AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Attention-Based Autism Spectrum Disorder Screening With Privileged Modality

Shi Chen, Qi Zhao

ICCV 2019 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 73 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 multi-modal distillation through a shared space (ablation)image-viewing model · image-viewing (own dataset)accuracy: 97% -> 99%Improved
add multi-modal distillation through a shared space (ablation)photo-taking model · photo-takingaccuracy: 76% -> 84%Improved
add multi-modal distillation (ablation)image-viewing model · Saliency4ASDaccuracy: 0.89 -> 0.93Improved
add the distillation-from-shared-space phase after shared space learning (ablation)photo-taking model · photo-takingaccuracy: 0.78 -> 0.84Improved
add shared space learning only (no distillation phase) (ablation)photo-taking model · photo-takingaccuracy: 0.76 -> 0.78Improved
add shared space learning only (ablation)image-viewing model · image-viewing (own dataset)accuracy: 0.97 -> 0.97No clear effect
add extra layers and training epochs on a single modality (ablation)image-viewing model · image-viewing (own dataset)accuracy: 0.97 -> 0.97No clear effect
add extra layers and training epochs on a single modality (ablation)photo-taking model · photo-takingaccuracy: 0.76 -> 0.73Hurt
learn a shared space across modalities (ablation)cross-modal matching · photo-taking to image-viewingRecall@5 (%): 62.2% -> 95.6%Improved
add recurrent temporal scanning of fixationsimage-viewing model · image-viewing (own dataset)accuracy: 0.92 -> 0.97Improved

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