Predicting Visual Importance Across Graphic Design Types

no code implementations • 7 Aug 2020 • Camilo Fosco, Vincent Casser, Amish Kumar Bedi, Peter O'Donovan, Aaron Hertzmann, Zoya Bylinskii

This paper introduces a Unified Model of Saliency and Importance (UMSI), which learns to predict visual importance in input graphic designs, and saliency in natural images, along with a new dataset and applications.

Hierarchical Deep Learning Architecture For 10K Objects Classification

no code implementations • 7 Sep 2015 • Atul Laxman Katole, Krishna Prasad Yellapragada, Amish Kumar Bedi, Sehaj Singh Kalra, Mynepalli Siva Chaitanya

We propose a two level hierarchical deep learning architecture inspired by divide & conquer principle that decomposes the large scale recognition architecture into root & leaf level model architectures.

Classification General Classification +1