activity
20172023
most citedPoNA: Pose-guided Non-local Attention for Human Pose Transfer

61 citations · 276 across the 28 of their papers we have counts for

collaborators
Showing cs.CVShow all

20 papers · 1 filter

cs.CV2023★ 1 cited

Generating Animatable 3D Cartoon Faces from Single Portraits

Chuanyu Pan, Guowei Yang, Taijiang Mu +1

With the booming of virtual reality (VR) technology, there is a growing need for customized 3D avatars. However, traditional methods for 3D avatar modeling are either time-consumin…

cs.CV2023★ 2 cited

Towards Artistic Image Aesthetics Assessment: a Large-scale Dataset and a New Method

Ran Yi, Haoyuan Tian, Zhihao Gu +2

Image aesthetics assessment (IAA) is a challenging task due to its highly subjective nature. Most of the current studies rely on large-scale datasets (e.g., AVA and AADB) to learn…

cs.CV2022

Playing Lottery Tickets in Style Transfer Models

Meihao Kong, Jing Huo, Wenbin Li +3

Style transfer has achieved great success and attracted a wide range of attention from both academic and industrial communities due to its flexible application scenarios. However,…

cs.CV2022★ 22 cited

Quality Metric Guided Portrait Line Drawing Generation from Unpaired Training Data

Ran Yi, Yong-Jin Liu, Yu-Kun Lai +1

Face portrait line drawing is a unique style of art which is highly abstract and expressive. However, due to its high semantic constraints, many existing methods learn to generate…

cs.CV2022★ 1 cited

MuSCLe: A Multi-Strategy Contrastive Learning Framework for Weakly Supervised Semantic Segmentation

Kunhao Yuan, Gerald Schaefer, Yu-Kun Lai +4

Weakly supervised semantic segmentation (WSSS) has gained significant popularity since it relies only on weak labels such as image level annotations rather than pixel level annotat…

cs.CV2022★ 55 cited

Audio-Driven Talking Face Video Generation with Dynamic Convolution Kernels

Zipeng Ye, Mengfei Xia, Ran Yi +5

In this paper, we present a dynamic convolution kernel (DCK) strategy for convolutional neural networks. Using a fully convolutional network with the proposed DCKs, high-quality ta…