AI Paper Atlas

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

Learning to Taste: A Multimodal Wine Dataset

Thoranna Bender, Simon Moe Sørensen, Alireza Kashani, Kristjan Eldjarn Hjorleifsson, Grethe Hyldig, Søren Hauberg, Serge Belongie, Frederik Rahbæk Warburg

NeurIPS 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Human-like visual cognition in VLMs · 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
add flavor modality to image+text embeddings (ablation)FEAST (CLIP+t-SNE+CCA) · WineSensed coarse flavor attribute prediction (avg accuracy, 5-fold CV)accuracy (SVM): 0.22 -> 0.28Improved
add text to image+flavor (ablation)FEAST · WineSensed coarse flavor attribute prediction (avg accuracy, 5-fold CV)accuracy (SVM): 0.23 -> 0.28Improved
add flavor to text (ablation)FEAST · WineSensed coarse flavor attribute prediction (avg accuracy, 5-fold CV)accuracy (SVM): 0.16 -> 0.23Improved
add flavor to text (ablation)FEAST · WineSensed coarse flavor attribute prediction (avg accuracy, 5-fold CV)accuracy (NN): 0.18 -> 0.18No clear effect
use NMDS instead of t-STE for human kernel (ablation)FEAST · WineSensed coarse flavor attribute prediction (avg accuracy, 5-fold CV)accuracy (SVM): 0.13 -> 0.16Improved
use t-SNE instead of UMAP for machine kernel reduction (ablation)FEAST · WineSensed coarse flavor attribute prediction (avg accuracy, 5-fold CV)accuracy (NN): 0.18 -> 0.25Improved
use t-SNE instead of PCA for machine kernel reduction (ablation)FEAST · WineSensed coarse flavor attribute prediction (avg accuracy, 5-fold CV)accuracy (SVM): 0.20 -> 0.22Improved
use CCA instead of SNaCK to combine kernels (ablation)FEAST · WineSensed coarse flavor attribute prediction (avg accuracy, 5-fold CV)accuracy (SVM): 0.23 -> 0.28Improved
use CCA instead of ICP to combine kernels (ablation)FEAST · WineSensed coarse flavor attribute prediction (avg accuracy, 5-fold CV)accuracy (NN): 0.24 -> 0.26Improved
use image encoders instead of text encoders (ablation)machine kernel · WineSensed coarse flavor attribute prediction (avg accuracy, 5-fold CV)accuracyHurt
add flavor (human kernel NMDS+CCA) to CLIP+t-SNE text (ablation)FEAST · WineSensed fine-grained (TAR)TAR: 0.82 -> 0.88Improved
add flavor to CLIP+t-SNE image (ablation)FEAST · WineSensed fine-grained (TAR)TAR: 0.82 -> 0.89Improved

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