Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation

Search Page

Filters

My NCBI Filters

Results by year

Table representation of search results timeline featuring number of search results per year.

Year Number of Results
2014 1
2016 1
2017 2
2018 2
2019 1
2022 2
2023 4
2024 1

Text availability

Article attribute

Article type

Publication date

Search Results

12 results

Results by year

Filters applied: . Clear all
Page 1
Weakly Supervised Visual Saliency Prediction.
Zhou L, Zhou T, Khan S, Sun H, Shen J, Shao L. Zhou L, et al. IEEE Trans Image Process. 2022;31:3111-3124. doi: 10.1109/TIP.2022.3158064. Epub 2022 Apr 18. IEEE Trans Image Process. 2022. PMID: 35380961
In contrast, in this paper, we introduce a model based on various cognitive theories of visual saliency, which learns visual attention patterns in a weakly supervised manner. Our approach incorporates insights from cognitive science as differentiable submodules, res …
In contrast, in this paper, we introduce a model based on various cognitive theories of visual saliency, which learns visual attention patte …
Constrained-CNN losses for weakly supervised segmentation.
Kervadec H, Dolz J, Tang M, Granger E, Boykov Y, Ben Ayed I. Kervadec H, et al. Med Image Anal. 2019 May;54:88-99. doi: 10.1016/j.media.2019.02.009. Epub 2019 Feb 13. Med Image Anal. 2019. PMID: 30851541
Weakly-supervised learning based on, e.g., partially labelled images or image-tags, is currently attracting significant attention in CNN segmentation as it can mitigate the need for full and laborious pixel/voxel annotations. ...We propose to introduce a differentiable …
Weakly-supervised learning based on, e.g., partially labelled images or image-tags, is currently attracting significant attention in …
Dual Consistency Enabled Weakly and Semi-Supervised Optic Disc and Cup Segmentation With Dual Adaptive Graph Convolutional Networks.
Meng Y, Zhang H, Zhao Y, Gao D, Hamill B, Patri G, Peto T, Madhusudhan S, Zheng Y. Meng Y, et al. IEEE Trans Med Imaging. 2023 Feb;42(2):416-429. doi: 10.1109/TMI.2022.3203318. Epub 2023 Feb 2. IEEE Trans Med Imaging. 2023. PMID: 36044486
However, they rely on a large set of labeled masks for training, which is expensive and time-consuming to acquire. To address this, we propose a weakly and semi-supervised graph-based network that investigates geometric associations and domain knowledge between segmentatio …
However, they rely on a large set of labeled masks for training, which is expensive and time-consuming to acquire. To address this, we propo …
Lagrangian large eddy simulations via physics-informed machine learning.
Tian Y, Woodward M, Stepanov M, Fryer C, Hyett C, Livescu D, Chertkov M. Tian Y, et al. Proc Natl Acad Sci U S A. 2023 Aug 22;120(34):e2213638120. doi: 10.1073/pnas.2213638120. Epub 2023 Aug 16. Proc Natl Acad Sci U S A. 2023. PMID: 37585463 Free PMC article.
Our Lagrangian LES, thus L-LES, is described by equations generalizing the weakly compressible smoothed particle hydrodynamics formulation with extended parametric and functional freedom, which is then resolved via Machine Learning training on Lagrangian data from d …
Our Lagrangian LES, thus L-LES, is described by equations generalizing the weakly compressible smoothed particle hydrodynamics formul …
Time Rescaling of a Primal-Dual Dynamical System with Asymptotically Vanishing Damping.
Hulett DA, Nguyen DK. Hulett DA, et al. Appl Math Optim. 2023;88(2):27. doi: 10.1007/s00245-023-09999-9. Epub 2023 May 31. Appl Math Optim. 2023. PMID: 37274932 Free PMC article.
In this work, we approach the minimization of a continuously differentiable convex function under linear equality constraints by a second-order dynamical system with an asymptotically vanishing damping term. ...When the objective function has a Lipschitz cont …
In this work, we approach the minimization of a continuously differentiable convex function under linear equality constraints …
Multi-granularity learning of explicit geometric constraint and contrast for label-efficient medical image segmentation and differentiable clinical function assessment.
Meng Y, Zhang Y, Xie J, Duan J, Joddrell M, Madhusudhan S, Peto T, Zhao Y, Zheng Y. Meng Y, et al. Med Image Anal. 2024 Apr 20;95:103183. doi: 10.1016/j.media.2024.103183. Online ahead of print. Med Image Anal. 2024. PMID: 38692098 Free article.
Thirdly, we exploit the task-specific clinical domain knowledge to differentiate the clinical function assessment end-to-end. The ground truth of clinical function assessment, on the other hand, can serve as auxiliary weak supervision for PolyV and PixelR learning. …
Thirdly, we exploit the task-specific clinical domain knowledge to differentiate the clinical function assessment end-to-end. The gro …
PosturePose: Optimized Posture Analysis for Semi-Supervised Monocular 3D Human Pose Estimation.
Amadi L, Agam G. Amadi L, et al. Sensors (Basel). 2023 Dec 11;23(24):9749. doi: 10.3390/s23249749. Sensors (Basel). 2023. PMID: 38139594 Free PMC article.
One motivation for studying semi-supervised techniques for human pose estimation is to compensate for the lack of variety in curated 3D human pose datasets by combining labeled 3D pose data with readily available unlabeled video data-effectively, leveraging the annotations of the …
One motivation for studying semi-supervised techniques for human pose estimation is to compensate for the lack of variety in curated 3D huma …
How Well Does Kohn-Sham Regularizer Work for Weakly Correlated Systems?
Kalita B, Pederson R, Chen J, Li L, Burke K. Kalita B, et al. J Phys Chem Lett. 2022 Mar 24;13(11):2540-2547. doi: 10.1021/acs.jpclett.2c00371. Epub 2022 Mar 14. J Phys Chem Lett. 2022. PMID: 35285630
Kohn-Sham regularizer (KSR) is a differentiable machine learning approach to finding the exchange-correlation functional in Kohn-Sham density functional theory that works for strongly correlated systems. ...The generalization error from our semilocal approxim …
Kohn-Sham regularizer (KSR) is a differentiable machine learning approach to finding the exchange-correlation functional in Ko …
Partial Label Learning via Gaussian Processes.
Zhou Y, He J, Gu H. Zhou Y, et al. IEEE Trans Cybern. 2017 Dec;47(12):4443-4450. doi: 10.1109/TCYB.2016.2611534. Epub 2016 Oct 4. IEEE Trans Cybern. 2017. PMID: 28113534
Then a new likelihood function is defined to disambiguate the ambiguous labeling information conveyed by the training data. By introducing the aggregate function to approximate the function involved in likelihood function, not only is a likelihood f …
Then a new likelihood function is defined to disambiguate the ambiguous labeling information conveyed by the training data. By introd …
An Inertial Proximal-Gradient Penalization Scheme for Constrained Convex Optimization Problems.
Boţ RI, Csetnek ER, Nimana N. Boţ RI, et al. Vietnam J Math. 2018;46(1):53-71. doi: 10.1007/s10013-017-0256-9. Epub 2017 Sep 1. Vietnam J Math. 2018. PMID: 32714952 Free PMC article.
We propose a proximal-gradient algorithm with penalization terms and inertial and memory effects for minimizing the sum of a proper, convex, and lower semicontinuous and a convex differentiable function subject to the set of minimizers of another convex different …
We propose a proximal-gradient algorithm with penalization terms and inertial and memory effects for minimizing the sum of a proper, convex, …
12 results