Large-Context Pointer-Generator Networks for Spoken-to-Written Style Conversion

2020 ◽  
Author(s):  
Mana Ihori ◽  
Akihiko Takashima ◽  
Ryo Masumura
Keyword(s):  
Large Context

scholarly journals Armenian Culture from the Semiotic Perspective

2016 ◽  
Vol 12 (2 (16)) ◽  
pp. 133-138
Author(s):  
Armine Matevosyan ◽  
Manana Dalalyan
Keyword(s):  
Community Media ◽  
Specific Context ◽  
Verbal Interactions ◽  
Social Community ◽  
Language And Culture ◽  
Large Context ◽  
Armenian Identity ◽  
Semiotic Perspective ◽  
Context Of Situation ◽  
Media And Communication

The present paper goes along the lines of Semiotics, a branch of linguistics. It studies the system of signs which takes the form of words, images, sounds, gestures and objects. Through the usage of signs we represent the linguocultural aspect of our knowledge, ethnic traditions and folklore. The interest we take in the paper is the study of signs and symbols in Armenian culture. Culture, including miniature paining, singing, dancing, architecture and cuisine, may involve any sphere of Armenian identity. Signs and symbols that constitute language and culture are constructed through verbal and non-verbal interactions and are arbitrary. The purpose of our analysis is to specify what why, whom questions in a specific context of situation, as well as in a large context of culture, such as social community, media and communication.

RECONSTRUCTED TEETH IMAGE FROM BRACES WITH GAN

2021 ◽  
pp. 2150043
Author(s):  
Vu Tuan Hai ◽  
Dang Thanh Vu ◽  
Huynh Ho Thi Mong Trinh ◽  
Pham The Bao
Keyword(s):  
Health Care ◽  
Deep Learning ◽  
Training Data ◽  
Learning Models ◽  
Paired Data ◽  
Object Removal ◽  
Interactive Tool ◽  
Learning Techniques ◽  
Large Context ◽  
Image Translation

Recent advances in deep learning models have shown promising potential in object removal, which is the task of replacing undesired objects with appropriate pixel values using known context. Object removal-based deep learning can commonly be solved by modeling it as the Img2Img (image to image) translation or Inpainting. Instead of dealing with a large context, this paper aims at a specific application of object removal, that is, erasing braces trace out of an image having teeth with braces (called braces2teeth problem). We solved the problem by three methods corresponding to different datasets. Firstly, we use the CycleGAN model to deal with the problem that paired training data is not available. In the second case, we try to create pseudo-paired data to train the Pix2Pix model. In the last case, we utilize GraphCut combining generative inpainting model to build a user-interactive tool that can improve the result in case the user is not satisfied with previous results. To our best knowledge, this study is one of the first attempts to take the braces2teeth problem into account by using deep learning techniques and it can be applied in various fields, from health care to entertainment.

scholarly journals Existence of Weak Solution for a Free Boundary Lubrication Problem

2011 ◽  
Vol 2011 ◽  
pp. 1-12
Author(s):  
Abdelhamid Laouar
Keyword(s):  
Weak Solution ◽  
Free Boundary ◽  
Boundary Problem ◽  
Free Boundary Problem ◽  
Boundary Lubrication ◽  
Hydrodynamic Lubrication ◽  
Weak Formulation ◽  
Large Context ◽  
A Free Boundary Problem

This paper is interested in a free boundary problem modelling a phenomenon of cavitation in hydrodynamic lubrication. We reformulate the problem (see Boukrouche, (1993)) in a large context by introducing two positive parameters, namely, N0 and a. We build a weak formulation and establish the existence of the solution to the problem.

scholarly journals Accelerated EM Connectome Reconstruction using 3D Visualization and Segmentation Graphs

2020 ◽  
Author(s):  
Philip M. Hubbard ◽  
Stuart Berg ◽  
Ting Zhao ◽  
Donald J. Olbris ◽  
Lowell Umayam ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Single Neuron ◽  
3D Visualization ◽  
Superior Performance ◽  
Neural Connectivity ◽  
Trade Offs ◽  
Large Context ◽  
Segmentation Algorithms ◽  
The Brain ◽  
Large Neurons

AbstractRecent advances in automatic image segmentation and synapse prediction in electron microscopy (EM) datasets of the brain enable more efficient reconstruction of neural connectivity. In these datasets, a single neuron can span thousands of images containing complex tree-like arbors with thousands of synapses. While image segmentation algorithms excel within narrow fields of views, the algorithms sometimes struggle to correctly segment large neurons, which require large context given their size and complexity. Conversely, humans are comparatively good at reasoning with large objects. In this paper, we introduce several semi-automated strategies that combine 3D visualization and machine guidance to accelerate connectome reconstruction. In particular, we introduce a strategy to quickly correct a segmentation through merging and cleaving, or splitting a segment along supervoxel boundaries, with both operations driven by affinity scores in the underlying segmentation. We deploy these algorithms as streamlined workflows in a tool called Neu3 and demonstrate superior performance compared to prior work, thus enabling efficient reconstruction of much larger datasets. The insights into proofreading from our work clarify the trade-offs to consider when tuning the parameters of image segmentation algorithms.

