Ehsan Adeli

TL;DR: In this paper, the authors proposed an end-to-end architecture for one-class classification, which consists of two deep networks, each of which trained by competing with each other while collaborating to understand the underlying concept in the target class, and then classify the testing samples.

TL;DR: This paper adopts a data‐driven learning approach to discover disease‐related anatomical landmarks in the brain MR images, along with their nearby image patches, and learns an end‐to‐end MR image classifier for capturing both the local structural information conveyed by image patches located by landmarks and the global structural information derived from all detected landmarks.

TL;DR: 3D convolutional neural networks are adopted and a new network architecture is proposed for using multi-channel data and learning supervised features to automatically extract features from multi-modal preoperative brain images of high-grade glioma patients to predict overall survival time.

TL;DR: This paper proposed a spatio-temporal graph model for video captioning that exploits object interactions in space and time to build interpretable links and is able to provide explicit visual grounding, and further proposed an object-aware knowledge distillation mechanism, in which local object information is used to regularize global scene features.

TL;DR: This work identifies the discriminative anatomical landmarks from MR images in a data-driven manner, and proposes a deep multi-task multi-channel convolutional neural network for joint classification and regression, using MRI data and demographic information of subjects.