scholarly journals Optimizing Visual Representations in Semantic Multi-modal Models with Dimensionality Reduction, Denoising and Contextual Information

2018 ◽  
pp. 292-300
Author(s):  
Maximilian Köper ◽  
Kim-Anh Nguyen ◽  
Sabine Schulte im Walde
Keyword(s):  
Dimensionality Reduction ◽  
Contextual Information ◽  
Visual Representations

scholarly journals ContextNet: representation and exploration for painting classification and retrieval in context

2019 ◽  
Vol 9 (1) ◽  
pp. 17-30
Author(s):  
Noa Garcia ◽  
Benjamin Renoust ◽  
Yuta Nakashima
Keyword(s):  
Contextual Information ◽  
Visual Representations ◽  
Fine Art ◽  
Multitask Learning ◽  
Knowledge Graph ◽  
Multiple Sources ◽  
Visual Elements ◽  
Knowledge Graphs ◽  
Art Analysis ◽  
Analysis Models

AbstractIn automatic art analysis, models that besides the visual elements of an artwork represent the relationships between the different artistic attributes could be very informative. Those kinds of relationships, however, usually appear in a very subtle way, being extremely difficult to detect with standard convolutional neural networks. In this work, we propose to capture contextual artistic information from fine-art paintings with a specific ContextNet network. As context can be obtained from multiple sources, we explore two modalities of ContextNets: one based on multitask learning and another one based on knowledge graphs. Once the contextual information is obtained, we use it to enhance visual representations computed with a neural network. In this way, we are able to (1) capture information about the content and the style with the visual representations and (2) encode relationships between different artistic attributes with the ContextNet. We evaluate our models on both painting classification and retrieval, and by visualising the resulting embeddings on a knowledge graph, we can confirm that our models represent specific stylistic aspects present in the data.

scholarly journals The Cortical Underpinnings of Context-based Memory Distortion

2008 ◽  
Vol 20 (12) ◽  
pp. 2226-2237 ◽  
Author(s):  
Elissa Aminoff ◽  
Daniel L. Schacter ◽  
Moshe Bar
Keyword(s):  
Magnetic Resonance Imaging ◽  
Contextual Information ◽  
False Memories ◽  
Visual Representations ◽  
Cortical Network ◽  
Memory Distortion ◽  
Functional Magnetic Resonance ◽  
Resonance Imaging ◽  
Contextual Processing ◽  
The Brain

Everyday contextual settings create associations that later afford generating predictions about what objects to expect in our environment. The cortical network that takes advantage of such contextual information is proposed to connect the representation of associated objects such that seeing one object (bed) will activate the visual representations of other objects sharing the same context (pillow). Given this proposal, we hypothesized that the cortical activity elicited by seeing a strong contextual object would predict the occurrence of false memories whereby one erroneously “remembers” having seen a new object that is related to a previously presented object. To test this hypothesis, we used functional magnetic resonance imaging during encoding of contextually related objects, and later tested recognition memory. New objects that were contextually related to previously presented objects were more often falsely judged as “old” compared with new objects that were contextually unrelated to old objects. This phenomenon was reflected by activity in the cortical network mediating contextual processing, which provides a better understanding of how the brain represents and processes context.

Feature Dimension Reduction and Graph Based Ranking Based Image Classification

2013 ◽  
Vol 380-384 ◽  
pp. 4035-4038 ◽  
Author(s):  
Nan Yao ◽  
Feng Qian ◽  
Zuo Lei Sun
Keyword(s):  
Dimensionality Reduction ◽  
Dimension Reduction ◽  
Image Classification ◽  
Learning Algorithm ◽  
Contextual Information ◽  
Original Data ◽  
Classification Problem ◽  
Image Features ◽  
Similarity Learning ◽  
Low Dimensional

Dimensionality reduction (DR) of image features plays an important role in image retrieval and classification tasks. Recently, two types of methods have been proposed to improve both the accuracy and efficiency for the dimensionality reduction problem. One uses Non-negative matrix factorization (NMF) to describe the image distribution on the space of base matrix. Another one for dimension reduction trains a subspace projection matrix to project original data space into some low-dimensional subspaces which have deep architecture, so that the low-dimensional codes would be learned. At the same time, the graph based similarity learning algorithm which tries to exploit contextual information for improving the effectiveness of image rankings is also proposed for image class and retrieval problem. In this paper, after above two methods mentioned are utilized to reduce the high-dimensional features of images respectively, we learn the graph based similarity for the image classification problem. This paper compares the proposed approach with other approaches on an image database.

scholarly journals Dimensionality reduction of medical image descriptors for multimodal image registration

2015 ◽  
Vol 1 (1) ◽  
pp. 201-205 ◽  
Author(s):  
Johanna Degen ◽  
Jan Modersitzki ◽  
Mattias P. Heinrich
Keyword(s):  
Image Registration ◽  
Dimensionality Reduction ◽  
Spatial Information ◽  
Contextual Information ◽  
Computation Time ◽  
Principal Component ◽  
Relevant Research ◽  
Multimodal Image Registration ◽  
Image Descriptors ◽  
Image Patches

AbstractDefining similarity forms a challenging and relevant research topic in multimodal image registration. The frequently used mutual information disregards contextual information, which is shared across modalities. A recent popular approach, called modality independent neigh-bourhood descriptor, is based on local self-similarities of image patches and is therefore able to capture spatial information. This image descriptor generates vectorial representations, i.e. it is multidimensional, which results in a disadvantage in terms of computation time. In this work, we present a problem-adapted solution for dimensionality reduction, by using principal component analysis and Horn’s parallel analysis. Furthermore, the influence of dimensionality reduction in global rigid image registration is investigated. It is shown that the registration results obtained from the reduced descriptor have the same high quality in comparison to those found for the original descriptor.

