Filters








1,250 Hits in 5.5 sec

Visualization-enabled multi-document summarization by Iterative Residual Rescaling

RIE ANDO, BRANIMIR BOGURAEV, ROY BYRD, MARY NEFF
2005 Natural Language Engineering  
For the former, we apply Iterative Residual Rescaling (IRR); for the latter, we argue for graphical display elements.  ...  This paper describes a novel approach to multi-document summarization, which explicitly addresses the problem of detecting, and retaining for the summary, multiple themes in document collections.  ...  The first author was partly supported by a McMullen fellowship from Cornell University.  ... 
doi:10.1017/s1351324904003389 fatcat:4hlblv34kngihmkfxj32pwwngq

iDVS: An Interactive Multi-document Visual Summarization System [chapter]

Yi Zhang, Dingding Wang, Tao Li
2011 Lecture Notes in Computer Science  
To address the above limitations, in this paper, we develop iDVS, a visualization-enabled multi-document summarization system with users' interaction, to improve the summarization performance using users  ...  Multi-document summarization is a fundamental tool for understanding documents.  ...  The work is partially supported by US National Science Foundation under grants IIS-0546280 and CCF-0830659.  ... 
doi:10.1007/978-3-642-23808-6_37 fatcat:fpdchtoutrhfxmk6bb3l3n7cwi

Thunor: visualization and analysis of high-throughput dose–response datasets

Alexander L R Lubbock, Leonard A Harris, Vito Quaranta, Darren R Tyson, Carlos F Lopez
2021 Nucleic Acids Research  
IC50, including across datasets or grouped by tags.  ...  High-throughput cell proliferation assays to quantify drug-response are becoming increasingly common and powerful with the emergence of improved automation and multi-time point analysis methods.  ...  Our GDSC analysis is summarized in Figure 3 .  ... 
doi:10.1093/nar/gkab424 pmid:34038546 pmcid:PMC8265171 fatcat:m7x2kncsundudjrqp4oevvsjzu

Semi-Supervised Classification with Graph Convolutional Networks [article]

Thomas N. Kipf, Max Welling
2017 arXiv   pre-print
In a number of experiments on citation networks and on a knowledge graph dataset we demonstrate that our approach outperforms related methods by a significant margin.  ...  This research was funded by SAP.  ...  Dataset statistics are summarized in Table 1 . In the citation network datasets-Citeseer, Cora and Pubmed (Sen et al., 2008 )-nodes are documents and edges are citation links.  ... 
arXiv:1609.02907v4 fatcat:pt7vcc7b5vecflnsu4xdigvceq

Dynamic Neural Networks: A Survey [article]

Yizeng Han, Gao Huang, Shiji Song, Le Yang, Honghui Wang, Yulin Wang
2021 arXiv   pre-print
In this survey, we comprehensively review this rapidly developing area by dividing dynamic networks into three main categories: 1) instance-wise dynamic models that process each instance with data-dependent  ...  Rather than skipping the execution of layers with independent parameters, iterative and adaptive mobile neural network (IamNN) [64] replaces multiple residual blocks in each ResNet stage by one block  ...  To summarize, a coarse update can be realized by with data-dependent network depth [11] or width [160] , [161] . 3) Selective updates in multi-scale RNNs.  ... 
arXiv:2102.04906v4 fatcat:zelspxwv6nel7kv2yu6ynakyuu

On the Importance of Attention in Meta-Learning for Few-Shot Text Classification [article]

Xiang Jiang, Mohammad Havaei, Gabriel Chartrand, Hassan Chouaib, Thomas Vincent, Andrew Jesson, Nicolas Chapados, Stan Matwin
2018 arXiv   pre-print
In comparisons with models trained from random initialization, pretrained models and meta trained MAML, our proposed ATAML method generalizes better on single-label and multi-label classification tasks  ...  Current deep learning based text classification methods are limited by their ability to achieve fast learning and generalization when the data is scarce.  ...  Figure 4 : Visualizing attentions learned by ATAML TCN(A). FREEZE TESTING Figure 2 : 2 Visualizing attentions learned by ATAML TCN(A).  ... 
arXiv:1806.00852v1 fatcat:g6jwlt5xxbfe7btti5ukkfqvbm

