27 papers · ranked by Valyu relevance
Sizhang Dai, Weibing Huang
We propose a learning-based network for depth map estimation from multi-view stereo (MVS) images. Our proposed network consists of three sub-networks: 1) a base network for initial depth map estimation from an unstructured stereo image pair, 2) a novel refinement network that leverages both photometric and geometric…
Xiheng Zhang, Yongkang Wong, Mohan S. Kankanhalli, Weidong Geng + 1 more
'Jie Zhang'] Sensor-based human activity recognition aims at detecting various physical activities performed by people with ubiquitous sensors. Different from existing deep learning-based method which mainly extracting black-box features from the raw sensor data, we propose a hierarchical multi-view aggregation network…
Long Shi, Chuanqing Tang, Hepu Deng, Cai Xu + 2 more
Hierarchical Opinion Aggregation Authors: ['Long Shi' 'Chuanqing Tang' 'Hepu Deng' 'Cai Xu' 'Lei Xing' 'Badong Chen'] Abstract—Recently, multi-view learning has witnessed a considerable interest on the research of trusted decision-making. Previous methods are mainly inspired from an important paper published by Han et…
Zunguan Fan, Yifan Feng, Kang Wang, Xiaoli Li + 1 more
Efficient flotation beneficiation heavily relies on accurate flotation condition recognition based on monitored froth video. However, the recognition accuracy is hindered by limitations of extracting temporal features from froth videos and establishing correlations between complex multi-modal high-order data. To…
Jun-Yu Chen, Long Shi, Badong Chen
Enhancement and Aggregation Authors: ['Jun-Yu Chen' 'Long Shi' 'Badong Chen'] Graph Neural Networks (GNNs) have exhibited remarkable efficacy in learning from multi-view graph data. In the framework of multi-view graph neural networks, a critical challenge lies in effectively combining diverse views, where each view…
Gori Sankar Borah, Sukriti Tiwari, Selvaraman Nagamani
Accurate prediction of biomedical relationships, such as chemical–gene interactions, is fundamental to understanding disease mechanisms and advancing drug discovery. With the rapid growth of heterogeneous biological data, modeling large-scale, multi-entity networks has become increasingly challenging. Traditional…
Jaswanth K. Yella, Anil G. Jegga
In-silico drug repositioning or predicting new indications for approved or late-stage clinical trial drugs is a resourceful and time-efficient strategy in drug discovery. However, inferring novel candidate drugs for a disease is challenging, given the heterogeneity and sparseness of the underlying biological entities…
Faisal M. Almutairi, Charilaos I. Kanatsoulis, Nicholas D. Sidiropoulos
'Nicholas D. Sidiropoulos'] Abstract—Multidimensional data have become ubiquitous and are frequently encountered in situations where the information is aggregated over multiple data atoms. The aggregation can be over time or other features, such as geographical location. We often have access to multiple aggregated…
Majid Hameed Ahmed, Sabrina Tiun, Nazlia Omar, Nor Samsiah Sani + 1 more
'Yunhe Wang'] Clustering texts together is an essential task in data mining and information retrieval, whose aim is to group unlabeled texts into meaningful clusters that facilitate extracting and understanding useful information from large volumes of textual data. However, clustering short texts (STC) is complex…
Juan Zamora, Jérémie Sublime, Alberto J. Rosales Silva, Francisco J. Gallegos-Funes
'Francisco J. Gallegos-Funes'] The ability to build more robust clustering from many clustering models with different solutions is relevant in scenarios with privacy-preserving constraints, where data features have a different nature or where these features are not available in a single computation unit. Additionally…
Youcheng Qian, Xueyan Yin, Jun Kong, Jianzhong Wang + 2 more
'Denis Horvath'] Graph-based dimensionality reduction methods have attracted substantial attention due to their successful applications in many tasks, including classification and clustering. However, most classical graph-based dimensionality reduction approaches are only applied to data from one view. Hence, combining…
Senhong Wang, Jiangzhong Cao, Fangyuan Lei, Qingyun Dai + 2 more
'Shangsong Liang' 'Bingo Wing-Kuen Ling'] A number of literature reports have shown that multi-view clustering can acquire a better performance on complete multi-view data. However, real-world data usually suffers from missing some samples in each view and has a small number of labeled samples. Additionally, almost all…
Yasser EL-Manzalawy, Tsung-Yu Hsieh, Manu Shivakumar, Dokyoon Kim + 1 more
Large-scale collaborative precision medicine initiatives (e.g., The Cancer Genome Atlas (TCGA)) are yielding rich multi-omics data. Integrative analyses of the resulting multi-omics data, such as somatic mutation, copy number alteration (CNA), DNA methylation, miRNA, gene expression, and protein expression, offer the…
Yixiang Huang, Yuan Gan, Xinqi Gong
