IEEE transactions on visualization and computer graphics
Aug 20, 2019
Emotions play a key role in human communication and public presentations. Human emotions are usually expressed through multiple modalities. Therefore, exploring multimodal emotions and their coherence is of great value for understanding emotional exp...
IEEE transactions on visualization and computer graphics
Aug 20, 2019
A key challenge in developing and deploying Machine Learning (ML) systems is understanding their performance across a wide range of inputs. To address this challenge, we created the What-If Tool, an open-source application that allows practitioners t...
IEEE transactions on visualization and computer graphics
Aug 19, 2019
Automation of tasks can have critical consequences when humans lose agency over decision processes. Deep learning models are particularly susceptible since current black-box approaches lack explainable reasoning. We argue that both the visual interfa...
IEEE transactions on visualization and computer graphics
Aug 19, 2019
Complex computational models are often designed to simulate real-world physical phenomena in many scientific disciplines. However, these simulation models tend to be computationally very expensive and involve a large number of simulation input parame...
IEEE transactions on visualization and computer graphics
Mar 15, 2019
Neural embeddings are widely used in language modeling and feature generation with superior computational power. Particularly, neural document embedding - converting texts of variable-length to semantic vector representations - has shown to benefit w...
IEEE transactions on visualization and computer graphics
Mar 8, 2019
We define behavior as a set of actions performed by some actor during a period of time. We consider the problem of analyzing a large collection of behaviors by multiple actors, more specifically, identifying typical behaviors and spotting anomalous b...
IEEE transactions on visualization and computer graphics
Aug 20, 2018
Face sketch synthesis shows great applications in a lot of fields such as online entertainment and suspects identification. Existing face sketch synthesis methods learn the patch-wise sketch style from the training dataset containing photo-sketch pai...
IEEE transactions on visualization and computer graphics
Aug 15, 2018
We propose a reinforcement learning approach for real-time exposure control of a mobile camera that is personalizable. Our approach is based on Markov Decision Process (MDP). In the camera viewfinder or live preview mode, given the current frame, our...
IEEE transactions on visualization and computer graphics
May 22, 2018
In this paper, we present a novel approach for 3D dental model segmentation via deep Convolutional Neural Networks (CNNs). Traditional geometry-based methods tend to receive undesirable results due to the complex appearance of human teeth (e.g., miss...
IEEE transactions on visualization and computer graphics
Aug 29, 2017
Recurrent neural networks, and in particular long short-term memory (LSTM) networks, are a remarkably effective tool for sequence modeling that learn a dense black-box hidden representation of their sequential input. Researchers interested in better ...