Multi-Compartment T2 Relaxometry Using a Spatially Constrained Multi-Gaussian Model

Ashish Raj, Sneha Pandya, Xiaobo Shen, Eve LoCastro, Thanh D. Nguyen, Susan A. Gauthier, Friedemann Paul
2014 PLoS ONE  
The brain's myelin content can be mapped by T2-relaxometry, which resolves multiple differentially relaxing T2 pools from multi-echo MRI.  ...  Consent was obtained both in oral and written form with detailed documentation.  ...  At each iteration we rescale the prior penalties such that the ratios c N ~lN h k k 2 y y{A exp (h) 2 , c S ~mS D S h k k 2 y y{A exp (h) 2 are held constant throughout the minimization, as follows.  ... 
doi:10.1371/journal.pone.0098391 pmid:24896833 pmcid:PMC4045663 fatcat:owrq7me37bda5k24skegowefna

Multivariable association discovery in population-scale meta-omics studies

Himel Mallick, Ali Rahnavard, Lauren J. McIver, Siyuan Ma, Yancong Zhang, Long H. Nguyen, Timothy L. Tickle, George Weingart, Boyu Ren, Emma H. Schwager, Suvo Chatterjee, Kelsey N. Thompson (+9 others)
2021 PLoS Computational Biology  
Microbiome multi-omics are typically noisy, sparse (zero-inflated), high-dimensional, extremely non-normal, and often in the form of count or compositional measurements.  ...  We also applied MaAsLin 2 to a microbial multi-omics dataset from the Integrative Human Microbiome (HMP2) project which, in addition to reproducing established results, revealed a unique, integrated landscape  ...  For instance, MaAsLin 2's multi-analysis framework has been used in the context of meta-analysis [54] , and the extracted residuals and random effects from a MaAsLin 2 fit can be used for further downstream  ... 
doi:10.1371/journal.pcbi.1009442 pmid:34784344 pmcid:PMC8714082 fatcat:znqkxasavzczrpbwxfas5on7d4

Iterative Inversion of Deformation Vector Fields with Feedback Control [article]

Abhishek Kumar Dubey, Alexandros-Stavros Iliopoulos, Xiaobai Sun, Fang-Fang Yin, Lei Ren
2018 arXiv   pre-print
By our numerical experiments, alternating control yields smaller IC residuals and inversion errors than constant control.  ...  Spatially variant control renders smaller residuals and errors by at least an order of magnitude, compared to other schemes, in no more than 10 steps.  ...  Acknowledgements This work was supported by the National Institutes of Health Grant No. R01-CA184173.  ... 
arXiv:1610.08589v4 fatcat:3d6rljwl3bhvnm6sknrszj3q3a

NiftyNet: a deep-learning platform for medical imaging

Eli Gibson, Wenqi Li, Carole Sudre, Lucas Fidon, Dzhoshkun I. Shakir, Guotai Wang, Zach Eaton-Rosen, Robert Gray, Tom Doel, Yipeng Hu, Tom Whyntie, Parashkev Nachev (+5 others)
2018 Computer Methods and Programs in Biomedicine  
NiftyNet is built on TensorFlow and supports TensorBoard visualization of 2D and 3D images and computational graphs by default.  ...  NiftyNet enables researchers to rapidly develop and distribute deep learning solutions for segmentation, regression, image generation and representation learning applications, or extend the platform to  ...  Results: illustrative applications Abdominal organ segmentation Segmentations of anatomy and pathology on medical images can support image-guided interventional workflows by enabling the visualization  ... 
doi:10.1016/j.cmpb.2018.01.025 pmid:29544777 pmcid:PMC5869052 fatcat:7wsoyoeljrdxljibrz3pwe4r5q

Novel genetic determinants of telomere length from a multi-ethnic analysis of 75,000 whole genome sequences in TOPMed [article]

