AI Paper Atlas

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

Defining Image Memorability Using the Visual Memory Schema

Erdem Akagündüz, Adrian G. Borş, Karla K. Evans

TPAMI 2019 · Vision-language and multimodal › Human and embodied modeling · approach: Human perception modeling · 40 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
pool features with VMS maps instead of whole image (ablation)combined GIST+SIFT+HoG SVR · VISCHEMA memorability predictionSpearman rank correlation: 0.24 -> 0.41Improved
pool features with VMS maps instead of whole image (ablation)HoG SVR · VISCHEMA memorability predictionSpearman rank correlation: 0.24 -> 0.34Improved
pool features with eye-fixation maps (ablation)combined features SVR · VISCHEMA memorability predictionSpearman rank correlation: 0.24 -> 0.29Improved
pool features with GBVS saliency maps (ablation)combined features SVR · VISCHEMA memorability predictionSpearman rank correlation: 0.24 -> 0.25No clear effect
pool GIST features with eye-fixation maps (ablation)GIST SVR · VISCHEMA memorability predictionSpearman rank correlation: 0.19 -> 0.13Hurt
pool GIST features with VMS maps (ablation)GIST SVR · VISCHEMA memorability predictionSpearman rank correlation: 0.19 -> 0.10Hurt
pool pixel histograms with VMS maps (ablation)Pixels SVR · VISCHEMA memorability predictionSpearman rank correlation: 0.044 -> 0.085Improved
use VMS pooling on combined features, bottom-20 imagescombined features SVR · VISCHEMA memorability predictionBottom-20 average empirical memorability (%): 32.15 -> 24.87Improved
use VMS pooling on combined features, top-20 imagescombined features SVR · VISCHEMA memorability predictionTop-20 average empirical memorability (%): 56.10 -> 61.25Improved
use l1-norm instead of l2-norm loss (ablation)VMS reconstruction CNN · VMS reconstruction (all VISCHEMA)Pearson correlation of reconstructed vs human VMSImproved
train longer than 20 epochs (ablation)VMS reconstruction CNN · VMS reconstruction (all VISCHEMA)Pearson correlation of reconstructed vs human VMS: 0.588 at epoch 20Hurt
transfer from deeper layers (conv-5^2) of VGG-VD-19L instead of shallow layers (ablation)VMS reconstruction CNN · VMS reconstruction (all VISCHEMA)Pearson correlation of reconstructed vs human VMS: 0.588Improved

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