National University of Singapore

About: National University of Singapore is a education organization based out in Singapore, Singapore. It is known for research contribution in the topics: Population & Membrane. The organization has 74269 authors who have published 165426 publications receiving 5474934 citations. The organization is also known as: NUS & Universiti Kebangsaan Singapura.

Neural Sparse Voxel Fields

Abstract: Photo-realistic free-viewpoint rendering of real-world scenes using classical computer graphics techniques is challenging, because it requires the difficult step of capturing detailed appearance and geometry models. Recent studies have demonstrated promising results by learning scene representations that implicitly encode both geometry and appearance without 3D supervision. However, existing approaches in practice often show blurry renderings caused by the limited network capacity or the difficulty in finding accurate intersections of camera rays with the scene geometry. Synthesizing high-resolution imagery from these representations often requires time-consuming optical ray marching. In this work, we introduce Neural Sparse Voxel Fields (NSVF), a new neural scene representation for fast and high-quality free-viewpoint rendering. NSVF defines a set of voxel-bounded implicit fields organized in a sparse voxel octree to model local properties in each cell. We progressively learn the underlying voxel structures with a differentiable ray-marching operation from only a set of posed RGB images. With the sparse voxel octree structure, rendering novel views can be accelerated by skipping the voxels containing no relevant scene content. Our method is typically over 10 times faster than the state-of-the-art (namely, NeRF(Mildenhall et al., 2020)) at inference time while achieving higher quality results. Furthermore, by utilizing an explicit sparse voxel representation, our method can easily be applied to scene editing and scene composition. We also demonstrate several challenging tasks, including multi-scene learning, free-viewpoint rendering of a moving human, and large-scale scene rendering. Code and data are available at our website: this https URL.

Beyond Text QA: Multimedia Answer Generation by Harvesting Web Information

Abstract: Community question answering (cQA) services have gained popularity over the past years. It not only allows community members to post and answer questions but also enables general users to seek information from a comprehensive set of well-answered questions. However, existing cQA forums usually provide only textual answers, which are not informative enough for many questions. In this paper, we propose a scheme that is able to enrich textual answers in cQA with appropriate media data. Our scheme consists of three components: answer medium selection, query generation for multimedia search, and multimedia data selection and presentation. This approach automatically determines which type of media information should be added for a textual answer. It then automatically collects data from the web to enrich the answer. By processing a large set of QA pairs and adding them to a pool, our approach can enable a novel multimedia question answering (MMQA) approach as users can find multimedia answers by matching their questions with those in the pool. Different from a lot of MMQA research efforts that attempt to directly answer questions with image and video data, our approach is built based on community-contributed textual answers and thus it is able to deal with more complex questions. We have conducted extensive experiments on a multi-source QA dataset. The results demonstrate the effectiveness of our approach.

Consumer Value Co-creation in a Hybrid Commerce Service-Delivery System

Abstract: Retailing firms operating in a hypercompetitive environment are increasingly leveraging a hybrid commerce strategy to reach their customers through both physical and virtual channels. This study seeks to better understand the aspects of physical and virtual retail channels that can be integrated to create value for consumers. The role of consumers in co-creating value is examined in a hybrid commerce service-delivery system. The study draws on the theoretical foundations of value co-production as well as the customer contact model to develop a set of hybrid process metrics. A structural model is then advanced to examine the relationships between these processes and consumer value. Survey data from 300 consumers assessing hybrid commerce stores were used to empirically test this value co-creation model. Results demonstrate that the integration of promotion information, product and pricing information, and transaction information enhances information quality, while the integration of information access, order fulfillment, and customer service increases service convenience. Overall, the metrics developed and the structural model results offer a better understanding of the design of an effective value-creating hybrid commerce service-delivery system.

Sphingolipids and insulin resistance: the five Ws.

Abstract: Purpose of reviewInhibition of sphingolipid synthesis increases insulin sensitivity, resolves hepatic steatosis, and prevents the onset of diabetes in obese rodents. I herein review these interventional studies, aiming to summarize the five Ws – the ‘Who, What, Where, When, and Why’ questions that n