Visual Saliency and Reward Saliency Guide Decision Making

25 May, 2020 by NExT

Project Name: Visual Saliency and Reward Saliency Guide Decision Making

Project Sponsor: Ministry of Education

Grant Amount: S$516,000

Duration: 3 Years

Description: Many social and economic decisions we make in real-life require the need to identify numerous alternatives quickly and then evaluate these options visually. Traditional rational choice theories argue that people make decisions based on their mental representations of options; thus, the same option will be evaluated in the same way and lead to identical decisions, regardless of how the stimulus is visually presented. However, recent behavioral economics studies show that the same option is perceived in different ways, depending on how it is framed. Hence, there is accumulating evidence supports the notion that high-level goals influence decision making via top-down mechanisms. What remains largely unexplored is how even low-level visual saliency biases our value-based decision making via bottom-up mechanisms. This project proposes that visual saliency, including low-level, object-level, and semantic-level saliency, drives what individuals pay attention to. In turn, what individuals pay attention to drives their decisions, and their decisions drive their actions. It is plausible that visual saliency guides attention and influences high-level decision making by changing the weights put onto decision dimensions.

Overall, our research aims to delineate neural mechanisms of how visual saliency propagates to the final decision and raise the possibility of a single framework unifying sensible and economical choice. In the end, this project provides an integrated neurobiological account for saliency-based decision making and further leads to more effective commercial and public interest advertisements that optimizing decision-making.

External Projects

Sea State Identification

25 May, 2020

Singapore Restaurant Food Image Annotation

25 May, 2020

Measuring Physical Profile and Use of PCN with Deep Learning and MM Data Analytics

25 May, 2020

Base Metals Price Forecasting from Alternate Data Sources using AI

25 May, 2020

Deep Learning for Recommendation System

25 May, 2020

Multilingual Multimodal Knowledge Graph (M3KG) and Its Application in Smart Nation

25 May, 2020

Visual Saliency and Reward Saliency Guide Decision Making

25 May, 2020

A GPU-based Engine for Dynamic Sparse Matrix Analytics

25 May, 2020

You Are What You Surf: Characterizing Preference and Decision-Making Styles with Digital Footprints

21 May, 2020

Back