AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Where, What, Why: Towards Explainable Driver Attention Prediction

Yuchen Zhou, Jiayu Tang, Xiaoyan Xiao, Yueyao Lin, Linkai Liu, Zipeng Guo, Hao Fei, Xiaobo Xia, Chao Gou

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 21 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the where (attention map prediction) task to joint training (ablation)LLada · W3DA Traffic Accident (text explanation)CIDEr-R: 0.307 -> 1.002Improved
add the where task to joint training (ablation)LLada · W3DA Traffic Accident (text explanation)BLEU-4: 0.289 -> 0.376Improved
add the what task to a map-only baseline (ablation)LLada · W3DAKLdiv: 1.500 -> 1.498Improved
add the why task on top of what (ablation)LLada · W3DAKLdiv: 1.498 -> 1.485Improved
add what and why tasks to attention-only baseline (ablation)LLada · W3DACC: 0.512 -> 0.527Improved
use end-to-end LLM-driven LLada instead of ERFNetattention map prediction · W3DA Normal DrivingKLdiv: 1.979 -> 1.219Improved
use LLada instead of GazeXplain for joint predictionexplainable driver attention · W3DA Normal DrivingKLdiv: 2.578 -> 1.219Improved
use end-to-end LLada instead of two-stage ERFNet + LLaVAtextual explanation · W3DA Safety-Critical (text explanation)CIDEr-R: 0.307 -> 1.233Improved
train LLada on cross-domain W3DA rather than DR(eye)VE-only modelsconventional attention prediction · DR(eye)VE testKLdiv: 1.35 -> 1.04Improved
train LLada on W3DA instead of BDDA-only FBLNetconventional attention prediction · BDDA testCC: 0.64 -> 0.60Hurt
train on W3DA with LLada vs DADA-only FBLNetconventional attention prediction · DADA testCC: 0.50 -> 0.48No clear effect
use grayscale mask attention maps instead of heatmap overlays as visual prompt (ablation)MLLM annotation pipeline · W3DA annotationannotation qualityImproved

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