Romain Bourqui
YOU?
Author Swipe
View article: Mean Opinion Score as a New Metric for User-Evaluation of XAI Methods
Mean Opinion Score as a New Metric for User-Evaluation of XAI Methods Open
This paper investigates the use of Mean Opinion Score (MOS), a common image quality metric, as a user-centric evaluation metric for XAI post-hoc explainers. To measure the MOS, a user experiment is proposed, which has been conducted with e…
View article: Overlap Removal by Stochastic Gradient Descent With(out) Shape Awareness
Overlap Removal by Stochastic Gradient Descent With(out) Shape Awareness Open
In many 2D visualizations, data points are projected without considering their surface area, although they are often represented as shapes in visualization tools. These shapes support the display of information such as labels or encode dat…
View article: Guaranteed Visibility in Scatterplots with Tolerance
Guaranteed Visibility in Scatterplots with Tolerance Open
In 2D visualizations, visibility of every datum's representation is crucial to ease the completion of visual tasks. Such a guarantee is barely respected in complex visualizations, mainly because of overdraws between datum representations t…
View article: NetPrune: A sparklines visualization for network pruning
NetPrune: A sparklines visualization for network pruning Open
Current deep learning approaches are cutting-edge methods for solving classification tasks. Arising transfer learning techniques allows applying large generic model to simple tasks whereas simpler models could be used. Large models raise t…
View article: State of the Art of Visual Analytics for eXplainable Deep Learning
State of the Art of Visual Analytics for eXplainable Deep Learning Open
The use and creation of machine‐learning‐based solutions to solve problems or reduce their computational costs are becoming increasingly widespread in many domains. Deep Learning plays a large part in this growth. However, it has drawbacks…
View article: Toward Efficient Deep Learning for Graph Drawing (DL4GD)
Toward Efficient Deep Learning for Graph Drawing (DL4GD) Open
Due to their great performance in many challenges, Deep Learning (DL) techniques keep gaining popularity in many fields. They have been adapted to process graph data structures to solve various complicated tasks such as graph classificatio…
View article: Relative Confusion Matrix: Efficient Comparison of Decision Models
Relative Confusion Matrix: Efficient Comparison of Decision Models Open
International audience
View article: VRGrid: Efficient Transformation of 2D Data into Pixel Grid Layout
VRGrid: Efficient Transformation of 2D Data into Pixel Grid Layout Open
International audience
View article: Deep Neural Network for DrawiNg Networks, (DNN)^2
Deep Neural Network for DrawiNg Networks, (DNN)^2 Open
By leveraging recent progress of stochastic gradient descent methods, several works have shown that graphs could be efficiently laid out through the optimization of a tailored objective function. In the meantime, Deep Learning (DL) techniq…
View article: Analysis of Deep Neural Networks Correlations with Human Subjects on a Perception Task
Analysis of Deep Neural Networks Correlations with Human Subjects on a Perception Task Open
International audience
View article: Visualizing food-drug interactions in the Thériaque database
Visualizing food-drug interactions in the Thériaque database Open
International audience
View article: Visualizing Food-Drug Interactions in the Thériaque Database
Visualizing Food-Drug Interactions in the Thériaque Database Open
This paper presents a prototype for the visualization of food-drug interactions implemented in the MIAM project, whose objective is to develop methods for the extraction and representation of these interactions and to make them available i…
View article: Impacts of the Numbers of Colors and Shapes on Outlier Detection: from Automated to User Evaluation
Impacts of the Numbers of Colors and Shapes on Outlier Detection: from Automated to User Evaluation Open
The design of efficient representations is well established as a fruitful way to explore and analyze complex or large data. In these representations, data are encoded with various visual attributes depending on the needs of the representat…
View article: Features Understanding in 3D CNNs for Actions Recognition in Video
Features Understanding in 3D CNNs for Actions Recognition in Video Open
International audience
View article: GSAn: an alternative to enrichment analysis for annotating gene sets
GSAn: an alternative to enrichment analysis for annotating gene sets Open
The revolution in new sequencing technologies is greatly leading to new understandings of the relations between genotype and phenotype. To interpret and analyze data that are grouped according to a phenotype of interest, methods based on s…
View article: Deep Dive into Deep Neural Networks with Flows
Deep Dive into Deep Neural Networks with Flows Open
International audience
View article: GSAn_Supplementary_Data: Description of the investigated gene sets
GSAn_Supplementary_Data: Description of the investigated gene sets Open
The following table provides the number of genes in each BTM gene set [1] as well as the number of genes annotated within GOA and by each of the following tools: GSAn, DAVID [2], g:Profiler [3], ClusterProfiler [4] and WebGestalt [5].
View article: GSAn_Supplementary_Data: Description of the investigated gene sets
GSAn_Supplementary_Data: Description of the investigated gene sets Open
The following table provides the number of genes in each BTM gene set [1] as well as the number of genes annotated within GOA and by each of the following tools: GSAn, DAVID [2], g:Profiler [3], ClusterProfiler [4] and WebGestalt [5].
View article: Deep Dive into Deep Neural Networks with Flows
Deep Dive into Deep Neural Networks with Flows Open
Deep neural networks are becoming omnipresent in reason of their growing popularity in media and their daily use. However, their global complexity makes them hard to understand which emphasizes their black-box aspect and the lack of confid…
View article: GSAn: an alternative to enrichment analysis for annotating gene sets
GSAn: an alternative to enrichment analysis for annotating gene sets Open
The revolution in new sequencing technologies, by strongly improving the production of omics data, is greatly leading to new understandings of the relations between genotype and phenotype. To interpret and analyze these massive data that a…
View article: CorFish: Coordinating Emphasis across Multiple Views using Spatial Distortion
CorFish: Coordinating Emphasis across Multiple Views using Spatial Distortion Open
International audience
View article: Enabling Hierarchical Exploration for Large-Scale Multidimensional Data with Abstract Parallel Coordinates
Enabling Hierarchical Exploration for Large-Scale Multidimensional Data with Abstract Parallel Coordinates Open
International audience
View article: HeatPipe: High Throughput, Low Latency Big Data Heatmap with Spark Streaming
HeatPipe: High Throughput, Low Latency Big Data Heatmap with Spark Streaming Open
International audience