AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Gaze-Language Alignment for Zero-Shot Prediction of Visual Search Targets from Human Gaze Scanpaths

Sounak Mondal, Naveen Sendhilnathan, Ting Zhang, Yue Liu, Michael Proulx, Michael Louis Iuzzolino, Chuan Qin, Tanya R. Jonker

ICCV 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification · 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 CWCL with GLAD training (LLM prompts) (ablation)GLAM · COCO-Search18 zero-shottarget accuracy: 23.82 -> 30.17Improved
replace CWCL with GLAD training (category label prompts) (ablation)GLAM · COCO-Search18 zero-shottarget accuracy: 22.34 -> 30.17Improved
replace CWCL with GLAD (LLM prompts) (ablation)GLAM · COCO-Search18 fully supervisedtarget accuracy: 52.95 -> 58.22Improved
use LLM-generated prompts instead of category labels under CWCL (ablation)GLAM + CWCL · COCO-Search18 fully supervisedtarget accuracy: 57.95 -> 52.95Hurt
use LLM-generated prompts instead of category labels under CWCL (ablation)GLAM + CWCL · COCO-Search18 zero-shottarget accuracy: 22.34 -> 23.82No clear effect
add GLAD with LLM prompts versus classification-based GLAM (zero-shot method vs supervised classifier)GLAM · COCO-Search18 fully supervisedtarget accuracy: 46.45 -> 58.19Improved
add contextual cues to appearance-only LLM prompts (ablation)GLAM + GLAD · COCO-Search18 fully supervised, all trialstarget accuracy: 49.91 -> 58.22Improved
add appearance cues to context-only LLM prompts (ablation)GLAM + GLAD · COCO-Search18 fully supervised, target-presenttarget accuracy: 70.75 -> 77.76Improved
add appearance cues to context-only LLM prompts (ablation)GLAM + GLAD · COCO-Search18 fully supervised, target-absenttarget accuracy: 37.39 -> 38.69No clear effect
add peripheral information (w=1 vs w=0) (ablation)GLAM + GLAD · COCO-Search18 zero-shottarget accuracy: 23.25 -> 30.17Improved
add peripheral information (w=1 vs w=0) (ablation)GLAM + GLAD · COCO-Search18 fully supervisedtarget accuracy: 59.43 -> 58.22Hurt
use full-image peripheral access instead of window w=1 (ablation)GLAM + GLAD · COCO-Search18 zero-shottarget accuracy: 30.17 -> 25.79Hurt

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