Please use this identifier to cite or link to this item:
https://scholarbank.nus.edu.sg/handle/10635/154983
DC Field | Value | |
---|---|---|
dc.title | COMPUTATIONAL MODELS OF BOTTOM-UP AND TOP-DOWN VISUAL ATTENTION | |
dc.contributor.author | ZHANG MENGMI | |
dc.date.accessioned | 2019-05-31T18:02:51Z | |
dc.date.available | 2019-05-31T18:02:51Z | |
dc.date.issued | 2019-01-17 | |
dc.identifier.citation | ZHANG MENGMI (2019-01-17). COMPUTATIONAL MODELS OF BOTTOM-UP AND TOP-DOWN VISUAL ATTENTION. ScholarBank@NUS Repository. | |
dc.identifier.uri | https://scholarbank.nus.edu.sg/handle/10635/154983 | |
dc.description.abstract | Humans have the remarkable ability of prioritizing the sequence of eye-fixations to survey a complex environment. This ability enables us to react rapidly to environmental changes, and maximize the amount of useful information obtained from visual inputs, in spite of the limited high-acuity processing capability and memory capacity in the brain. This thesis describes several biologically-inspired computational implementations of integrated bottom-up and top-down visual attention that learn to exploit the temporal dynamics across fixations via supervised training, and modulate the visual processing pathway in a top-down fashion via zero-shot learning. These models not only contribute to the development of artificial intelligence in terms of state-of-the-art prediction of fixation locations and anticipation in images, as well as egocentric and third-person videos, but also provide insights into the mechanisms of human visual attention. The latter was demonstrated by closely approximating the behavior of human eye movements in a series of psychophysics experiments. | |
dc.language.iso | en | |
dc.subject | visual attention, saliency, biologically-inspired vision, bottom-up attention, top-down attention, eye fixation | |
dc.type | Thesis | |
dc.contributor.department | DEAN'S OFFICE (NGS FOR INTGR SCI & ENGG) | |
dc.contributor.supervisor | YEN SHIH-CHENG | |
dc.contributor.supervisor | LIM JOO HWEE | |
dc.contributor.supervisor | FENG JIASHI | |
dc.description.degree | Ph.D | |
dc.description.degreeconferred | DOCTOR OF PHILOSOPHY | |
dc.identifier.orcid | 0000-0002-2694-7097 | |
Appears in Collections: | Ph.D Theses (Open) |
Show simple item record
Files in This Item:
File | Description | Size | Format | Access Settings | Version | |
---|---|---|---|---|---|---|
ZhangMM_thesis.pdf | 24.34 MB | Adobe PDF | OPEN | None | View/Download |
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.