Analysis on Research Paper Publication Recommendation System with Composition of Papers and Conferences Matrices

2020 ◽  
pp. 120-127
Author(s):  
Htay Htay Win ◽  
Aye Thida Myint ◽  
Mi Cho Cho
Keyword(s):  
Social Network ◽  
Dimensionality Reduction ◽  
Correspondence Analysis ◽  
Recommendation System ◽  
Research Paper ◽  
Topic Modelling ◽  
Research Papers ◽  
The Right ◽  
Publication Recommendation

For years, achievements and discoveries made by researcher are made aware through research papers published in appropriate journals or conferences. Many a time, established s researcher and mainly new user are caught up in the predicament of choosing an appropriate conference to get their work all the time. Every scienti?c conference and journal is inclined towards a particular ?eld of research and there is a extensive group of them for any particular ?eld. Choosing an appropriate venue is needed as it helps in reaching out to the right listener and also to further one’s chance of getting their paper published. In this work, we address the problem of recommending appropriate conferences to the authors to increase their chances of receipt. We present three di?erent approaches for the same involving the use of social network of the authors and the content of the paper in the settings of dimensionality reduction and topic modelling. In all these approaches, we apply Correspondence Analysis (CA) to obtain appropriate relationships between the entities in question, such as conferences and papers. Our models show hopeful results when compared with existing methods such as content-based ?ltering, collaborative ?ltering and hybrid ?ltering.

A Medieval Burial from Graham Street, Leith, Edinburgh

2003 ◽  
Vol 25 (2) ◽  
pp. 165-169
Author(s):  
Paul R. J. Duffy ◽  
Olivia Lelong
Keyword(s):  
Contextual Information ◽  
Human Remains ◽  
Housing Development ◽  
Archaeological Research ◽  
Archaeological Excavation ◽  
Radiocarbon Dates ◽  
Physical Evidence ◽  
Research Division ◽  
The North ◽  
The Individual

Summary An archaeological excavation was carried out at Graham Street, Leith, Edinburgh by Glasgow University Archaeological Research Division (GUARD) as part of the Historic Scotland Human Remains Call-off Contract following the discovery of human remains during machine excavation of a foundation trench for a new housing development. Excavation demonstrated that the burial was that of a young adult male who had been interred in a supine position with his head orientated towards the north. Radiocarbon dates obtained from a right tibia suggest the individual died between the 15th and 17th centuries AD. Little contextual information exists in documentary or cartographic sources to supplement this scant physical evidence. Accordingly, it is difficult to further refine the context of burial, although a possible link with a historically attested siege or a plague cannot be discounted.

PRIMING AND THE PREDICTABILITY OF CONTEXTUAL INFORMATION

2004 ◽  
Vol 99 (7) ◽  
pp. 1075
Author(s):  
MAURA PILOTTI
Keyword(s):  
Contextual Information

Speech Emotion Recognition Based on Sparse Representation

2013 ◽  
Vol 38 (4) ◽  
pp. 465-470 ◽  
Author(s):  
Jingjie Yan ◽  
Xiaolan Wang ◽  
Weiyi Gu ◽  
LiLi Ma
Keyword(s):  
Dimensionality Reduction ◽  
Emotion Recognition ◽  
Least Squares ◽  
Partial Least Squares ◽  
Partial Least Squares Regression ◽  
Speech Emotion Recognition ◽  
Least Squares Regression ◽  
Computer Science Pedagogy ◽  
Reduction Methods ◽  
Analysis Computer

Abstract Speech emotion recognition is deemed to be a meaningful and intractable issue among a number of do- mains comprising sentiment analysis, computer science, pedagogy, and so on. In this study, we investigate speech emotion recognition based on sparse partial least squares regression (SPLSR) approach in depth. We make use of the sparse partial least squares regression method to implement the feature selection and dimensionality reduction on the whole acquired speech emotion features. By the means of exploiting the SPLSR method, the component parts of those redundant and meaningless speech emotion features are lessened to zero while those serviceable and informative speech emotion features are maintained and selected to the following classification step. A number of tests on Berlin database reveal that the recogni- tion rate of the SPLSR method can reach up to 79.23% and is superior to other compared dimensionality reduction methods.

Migration, Gender and Visual Culture:

MedienJournal ◽  
2017 ◽  
Vol 37 (3) ◽  
pp. 32-44 ◽  
Author(s):  
Ksenija Vidmar Horvat
Keyword(s):  
Cultural Studies ◽  
Visual Culture ◽  
Critical Angle ◽  
Visual Representations ◽  
Public Culture ◽  
Migration Studies ◽  
New Paradigm ◽  
Current Field ◽  
Shared Interest ◽  
European Migration

 This paper investigates visual representations of migrants in Slovenia. The focus is on immigrant groups from China and Thailand and the construction of their ‘ethnic’ presence in postsocialist public culture. The aim of the paper is to provide a critical angle on the current field of cultural studies as well as on European migration studies. The author argues that both fields can find a shared interest in mutual theoretical and critical collaboration; but what the two traditions also need, is to reconceptualize the terrain of investigation of Europe which will be methodologically reorganized as a post- 1989 and post-westernocentric. Examination of migration in postsocialism may be an important step in drawing the new paradigm.

Sign in / Sign up

Export Citation Format

Share Document