3 accepted papers
In this paper, we present the DeformAvatar, a novel architecture for human avatar re-targetting and rendering based on point clouds. Given the multiple views of a person, we first build a point-model-paired human representation containing a raw point cloud and an optimal parametric model. Then, we r…
A high-quality traumatic brain injury (TBI) dataset is essential to intelligent assisted diagnosis. In this work, we present a new labeled public TBI dataset containing head CT scans and various examination variables. The dataset was collected from 545 patients with moderate to severe TBI and CT ann…
Emotional Text-to-Speech (E-TTS) synthesis has garnered significant attention in recent years due to its potential to revolutionize human-computer interaction. However, current E-TTS approaches often struggle to capture the intricacies of human emotions, primarily relying on oversimplified emotional…