Related papers: Visual link retrieval and knowledge discovery in p…
User preference profiling is an important task in modern online social networks (OSN). With the proliferation of image-centric social platforms, such as Pinterest, visual contents have become one of the most informative data streams for…
We study the problem of graph structure identification, i.e., of recovering the graph of dependencies among time series. We model these time series data as components of the state of linear stochastic networked dynamical systems. We assume…
Human reasoning in visual analytics of data networks relies mainly on the quality of visual perception and the capability of interactively exploring the data from different facets. Visual quality strongly depends on networks' size and…
Many visualization techniques have been created to explain the behavior of computer vision models, but they largely consist of static diagrams that convey limited information. Interactive visualizations allow users to more easily interpret…
In a real-world setting, visual recognition systems can be brought to make predictions for images belonging to previously unknown class labels. In order to make semantically meaningful predictions for such inputs, we propose a two-step…
We are developing semantic visualization techniques in order to enhance exploration and enable discovery over large datasets of complex networks of relations. Semantic visualization is a method of enabling exploration and discovery over…
We propose a new technique for visual attribute transfer across images that may have very different appearance but have perceptually similar semantic structure. By visual attribute transfer, we mean transfer of visual information (such as…
We study the intriguing connection between visual data, deep networks, and the brain. Our method creates a universal channel alignment by using brain voxel fMRI response prediction as the training objective. We discover that deep networks,…
Supply chain network data is a valuable asset for businesses wishing to understand their ethical profile, security of supply, and efficiency. Possession of a dataset alone however is not a sufficient enabler of actionable decisions due to…
In analyzing vast amounts of digitally stored historical image data, existing content-based retrieval methods often overlook significant non-semantic information, limiting their effectiveness for flexible exploration across varied themes.…
The study of canvas fabrics in works of art is a crucial tool for authentication, attribution and conservation. Traditional methods are based on thread density map matching, which cannot be applied when canvases do not come from contiguous…
Learnable keypoint detectors and descriptors are beginning to outperform classical hand-crafted feature extraction methods. Recent studies on self-supervised learning of visual representations have driven the increasing performance of…
Understanding visual relationships involves identifying the subject, the object, and a predicate relating them. We leverage the strong correlations between the predicate and the (subj,obj) pair (both semantically and spatially) to predict…
When applying learning to rank algorithms to Web search, a large number of features are usually designed to capture the relevance signals. Most of these features are computed based on the extracted textual elements, link analysis, and user…
Human observers engage in selective information uptake when classifying visual patterns. The same is true of deep neural networks, which currently constitute the best performing artificial vision systems. Our goal is to examine the…
We introduce a new video synthesis task: synthesizing time lapse videos depicting how a given painting might have been created. Artists paint using unique combinations of brushes, strokes, and colors. There are often many possible ways to…
In the forensic studies of painting masterpieces, the analysis of the support is of major importance. For plain weave fabrics, the densities of vertical and horizontal threads are used as main features, while angle deviations from the…
More than ten thousand Chinese historical painters are recorded in the literature; their cohort analysis has always been a key area of research on Chinese painting history for both professional historians and amateur enthusiasts. However,…
Traditionally, training neural networks to perform semantic segmentation required expensive human-made annotations. But more recently, advances in the field of unsupervised learning have made significant progress on this issue and towards…
The goal of our research is to develop methods advancing automatic visual recognition. In order to predict the unique or multiple labels associated to an image, we study different kind of Deep Neural Networks architectures and methods for…