. The model is tested on three types of tasks: single-target detection in 343 natural and synthetic images, where biasing for the target accelerates target detection over twofold on average; sequential multiple-target detection in 28 natural images, where biasing, recognition, working memory and long term memory contribute to rapidly finding all targets; and learning a map of likely locations of cars from a video clip filmed while driving on a highway. The model's performance on search for single features and feature conjunctions is consistent with existing psychophysical data. These results of our biologically-motivated architecture suggest that the model may provide a reasonable approximation to many brain processes involved in complex task-driven visual behaviors.}, address = {Department of Computer Science, Psychology and Neuroscience Graduate Program, University of Southern California, Hedco Neuroscience Building, Room 30A, Mail Code 2520, 3641 Watt Way, Los Angeles, CA 90089-2520, USA. navalpak@usc.edu}, author = {Navalpakkam, V. and Itti, L. }, citeulike-article-id = {147950}, doi = {10.1016/j.visres.2004.07.042}, issn = {0042-6989}, journal = {Vision Res}, keywords = {attention, down, driven, saliency, task, top, visual}, month = {January}, number = {2}, pages = {205--231}, posted-at = {2005-04-03 09:10:01}, priority = {0}, title = {Modeling the influence of task on attention.}, url = {http://dx.doi.org/10.1016/j.visres.2004.07.042}, volume = {45}, year = {2005} }

TY - JOUR ID - navalpak05 L3 - citeulike-article-id:147950 TI - Modeling the influence of task on attention. JF - Vision Res VL - 45 IS - 2 SP - 205 EP - 231 AD - Department of Computer Science, Psychology and Neuroscience Graduate Program, University of Southern California, Hedco Neuroscience Building, Room 30A, Mail Code 2520, 3641 Watt Way, Los Angeles, CA 90089-2520, USA. navalpak@usc.edu SN - 0042-6989 N2 - We propose a computational model for the task-specific guidance of visual attention in real-world scenes. Our model emphasizes four aspects that are important in biological vision: determining task-relevance of an entity, biasing attention for the low-level visual features of desired targets, recognizing these targets using the same low-level features, and incrementally building a visual map of task-relevance at every scene location. Given a task definition in the form of keywords, the model first determines and stores the task-relevant entities in working memory, using prior knowledge stored in long-term memory. It attempts to detect the most relevant entity by biasing its visual attention system with the entity's learned low-level features. It attends to the most salient location in the scene, and attempts to recognize the attended object through hierarchical matching against object representations stored in long-term memory. It updates its working memory with the task-relevance of the recognized entity and updates a topographic task-relevance map with the location and relevance of the recognized entity. The model is tested on three types of tasks: single-target detection in 343 natural and synthetic images, where biasing for the target accelerates target detection over twofold on average; sequential multiple-target detection in 28 natural images, where biasing, recognition, working memory and long term memory contribute to rapidly finding all targets; and learning a map of likely locations of cars from a video clip filmed while driving on a highway. The model's performance on search for single features and feature conjunctions is consistent with existing psychophysical data. These results of our biologically-motivated architecture suggest that the model may provide a reasonable approximation to many brain processes involved in complex task-driven visual behaviors. KW - attention KW - down KW - driven KW - saliency KW - task KW - top KW - visual AU - Navalpakkam, V AU - Itti, L PY - 2005/01// UR - http://dx.doi.org/10.1016/j.visres.2004.07.042 ER -