AI Paper Atlas

Research map / Detection and segmentation / CNN features

OAT: Object-Level Attention Transformer for Gaze Scanpath Prediction

Yini Fang, Jingling Yu, Haozheng Zhang, Ralf van der Lans, Bertram E Shi

ECCV 2024 · Detection and segmentation › CNN features · approach: RGB salient object detection · 4 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
replace end-to-end learnable PE with distance-based PE (ablation)OAT · Amazon book coverOverall behaviour difference: 0.088 -> 0.074Improved
add relative positional encoding on top of DPE (ablation)OAT · Amazon book coverOverall behaviour difference: 0.074 -> 0.088Hurt
add distance-based PE (ablation)OAT · Yogurt/wine (collected)Overall behaviour difference: 0.119 -> 0.031Improved
add object attention module (ablation)OAT · Yogurt/wine (collected)Overall behaviour difference: 0.169 -> 0.031Improved
add both DPE and OA (ablation)OAT · Yogurt/wine (collected)Sequence Score: 0.224 -> 0.346Improved
tokenize at object level instead of sub-object grid (12x28 patches) (ablation)OAT · Amazon book coverOverall behaviour difference: 1.14 -> 0.07Improved
coarser grid of 3x7 (patches of four objects) vs object-level 6x14 (ablation)OAT · Amazon book cover (mapped to 3x7)Overall behaviour difference: 0.05 -> 0.01No clear effect
model scanpaths at object level with autoregressive decoding vs GazeformerOAT · Amazon book coverSequence Score: 0.098 -> 0.950Improved
OAT vs Gazeformer on FED in collected datasetOAT · Yogurt/wine (collected)FED: 7.69 -> 7.19Improved
OAT on MultiMatch direction score in collected dataset vs IRLOAT · Yogurt/wine (collected)MultiMatch direction: 0.603 vs 0.645 (IRL)Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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