Related papers: Joint Quality Assessment and Example-Guided Image …
Image denoising is a fundamental task in low-level computer vision. While recent deep learning-based image denoising methods have achieved impressive performance, they are black-box models and the underlying denoising principle remains…
Image degradation synthesis is highly desirable in a wide variety of applications ranging from image restoration to simulating artistic effects. Existing models are designed to generate one specific or a narrow set of degradations, which…
Despite the limited availability and quantum volume of quantum computers, quantum image representation is a widely researched area. Currently developed methods use quantum entanglement to encode information about pixel positions. These…
For visual manipulation tasks, we aim to represent image content with semantically meaningful features. However, learning implicit representations from images often lacks interpretability, especially when attributes are intertwined. We…
Representation learning is the foundation for the recent success of neural network models. However, the distributed representations generated by neural networks are far from ideal. Due to their highly entangled nature, they are di cult to…
A crucial problem in learning disentangled image representations is controlling the degree of disentanglement during image editing, while preserving the identity of objects. In this work, we propose a simple yet effective model with the…
Self-supervised learning has achieved remarkable success in learning visual representations from clean data, yet remains challenging when clean observations are sparse or not available at all. In this paper, we demonstrate that pretrained…
Quantization has been applied to multiple domains in Deep Neural Networks (DNNs). We propose Depthwise Quantization (DQ) where $\textit{quantization}$ is applied to a decomposed sub-tensor along the $\textit{feature axis}$ of weak…
Previous literature suggests that perceptual similarity is an emergent property shared across deep visual representations. Experiments conducted on a dataset of human-judged image distortions have proven that deep features outperform…
Perceptual video quality assessment (VQA) is an integral component of many streaming and video sharing platforms. Here we consider the problem of learning perceptually relevant video quality representations in a self-supervised manner.…
We propose a new representation of visual data that disentangles object position from appearance. Our method, termed Deep Latent Particles (DLP), decomposes the visual input into low-dimensional latent ``particles'', where each particle is…
In recent years, deep learning has achieved promising success for multimedia quality assessment, especially for image quality assessment (IQA). However, since there exist more complex temporal characteristics in videos, very little work has…
In this paper, we propose a framework for disentangling the appearance and geometry representations in the face recognition task. To provide supervision for this aim, we generate geometrically identical faces by incorporating spatial…
Learning rich representation from data is an important task for deep generative models such as variational auto-encoder (VAE). However, by extracting high-level abstractions in the bottom-up inference process, the goal of preserving all…
We aim at advancing blind image quality assessment (BIQA), which predicts the human perception of image quality without any reference information. We develop a general and automated multitask learning scheme for BIQA to exploit auxiliary…
Conflicting objectives present a considerable challenge in interleaving multi-task learning, necessitating the need for meticulous design and balance to ensure effective learning of a representative latent data space across all tasks…
In disentangled representation learning, a model is asked to tease apart a dataset's underlying sources of variation and represent them independently of one another. Since the model is provided with no ground truth information about these…
Knowledge Editing has emerged as a promising solution for efficiently updating embedded knowledge in large language models (LLMs). While existing approaches demonstrate effectiveness in integrating new knowledge and preserving the original…
Human motion data is inherently rich and complex, containing both semantic content and subtle stylistic features that are challenging to model. We propose a novel method for effective disentanglement of the style and content in human motion…
Knowledge graph embedding (KGE), aiming to embed entities and relations into low-dimensional vectors, has attracted wide attention recently. However, the existing research is mainly based on the black-box neural models, which makes it…