scholarly journals Medical Image Segmentation using Squeeze-and-Expansion Transformers

2021 ◽  
Author(s):  
Shaohua Li ◽  
Xiuchao Sui ◽  
Xiangde Luo ◽  
Xinxing Xu ◽  
Yong Liu ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Medical Image ◽  
Receptive Fields ◽  
Image Features ◽  
Medical Image Segmentation ◽  
Tumor Segmentation ◽  
Brain Tumor Segmentation ◽  
Large Context ◽  
Mri Scans ◽  
Big Picture

Medical image segmentation is important for computer-aided diagnosis. Good segmentation demands the model to see the big picture and fine details simultaneously, i.e., to learn image features that incorporate large context while keep high spatial resolutions. To approach this goal, the most widely used methods -- U-Net and variants, extract and fuse multi-scale features. However, the fused features still have small "effective receptive fields" with a focus on local image cues, limiting their performance. In this work, we propose Segtran, an alternative segmentation framework based on transformers, which have unlimited "effective receptive fields" even at high feature resolutions. The core of Segtran is a novel Squeeze-and-Expansion transformer: a squeezed attention block regularizes the self attention of transformers, and an expansion block learns diversified representations. Additionally, we propose a new positional encoding scheme for transformers, imposing a continuity inductive bias for images. Experiments were performed on 2D and 3D medical image segmentation tasks: optic disc/cup segmentation in fundus images (REFUGE'20 challenge), polyp segmentation in colonoscopy images, and brain tumor segmentation in MRI scans (BraTS'19 challenge). Compared with representative existing methods, Segtran consistently achieved the highest segmentation accuracy, and exhibited good cross-domain generalization capabilities.

Attentional Modulation of Size Contrast

1992 ◽  
Vol 45 (4) ◽  
pp. 529-546 ◽  
Author(s):  
Gordon L. Shulman
Keyword(s):  
Vertical Axis ◽  
Horizontal Axis ◽  
Ebbinghaus Illusion ◽  
Attentional Modulation ◽  
Test Circle ◽  
Test Size ◽  
Large Context ◽  
Size Contrast

A test circle surrounded by smaller context circles appears larger if presented in isolation, whereas a test circle surrounded by large context circles is seen as smaller than in isolation. Two experiments are reported indicating that this phenomenon, the Ebbinghaus illusion, depends on whether subjects are attending to the context circles. Subjects first saw a reference circle and then a briefly presented (150 msec) test circle. Their task was to determine whether the test circle was larger or smaller than the reference. The test circle was surrounded by smaller context circles of one colour arrayed along a horizontal axis centred on the test, and larger context circles of a different colour arrayed along a vertical axis centred on the test. Subjects judged both the size of the test and the colours of either the small or large context circles. Perceived test size changed systematically, depending on which context circles were task-relevant.

scholarly journals Integrating self-regulated learning and discovery learning into English lesson plan

2018 ◽  
Vol 42 ◽  
pp. 00047
Author(s):  
Ni Kadek Heny Sayukti
Keyword(s):  
Lesson Plan ◽  
Lesson Planning ◽  
National Curriculum ◽  
Structured Interview ◽  
Discovery Learning ◽  
Self Regulated Learning ◽  
Learner Centeredness ◽  
Large Context ◽  
Regulated Learning ◽  
Tenth Grade

The notion of learner-centeredness has been embedded in the National Curriculum of Indonesia, 2013 Curriculum. However, most of the teachers seem to be hardly acquainted with the concept of Self-Regulated Learning (SRL) and discovery learning in the lesson planning. Considering the phenomenon, this study intends to explore the concept of Self-Regulated Learning in the lesson plan of English subject for a tenth-grade level by employing a qualitative design with data obtained from a teacher-made lesson plan and a semi-structured interview. The researcher used content analysis to analyze the lesson plan. Meanwhile, the qualitative data from interview result were preceded through a coding sheet and transcribed modified figure. The findings revealed an integration of SRL cyclical phase and discovery learning in the teacher-made lesson plan. Based on the discussion, the results need to be applied in a considerably large context, in order to see thoroughly dynamic integration between Self-Regulated Learning model, lesson planning and the concept of learner autonomy.

Sign in / Sign up

Export Citation Format

Share Document