AI Paper Atlas

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

Understanding Image Impressiveness Inspired by Instantaneous Human Perceptual Cues

Jufeng Yang, Yan Sun, Jie Liang, Yong-Liang Yang, Ming-Ming Cheng

AAAI 2018 · Vision-language and multimodal › Human and embodied modeling · approach: Human perception modeling · 10 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
fuse all low-level features instead of single cues (T&C&G&S vs texture) (ablation)impressiveness classifier · Flickr Impaccuracy: 0.539 -> 0.734Improved
use deep features (EmoNet+CaffeNet) instead of low-level fusion (ablation)impressiveness classifier · Flickr Impaccuracy: 0.734 -> 0.845Improved
use deep features instead of low-level fusion (ablation)impressiveness classifier · Trip Impaccuracy: 0.728 -> 0.808Improved
add low-level and mid-level cues to deep features (all fusion) (ablation)impressiveness classifier · Flickr Impaccuracy: 0.845 -> 0.852Improved
add low-level and mid-level cues to deep features (all fusion) (ablation)impressiveness classifier · Trip Impaccuracy: 0.808 -> 0.820Improved
use unusualness cue (C&G&S) instead of aesthetics (T&C&G) (ablation)impressiveness classifier · Flickr Impaccuracy: 0.660 -> 0.715Improved
add mid-level emotion and object features to low-level in recommendation (impressiveness vs low-level)image recommendation · News Imp SportMAP: 0.603 -> 0.763Improved
impressiveness vs low-level features in recommendationimage recommendation · News Imp TechnologyMRR: 0.768 -> 0.759Hurt
impressiveness representation vs SIFT&BoWimage recommendation · News Imp PoliticsMAP: 0.664 -> 0.807Improved

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