Filters








738 Hits in 6.2 sec

Accounting for Random Regressors: A Unified Approach to Multi-modality Imaging [chapter]

Xue Yang, Carolyn B. Lauzon, Ciprian Crainiceanu, Brian Caffo, Susan M. Resnick, Bennett A. Landman
2011 Lecture Notes in Computer Science  
Herein, we describe a unified regression and inference approach using the design matrix paradigm which accounts for both random and non-random imaging regressors.  ...  Current statistical methods assume that the regressors are non-random.  ...  This work described herein has not been submitted elsewhere for publication.  ... 
doi:10.1007/978-3-642-24446-9_1 pmid:25346952 pmcid:PMC4208720 fatcat:ben2qe7dvbhajgtp6teso4qhgu

Biological parametric mapping accounting for random regressors with regression calibration and model II regression

Xue Yang, Carolyn B. Lauzon, Ciprian Crainiceanu, Brian Caffo, Susan M. Resnick, Bennett A. Landman
2012 NeuroImage  
These methods use the design matrix paradigm and account for both random and non-random imaging regressors.  ...  Herein, we discuss two unified regression and inference approaches, model II regression and regression calibration, for use in massively univariate inference with imaging data.  ...  Regression analysis accounting for errors in regressors would greatly improve the credibility of the BPM model by reasonably considering the randomness of the imaging modality in both the regressors and  ... 
doi:10.1016/j.neuroimage.2012.05.020 pmid:22609453 pmcid:PMC3408815 fatcat:hztpvvhvcvdlxlv4hjvvviibem

Canonical feature selection for joint regression and multi-class identification in Alzheimer's disease diagnosis

Xiaofeng Zhu, Heung-Il Suk, Seong-Whan Lee, Dinggang Shen
2015 Brain Imaging and Behavior  
We then perform the sparse multi-task learning for discriminative feature selection by using the canonical features as regressors and penalizing a loss function with a canonical regularizer.  ...  In this paper, we propose a novel method to transform the original features from different modalities to a common space, where the transformed features become comparable and easy to find their relation  ...  There are two approaches for multi-class classification (Suk and Lee 2013; Zhang and Shen 2012) , such as one-against-rest and oneagainst-one.  ... 
doi:10.1007/s11682-015-9430-4 pmid:26254746 pmcid:PMC4747862 fatcat:ce5aejjgpfhahc5gmf7ouvoxne

"You might also like this model": Data Driven Approach for Recommending Deep Learning Models for Unknown Image Datasets [article]

Ameya Prabhu, Riddhiman Dasgupta, Anush Sankaran, Srikanth Tamilselvam, Senthil Mani
2020 arXiv   pre-print
We discuss the implications of the proposed approach for three benchmark images datasets and also the challenges in using the approach for text modality.  ...  We propose a model encoder approach to learn a fixed length representation of deep learning architectures along with its hyperparameters, in an unsupervised fashion.  ...  the image modality: (i) GIST [22] (ii) DAISY [30] (iii) Local Binary Pattern (LBP) [35] .  ... 
arXiv:1911.11433v2 fatcat:w4ki22d2hzhhvf5fy3e4wsqiye

M2Net: Multi-modal Multi-channel Network for Overall Survival Time Prediction of Brain Tumor Patients [article]

Tao Zhou, Huazhu Fu, Yu Zhang, Changqing Zhang, Xiankai Lu, Jianbing Shen, Ling Shao
2020 arXiv   pre-print
A multi-modal shared network is built to fuse these features using a bilinear pooling model, exploiting their correlations to provide complementary information.  ...  To address the above issues, we propose an end-to-end OS time prediction model; namely, Multi-modal Multi-channel Network (M2Net).  ...  [9] conducted OS prediction by training an ensemble of a random forest regressor. Nie et al.  ... 
arXiv:2006.10135v2 fatcat:blzhuroxyzgo7crgim4nmcgzse

Cascade Graph Neural Networks for RGB-D Salient Object Detection [article]

Ao Luo, Xin Li, Fan Yang, Zhicheng Jiao, Hong Cheng, Siwei Lyu
2020 arXiv   pre-print
the mutual benefits between these two data sources through a set of cascade graphs, to learn powerful representations for RGB-D salient object detection.  ...  images is how to fully leverage the two complementary data sources.  ...  Classical approaches extract handcrafted features from the input RGB-D data and perform cross-modality feature fusion by various strategies, such as random forest regressor [56] and minimum barrier distance  ... 
arXiv:2008.03087v1 fatcat:nrjn4fkk65bynf3yyzfjn4wimy

Deep Head Pose: Gaze-Direction Estimation in Multimodal Video

Sankha S. Mukherjee, Neil Martin Robertson
2015 IEEE transactions on multimedia  
In this paper we present a convolutional neural network (CNN)-based model for human head pose estimation in low-resolution multi-modal RGB-D data.  ...  We further fine-tune a regressor based on the learned deep classifier. Next we combine the two models (classification and regression) to estimate approximate regression confidence.  ...  They would also like to thank Microsoft for providing access to the Kinect developer program.  ... 
doi:10.1109/tmm.2015.2482819 fatcat:qrz7fhtnynbjbfwt6eqlr4enw4

Revealing the mechanisms behind novel auditory stimuli discrimination: An evaluation of silent functional MRI using looping star

Nikou L Damestani, Owen O'Daly, Ana Beatriz Solana, Florian Wiesinger, David J Lythgoe, Simon Hill, Alfonso de Lara Rubio, Elena Makovac, Steven C R Williams, Fernando Zelaya
2021 Human Brain Mapping  
Looping Star is a near-silent, multi-echo, 3D functional magnetic resonance imaging (fMRI) technique.  ...  We aimed to demonstrate, for the first time, that multi-echo Looping Star has sufficient sensitivity to the BOLD response, compared to that of GRE-EPI, during a well-established event-related auditory  ...  Scale of ICC z-score maps adjusted to account for functional sensitivity differences between modalities et al.  ... 
doi:10.1002/hbm.25407 pmid:33729637 pmcid:PMC8127154 fatcat:gbrfmb7xivflbc2v4sppnofata

