We present CartoonX (Cartoon Explanation), a novel model-agnostic explanation method tailored towards image classifiers and based on the rate-distortion (RDE) framework. Natural images are roughly piece-wise smooth signals—also called cartoon-like images—and tend to be sparse in wavelet domain. is first exploit this by requiring its explanations domain, thus extracting relevant part of an inste...

In this paper we present our participation at TAC 2009 AESOP (Automatically Evaluating Summaries Of Peers) task. We make use of a statistical model for evaluation metric correlating to Overall Responsiveness and a nugget-based pyramid model for correlating to the Pyramid manual metric of TAC 2009. We also present the performance of our three submitted runs as per the official TAC 2009 evaluatio...

BACKGROUND Integrated control programs, emphasizing preventive chemotherapy along with health education, can reduce the incidence of soil-transmitted helminthiasis and schistosomiasis. The aim of this study was to develop an educational animated cartoon to improve school children's awareness regarding soil-transmitted helminthiasis, diarrheal diseases, and related hygiene practices in Côte d'Iv...

Natural scenes contain a wide range of textured motion patterns which are characterized by the movement of a large amount of particle and wave elements, such as falling snow, water waves, dancing grass, etc. In this paper, we present a generative method for modeling these motion phenomena and our method consists of four components: (1). A photometric model which represents an image as a linear ...

In this paper we present an approach for synthesising and editing cartoon fire series based on hand-drawn samples. Our approach first extracts outlines of hand-drawn cartoon fire series and, based on the central reference skeleton, synthesises fire of arbitrary length by high level control on flame skeletons. With our approach users may edit cartoon fire series to achieve effects such as fire s...

We formulate a model for probability distributions on image spaces. We show that any distribution of images can be factored exactly into conditional distributions of feature vectors at one resolution (pyramid level) conditioned on the image information at lower resolutions. We would like to factor this over positions in the pyramid levels to make it tractable, but such factoring may miss long-r...

We formulate a model for probability distributions on image spaces. We show that any distribution of images can be factored exactly into conditional distributions of feature vectors at one resolution (pyramid level) conditioned on the image information at lower resolutions. We would like to factor this over positions in the pyramid levels to make it tractable, but such factoring may miss long-r...

In this paper, we present a generative model for textured motion phenomena, such as falling snow, wavy river and dancing grass, etc. Firstly, we represent an image as a linear superposition of image bases selected from a generic and over-complete dictionary. The dictionary contains Gabor bases for point/particle elements and Fourier bases for wave-elements. These bases compete to explain the in...

Scene recognition is a basic task towards image understanding. Spatial Pyramid Matching (SPM) has been shown to be an efficient solution for spatial context modeling. In this paper, we introduce an alternative approach, Orientational Pyramid Matching (OPM), for orientational context modeling. Our approach is motivated by the observation that the 3D orientations of objects are a crucial factor t...

We formulate a model for probability distributions on image spaces. We show that any distribution of images can be factored exactly into conditional distributions of feature vectors at one resolution (pyramid level) conditioned on the image information at lower resolutions. We would like to factor this over positions in the pyramid levels to make it tractable, but such factoring may miss long-r...