AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attention

Sounak Mondal, Zhibo Yang, Seoyoung Ahn, Dimitris Samaras, Gregory Zelinsky, Minh Hoai

CVPR 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Visual relationship and scene graph detection · 48 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
Use RoBERTa target embeddings instead of fixed random embeddings (ablation)Gazeformer · COCO-Search18 ZeroGazeSS: 0.336 -> 0.359Improved
Use RoBERTa target embeddings instead of fixed random embeddings (ablation)Gazeformer · COCO-Search18 ZeroGazeFED: 2.873 -> 2.788Improved
Use RoBERTa target embeddings instead of fixed random embeddings (ablation)Gazeformer · COCO-Search18 ZeroGazeNSS: 4.524 -> 4.671Improved
Replace patch classification with coordinate regression (ablation)Gazeformer · COCO-Search18 GazeTrainSS: 0.477 -> 0.504Improved
Replace patch classification with coordinate regression (ablation)Gazeformer · COCO-Search18 GazeTrainFED: 2.158 -> 2.072Improved
Replace patch classification with coordinate regression (ablation)Gazeformer · COCO-Search18 GazeTrainNSS: 7.545 -> 8.375Improved
Do not model fixation duration (ablation)Gazeformer · COCO-Search18 ZeroGazeSS (w/o Dur): 0.358 -> 0.359No clear effect
Do not model fixation duration (ablation)Gazeformer · COCO-Search18 GazeTrainSS (w/o Dur): 0.504 -> 0.504No clear effect
Use parallel transformer decoding to generate the scanpathGazeformer · COCO-Search18 target-present test splitinference time (ms): 386 -> 68 ms; 5.7XImproved
Use RoBERTa semantic target features to predict unseen target categoriesGazeformer · COCO-Search18 ZeroGazeSS: 0.300 -> 0.358Improved

Later papers that compared with this method

1 later accepted paper reports Gazeformer as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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