Margaret A Taub, Joshua S Weinstock, Kruthika R Iyer, Lisa R Yanek, Matthew P Conomos, Alexander P Reiner, Rasika A Mathias, NHLBI Trans-Omics for Precision Medicine (TOPMed) Consortium
2019 bioRxiv   pre-print
We performed the largest multi-ethnic and only WGS-based genome-wide association analysis of TL to date. We identified 22 associated loci (p-value <5x10-8), including 10 novel loci.  ...  Details on the specific samples included for telomere length analysis are outlined below, summarized in Supplementary Tables S1A and S1B , and described by TOPMed 38 .  ...  Note: In bold are genes documented to play a role in telomere length or DNA damage repair.  ... 
doi:10.1101/749010 fatcat:mmts2tu5drafvgxzsi5dq5463a

Extending Semiautomatic Ventilation Defect Analysis for Hyperpolarized 129Xe Ventilation MRI

Mu He, S. Sivaram Kaushik, Scott H. Robertson, Matthew S. Freeman, Rohan S. Virgincar, H. Page McAdams, Bastiaan Driehuys
2014 Academic Radiology  
Results-Linear-binning enabled a faster and more reproducible workflow, and enabled analysis of an additional 0.25 ± 0.18 L of lung volume by accounting for vasculature.  ...  Rationale and Objectives-Clinical deployment of hyperpolarized (HP) 129 Xe MRI requires accurate quantification and visualization of the ventilation defect percentage (VDP).  ...  Prior to imaging, all subjects practiced achieving reproducible breath-holds by inhaling 1-liter of air from a bag starting from functional residual capacity (FRC).  ... 
doi:10.1016/j.acra.2014.07.017 pmid:25262951 pmcid:PMC4254215 fatcat:2vmer7blo5b3bdhcllckil3sii

Adaptive timeline interface to personal history data

Antti Ajanki, Markus Koskela, Jorma Laaksonen, Samuel Kaski
2013 Proceedings of the 15th ACM on International conference on multimodal interaction - ICMI '13  
The novelty is that the visualization is dynamically changed to emphasize relevant items, which makes them easier to recognize and select.  ...  The assumption of normality of the residuals was checked by graphical inspection of the normal probability plot.  ...  In our approach, we assume that the recorded personal history is made of multi-domain information items, typically consisting of textual and visual documents together with contextual metadata such as location  ... 
doi:10.1145/2522848.2522870 dblp:conf/icmi/AjankiKLK13 fatcat:e44w2sisfzarnpiz4mlv4cph74

Classification of Architectural Heritage Images Using Deep Learning Techniques

Jose Llamas, Pedro M. Lerones, Roberto Medina, Eduardo Zalama, Jaime Gómez-García-Bermejo
2017 Applied Sciences  
The availability of automatic techniques to facilitate these sorting tasks would improve an important part of the digital documentation process.  ...  The classification of the images taken during the measurement of an architectural asset is an essential task within the digital documentation of cultural heritage.  ...  Roberto Medina revised the paper and suggested important changes to improve the final document. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app7100992 fatcat:rbfrdyz6zbcjpmyt3rnihkfcjm

MFE: Multi-scale Feature Enhancement for Object Detection

Zhenhu Zhang, Xueying Qin, Fan Zhong
2021 British Machine Vision Conference  
For ATSS and FSAF with ResNet101 as backbone, using MFE can increase AP by 1.2 and 1.3 points. Our method also performs well on Pascal VOC dataset.  ...  For FCOS, RetinaNet and Mask R-CNN with ResNet50, using MFE can increase the Average Precision (AP) by 1.2, 1.1 and 1.0 points on MS COCO test-dev.  ...  This work is partially supported by NSF of China (No. 62172260), and also sponsored by SenseTime.  ... 
dblp:conf/bmvc/ZhangQZ21 fatcat:badwf73xnrh23dle4bmkraxpbu
« Previous Showing results 1 — 15 out of 1,250 results