Zobrazeno 1 - 10
of 1 472
pro vyhledávání: '"Lai, Jian"'
Sparse-view computed tomography (SVCT) reconstruction aims to acquire CT images based on sparsely-sampled measurements. It allows the subjects exposed to less ionizing radiation, reducing the lifetime risk of developing cancers. Recent researches emp
Externí odkaz:
http://arxiv.org/abs/2406.14976
Text-to-3D generation aims to create 3D assets from text-to-image diffusion models. However, existing methods face an inherent bottleneck in generation quality because the widely-used objectives such as Score Distillation Sampling (SDS) inappropriate
Externí odkaz:
http://arxiv.org/abs/2406.14964
Diffusion model is a promising approach to image generation and has been employed for Pose-Guided Person Image Synthesis (PGPIS) with competitive performance. While existing methods simply align the person appearance to the target pose, they are pron
Externí odkaz:
http://arxiv.org/abs/2402.18078
Emotional Voice Conversion aims to manipulate a speech according to a given emotion while preserving non-emotion components. Existing approaches cannot well express fine-grained emotional attributes. In this paper, we propose an Attention-based Inter
Externí odkaz:
http://arxiv.org/abs/2312.17508
Universal domain adaptation (UniDA) is a practical but challenging problem, in which information about the relation between the source and the target domains is not given for knowledge transfer. Existing UniDA methods may suffer from the problems of
Externí odkaz:
http://arxiv.org/abs/2312.07871
Contrastive learning (CL) has become the de-facto learning paradigm in self-supervised learning on graphs, which generally follows the "augmenting-contrasting" learning scheme. However, we observe that unlike CL in computer vision domain, CL in graph
Externí odkaz:
http://arxiv.org/abs/2306.09614