AI Paper Atlas

Research map / Detection and segmentation / CNN features

Driver Attention as Competitive Allocation: A Scene--Task-Aware Dual-Branch Framework

Qianfang Wang, Bin Rao, Pengpeng Xu, Tiantian Chen

NeurIPS 2026 · Detection and segmentation › CNN features · approach: Lane detection

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a scene-task-aware dual-branch framework that models driver attention as a competitive allocation between bottom-up visual saliency and top-down task-driven components, rather than direct scene-to-heatmap regression.

Problem

Driver attention prediction is typically treated as scene-to-heatmap regression, which fails to capture the underlying dynamic attention redistribution mechanism.

Approach

Decomposes driver attention into bottom-up visual saliency and top-down scene/task-driven components that compete for allocation, implemented as a dual-branch framework.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy