Browsing by Author "Lin, Xiao"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
- Analyzing and Visualizing Disaster Phases from Social Media StreamsLin, Xiao; Chen, Liangzhe; Wood, Andrew (2012-12-11)Working under the direction of CTRNet, we developed a procedure for classifying Twitter data related to natural/man-made disasters into one of the Four Phases of Emergency Management (response, recovery, mitigation, and preparedness) as well as a multi-view system for visualizing the resulting data.
- GreenVis: Energy-Saving Color Schemes for Sequential Data Visualization on OLED DisplaysWang, Ji; Lin, Xiao; North, Christopher L. (Department of Computer Science, Virginia Polytechnic Institute & State University, 2012-03-01)The organic light emitting diode (OLED) display has recently become popular in the consumer electronics market. Compared with current LCD display technology, OLED is an emerging display technology that emits light by the pixels themselves and doesn’t need an external back light as the illumination source. In this paper, we offer an approach to reduce power consumption on OLED displays for sequential data visualization. First, we create a multi-objective optimization approach to find the most energy-saving color scheme for given visual perception difference levels. Second, we apply the model in two situations: pre-designed color schemes and auto generated color schemes. Third, our experiment results show that the energy-saving sequential color scheme can reduce power consumption by 17.2% for pre-designed color schemes. For auto-generated color schemes, it can save 21.9% of energy in comparison to the reference color scheme for sequential data.
- Leveraging Multimodal Perspectives to Learn Common Sense for Vision and Language TasksLin, Xiao (Virginia Tech, 2017-10-05)Learning and reasoning with common sense is a challenging problem in Artificial Intelligence (AI). Humans have the remarkable ability to interpret images and text from different perspectives in multiple modalities, and to use large amounts of commonsense knowledge while performing visual or textual tasks. Inspired by that ability, we approach commonsense learning as leveraging perspectives from multiple modalities for images and text in the context of vision and language tasks. Given a target task (e.g., textual reasoning, matching images with captions), our system first represents input images and text in multiple modalities (e.g., vision, text, abstract scenes and facts). Those modalities provide different perspectives to interpret the input images and text. And then based on those perspectives, the system performs reasoning to make a joint prediction for the target task. Surprisingly, we show that interpreting textual assertions and scene descriptions in the modality of abstract scenes improves performance on various textual reasoning tasks, and interpreting images in the modality of Visual Question Answering improves performance on caption retrieval, which is a visual reasoning task. With grounding, imagination and question-answering approaches to interpret images and text in different modalities, we show that learning commonsense knowledge from multiple modalities effectively improves the performance of downstream vision and language tasks, improves interpretability of the model and is able to make more efficient use of training data. Complementary to the model aspect, we also study the data aspect of commonsense learning in vision and language. We study active learning for Visual Question Answering (VQA) where a model iteratively grows its knowledge through querying informative questions about images for answers. Drawing analogies from human learning, we explore cramming (entropy), curiosity-driven (expected model change), and goal-driven (expected error reduction) active learning approaches, and propose a new goal-driven scoring function for deep VQA models under the Bayesian Neural Network framework. Once trained with a large initial training set, a deep VQA model is able to efficiently query informative question-image pairs for answers to improve itself through active learning, saving human effort on commonsense annotations.
- Text Clustering Using LucidWorks and Apache MahoutChen, Liangzhe; Lin, Xiao; Wood, Andrew (2012-11-17)This module introduces algorithms and evaluation metrics for flat clustering. We focus on the usage of LucidWorks big data analysis software and Apache Mahout, an open source machine learning library in clustering of document collections with the k-means algorithm.