Related papers: Enhancing Perceptual Attributes with Bayesian Styl…

Large text-to-image models achieved a remarkable leap in the evolution of AI, enabling high-quality and diverse synthesis of images from a given text prompt. However, these models lack the ability to mimic the appearance of subjects in a…

Previous text-to-image synthesis algorithms typically use explicit textual instructions to generate/manipulate images accurately, but they have difficulty adapting to guidance in the form of coarsely matched texts. In this work, we attempt…

Generative adversarial networks (GANs) have shown potential in learning emotional attributes and generating new data samples. However, their performance is usually hindered by the unavailability of larger speech emotion recognition (SER)…

Over the last few decades, psychologists have developed sophisticated formal models of human categorization using simple artificial stimuli. In this paper, we use modern machine learning methods to extend this work into the realm of…

Visual attributes are great means of describing images or scenes, in a way both humans and computers understand. In order to establish a correspondence between images and to be able to compare the strength of each property between images,…

Deep learning has shown its human-level performance in various applications. However, current deep learning models are characterised by catastrophic forgetting of old knowledge when learning new classes. This poses a challenge particularly…

Change detection has been a challenging visual task due to the dynamic nature of real-world scenes. Good performance of existing methods depends largely on prior background images or a long-term observation. These methods, however, suffer…

Generative models are now widely used by graphic designers and artists. Prior works have shown that these models remember and often replicate content from their training data during generation. Hence as their proliferation increases, it has…

We present a deep learning-based method for propagating spatially-varying visual material attributes (e.g. texture maps or image stylizations) to larger samples of the same or similar materials. For training, we leverage images of the…

Automating quality inspection with computer vision techniques is often a very data-demanding task. Specifically, supervised deep learning requires a large amount of annotated images for training. In practice, collecting and annotating such…

In this study, we explore building a two-stage framework for enabling users to directly manipulate high-level attributes of a natural scene. The key to our approach is a deep generative network which can hallucinate images of a scene as if…

There is significant growth and interest in the use of synthetic data as an enabler for machine learning in environments where the release of real data is restricted due to privacy or availability constraints. Despite a large number of…

Despite data augmentation being a de facto technique for boosting the performance of deep neural networks, little attention has been paid to developing augmentation strategies for generative adversarial networks (GANs). To this end, we…

Learning useful representations from unstructured data is one of the core challenges, as well as a driving force, of modern data-driven approaches. Deep learning has demonstrated the broad advantages of learning and harnessing such…

Performance achievable by modern deep learning approaches are directly related to the amount of data used at training time. Unfortunately, the annotation process is notoriously tedious and expensive, especially for pixel-wise tasks like…

The style of an image plays a significant role in how it is viewed, but style has received little attention in computer vision research. We describe an approach to predicting style of images, and perform a thorough evaluation of different…

Recently, it has been shown that in super-resolution, there exists a tradeoff relationship between the quantitative and perceptual quality of super-resolved images, which correspond to the similarity to the ground-truth images and the…

We describe a novel learning-by-synthesis method for estimating gaze direction of an automated intelligent surveillance system. Recently, progress in learning-by-synthesis has proposed training models on synthetic images, which can…

Many aesthetic models in computer vision suffer from two shortcomings: 1) the low descriptiveness and interpretability of those hand-crafted aesthetic criteria (i.e., nonindicative of region-level aesthetics), and 2) the difficulty of…

Humans perceive the seemingly chaotic world in a structured and compositional way with the prerequisite of being able to segregate conceptual entities from the complex visual scenes. The mechanism of grouping basic visual elements of scenes…