Multi-omics profiling—spanning proteomics, transcriptomics, and additional omics data types—is rapidly advancing, providing increasingly detailed maps of cellular identity and function. In parallel, computational methods have evolved to integrate diverse omics with increasing precision in resolving cellular…
Yasser El-Manzalawy
Recent technological advances in high-throughput omics technologies and their applications in genomic medicine have opened up outstanding opportunities for individualized medicine. However, several challenges arise in the integrative analysis of such data including heterogeneity and high dimensionality of the omics…
Katarína Furmanová, Samuel Gratzl, Holger Stitz, Thomas Zichner + 3 more
'Miroslava Jarešová' 'Alexander Lex' 'Marc Streit'] Most tabular data visualization techniques focus on overviews, yet many practical analysis tasks are concerned with investigating individual items of interest. At the same time, relating an item to the rest of a potentially large table is important. In this work we…
Raphael Kirchgaessner, Kaya Keutler, Layaa Sivakumar, Xubo Song + 1 more
AI based embeddings offer the possibilities of encoding complex biological data into low dimensional spaces, called embedding spaces, that maintain the relationships between entities. There is an open question about the compatibility of embedding spaces that are created without any coordination. It has been assumed…
Christina Humer, Rachel Nicholls, Henry Heberle, Moritz Heckmann + 7 more
Chemical reaction optimization (RO) is an iterative process that results in large and high-dimensional datasets. Current tools only allow for limited analysis and understanding of parameter spaces, making it hard for scientists to review or follow changes throughout the process. With the recent emergence of using…
Ping Zhang, Wenjun Li, Hua Sun, Francesco Pappalardo
Secure aggregation is an essential component of modern distributed applications and data mining platforms. Aggregated statistical results are typically adopted in constructing a data cube for data analysis at multiple abstraction levels in data warehouse platforms. Generating different types of statistical results…
Abdur Rehman Khan, Umer Rashid, Khalid Saleem, Adeel Ahmed + 1 more
'Susan Gauch'] The recent proliferation of multimedia information on the web enhances user information need from simple textual lookup to multi-modal exploration activities. The current search engines act as major gateways to access the immense amount of multimedia data. However, access to the multimedia content is…
Md Naimul Hoque, Niklas Elmqvist
Multidimensional datasets consist of many attributes per observation, and are routinely found in both tabular as well network applications. For example, the U.S. Census dataset of citizen demographics includes hundreds of attributes capturing individuals living in the United States, including properties such as age…
Authors not listed
Machine olfaction—the artificial replication of the sense of smell—faces significant challenges due to the absence of large, standardized training datasets. Unlike vision, language, and audio models, which benefit from extensive corpora such as ImageNet, GLUE, and AudioSet, olfaction lacks scaled equivalents and…
Belinda Boehm, Christopher McNeill, David Huang
Understanding the solution-phase behaviour of organic semiconducting polymers is important for systematically improving the performance of devices based on solution-processed thin films of these molecules. Conventional polymer theory predicts that polymer conformations become more compact as solvent quality decreases…
Jaclyn Smith, Yao Shi, Michael Benedikt, Milos Nikolic
Targeted diagnosis and treatment options are dependent on insights drawn from multi-modal analysis of large-scale biomedical datasets. Advances in genomics sequencing, image processing, and medical data management have supported data collection and management within medical institutions. These efforts have produced…
Yuanqing Lu, Timur Fazletdinov, Zhiwen Pan, Katrin Wondraczek + 1 more
The synthesis of nanoscale particles and particle aggregates from liquid or gaseous precursors is affected by a variety of trade-off relations, for example, in terms of product composition, yield, or energy efficiency. Machine-supported process evaluation and learning (ML) of these relations enables optimization…
Authors not listed
Identifying synthesis routes from knowledge graphs poses challenges beyond retrosynthesis, including path–finding artifacts and data issues. We introduce “SynGPS”, a novel algorithm that overcomes these limitations by identifying viable routes even with common artifacts. SynGPS can resolve nonsensical cycles…
Kevin Mildau, Christoph Büschl, Jürgen Zanghellini, Justin J.J. van der Hooft
Computational metabolomics workflows have revolutionized the untargeted metabolomics field. However, the organization and prioritization of metabolite features remains a laborious process. Organizing metabolomics data is often done through mass fragmentation-based spectral similarity grouping, resulting in feature sets…