Pheno-Deep Counter: a unified and versatile deep learning architecture for leaf counting

Mario Valerio Giuffrida, Peter Doerner, Sotirios A. Tsaftaris
2018 The Plant Journal  
We demonstrate that our architecture can count leaves from multi-modal 2D images, such as visible light, fluorescence and near-infrared.  ...  Our network design is flexible, allowing for inputs to be added or removed to accommodate new modalities.  ...  ACKNOWLEDGEMENTS We thank Nvidia Corp. for providing the GPU used for this paper. We also thank Andrei Dobrescu for his valuable help.  ... 
doi:10.1111/tpj.14064 pmid:30101442 fatcat:lr24zpm6arhvhdh76tmol5rjpu

Highly parallel steered mixture-of-experts rendering at pixel-level for image and light field data

Vasileios Avramelos, Ruben Verhack, Ignace Saenen, Glenn Van Wallendael, Bart Goossens, Peter Lambert
2018 Journal of Real-Time Image Processing  
In particular, it has strong potential for coding and streaming higher dimensional image modalities that are necessary to leverage full translational and rotational freedom (6 Degrees-of-Freedom) in virtual  ...  A novel image approximation framework called Steered Mixture-of-Experts (SMoE) was recently presented.  ...  The joint probability function of the coordinate space X and color space Y is modeled as a multi-modal, multi-variate Gaussian Mixture Model.  ... 
doi:10.1007/s11554-018-0843-3 fatcat:pcubeilcizeu5ezx52wnv2udvi

Ensemble CCA for Continuous Emotion Prediction

Heysem Kaya, Fazilet Çilli, Albert Ali Salah
2014 Proceedings of the 4th International Workshop on Audio/Visual Emotion Challenge - AVEC '14  
Combining both representations in a CCA ensemble approach, on the challenge test set we reach an average Pearson's Correlation Coefficient (PCC) of 0.3932, outperforming the ASC test set baseline PCC of  ...  We obtain an ensemble of regional linear regressors via CCA and MPGI.  ...  The authors thank the anonymous reviewers for beneficial suggestions. The first author is a member of Faculty Member Training Program (ÖYP) supervised by the Turkish Higher Education Council (YÖK).  ... 
doi:10.1145/2661806.2661814 dblp:conf/mm/KayaCS14 fatcat:rahuwjxrevfzbexzeef5a4wsvy

Review of Disentanglement Approaches for Medical Applications – Towards Solving the Gordian Knot of Generative Models in Healthcare [article]

Jana Fragemann, Lynton Ardizzone, Jan Egger, Jens Kleesiek
2022 arXiv   pre-print
Deep neural networks are commonly used for medical purposes such as image generation, segmentation, or classification.  ...  Encouraging the latent representation of a generative model to be disentangled offers new perspectives of control and interpretability.  ...  Multi-Modal Brain Analysis Results from Synthetic MRI Modality Generation For Magnetic Resonance (MR) images, different contrast acquisitions show different aspects, important for diagnosis.  ... 
arXiv:2203.11132v1 fatcat:fxrniu6dtjcz5cumwientkqh7i

Seeing Beyond Appearance - Mapping Real Images into Geometrical Domains for Unsupervised CAD-based Recognition [article]

Benjamin Planche, Sergey Zakharov, Ziyan Wu, Andreas Hutter, Harald Kosch, Slobodan Ilic
2018 arXiv   pre-print
a more refined mapping for unseen color images.  ...  Applying our approach to object recognition from texture-less CAD data, we present a custom generative network which fully utilizes the purely geometrical information to learn robust features and achieve  ...  [27] use a unified Deep Convolutional Neural Fields (DCNF) framework based on the combination of a CNN and conditional random field (CRF) to regress depth from monocular color images of various scenes  ... 
arXiv:1810.04158v1 fatcat:vhywhkfbjnbsndpjjpabf537b4

Self-supervised learning methods and applications in medical imaging analysis: A survey [article]

Saeed Shurrab, Rehab Duwairi
2021 arXiv   pre-print
This article reviews the state-of-the-art research directions in self-supervised learning approaches for image data with concentration on their applications in the field of medical imaging analysis.  ...  The article covers a set of the most recent self-supervised learning methods from the computer vision field as they are applicable to the medical imaging analysis and categorize them as predictive, generative  ...  [2020a] proposed multi-modal reconstruction task as a self-supervised approach for retinal anatomy learning.  ... 
arXiv:2109.08685v2 fatcat:iu2zanqqrnaflawcxndb6xszgu

Audio-Visual Perception of 3D Cinematography: An fMRI Study Using Condition-Based and Computation-Based Analyses

Akitoshi Ogawa, Cecile Bordier, Emiliano Macaluso, Jyrki Ahveninen
2013 PLoS ONE  
Here, we exploited both approaches to investigate the neural correlates of complex visual and auditory spatial signals in cinematography.  ...  The complexity of the surround sounds was associated with activity in specific sub-regions of S/MTG, even after accounting for changes of sound intensity.  ...  Specifically, we considered the sound intensity contrast extracted using the same multi-scale approach adopted for the visual modality (see also [55] ).  ... 
doi:10.1371/journal.pone.0076003 pmid:24194828 pmcid:PMC3806767 fatcat:bif2ixoe7jafxg77hynebpiuw4
« Previous Showing results 1 — 15 out of 738 results