AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Deep Cropping via Attention Box Prediction and Aesthetics Assessment

Wenguan Wang, Jianbing Shen

ICCV 2017 · Image generation › Autoregressive and latent generation · approach: Classical generative image synthesis · 126 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
use the attention-box regression network instead of the best saliency model (SalNet)attention box prediction · PASCAL attention box (850 images)IoU: 0.379 -> 0.517Improved
use the attention-box regression network instead of a classic saliency model (ITTI)attention box prediction · PASCAL attention box (850 images)IoU: 0.318 -> 0.517Improved
use the proposed cascaded crop pipeline instead of the aesthetics method LCCphoto cropping · MSR-ICD (photographer 1)IoU: 0.748 -> 0.813Improved
use the proposed cascaded crop pipeline instead of the aesthetics method LCCphoto cropping · MSR-ICD (photographer 1)BDE: 0.066 -> 0.030Improved
use the proposed pipeline instead of sliding-window ARC aesthetics rankingphoto cropping · MSR-ICD (photographer 1)IoU: 0.448 -> 0.813Improved
use the proposed pipeline instead of the attention-based ATCphoto cropping · MSR-ICD (photographer 1)IoU: 0.605 -> 0.813Improved
use the proposed pipeline instead of VBCphoto cropping · FLMSIoU: 0.74 -> 0.81Improved
use the proposed pipeline instead of ATCphoto cropping · FLMSBDE: 0.063 -> 0.057Improved
use the proposed AA network instead of the handcrafted-feature AVA baselineaesthetics assessment · AVA test (19,930 images)accuracy: 0.667 -> 0.769Improved
use the proposed AA network instead of CPDaesthetics assessment · AVA test (19,930 images)accuracy: 0.774 -> 0.769No clear effect
use the proposed AA network instead of ARCaesthetics assessment · AVA test (19,930 images)accuracy: 0.773 -> 0.769No clear effect

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