Paper  abstract   bibtex   

@article{
 title = {Modeling the influence of task on attention},
 type = {article},
 identifiers = {[object Object]},
 keywords = {Attention,Bottom-up,Object detection,Recognition,Scene analysis,Task-relevance,Top-down},
 id = {cb89dc40-bd68-3f0d-9c96-7c9824db361b},
 created = {2017-09-01T15:54:06.416Z},
 file_attached = {true},
 profile_id = {80da7853-f7b7-36a9-8e4c-d7ddb2d9e538},
 group_id = {a2333ea3-15a4-3d40-8d36-f0d9590ca926},
 last_modified = {2017-09-01T15:54:06.531Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 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 entityÕs 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 modelÕs 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.},
 bibtype = {article},
 author = {Navalpakkam, Vidhya and Itti, Laurent}
}