AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

GazeXplain: Learning to Predict Natural Language Explanations of Visual Scanpaths

Xianyu Chen, Ming Jiang, Qi Zhao

ECCV 2024 · Vision-language and multimodal › Human and embodied modeling · approach: Human perception modeling · 11 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 semantic alignment loss (ablation)GazeXplain · AiR-DCIDEr-R: 97.3 -> 123.1Improved
add semantic alignment loss (ablation)GazeXplain · AiR-DScanMatch (SM): 0.378 -> 0.386Improved
add the language decoder for explanations (with co-training) (ablation)GazeXplain · AiR-DScanMatch (SM): 0.356 -> 0.378Improved
add the language decoder for explanations (no co-training, no alignment) (ablation)GazeXplain · AiR-DScanMatch (SM): 0.337 -> 0.339No clear effect
add the language decoder for explanations (ablation)GazeXplain · AiR-DCIDEr-R: 66.7 -> 97.3Improved
add cross-dataset co-training (ablation)GazeXplain · AiR-DScanMatch (SM): 0.346 -> 0.386Improved
add semantic alignment loss (ablation)GazeXplain · AiR-DBLEU-4: 27.7 -> 30.7Improved
add semantic alignment loss (ablation)GazeXplain · COCO-Search18 target-absentvocabulary size: 566 -> 685Improved
add semantic alignment loss (ablation)GazeXplain · COCO-Search18 explanation faithfulnessROC AUC: 0.878 -> 0.902Improved
add cross-dataset co-training (ablation)GazeXplain · COCO-Search18 explanation faithfulnessROC AUC: 0.871 -> 0.902Improved
use GazeXplain versus ChenLSTM on target-present searchGazeXplain · COCO-Search18 target-presentSED: ChenLSTM 1.932 vs GazeXplain 1.981 (SED); SM 0.448 vs 0.480Mixed

Later papers that compared with this method

1 later accepted paper reports GazeXplain 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