activity
20192023
most citedBMN: Boundary-Matching Network for Temporal Action Proposal Generation

73 citations · 196 across the 22 of their papers we have counts for

collaborators
Showing 2021 · cs.CVShow all

6 papers · 2 filters

cs.CV2021★ 1 cited

Paint Transformer: Feed Forward Neural Painting with Stroke Prediction

Songhua Liu, Tianwei Lin, Dongliang He +5

Neural painting refers to the procedure of producing a series of strokes for a given image and non-photo-realistically recreating it using neural networks. While reinforcement lear…

cs.CV2021★ 26 cited

AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer

Songhua Liu, Tianwei Lin, Dongliang He +6

Fast arbitrary neural style transfer has attracted widespread attention from academic, industrial and art communities due to its flexibility in enabling various applications. Exist…

cs.CV2021

Image Inpainting by End-to-End Cascaded Refinement with Mask Awareness

Manyu Zhu, Dongliang He, Xin Li +5

Inpainting arbitrary missing regions is challenging because learning valid features for various masked regions is nontrivial. Though U-shaped encoder-decoder frameworks have been w…

cs.CV2021

NTIRE 2021 Depth Guided Image Relighting Challenge

Majed El Helou, Ruofan Zhou, Sabine Susstrunk +1

Image relighting is attracting increasing interest due to its various applications. From a research perspective, image relighting can be exploited to conduct both image normalizati…

cs.CV2021★ 10 cited

Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer

Tianwei Lin, Zhuoqi Ma, Fu Li +6

Artistic style transfer aims at migrating the style from an example image to a content image. Currently, optimization-based methods have achieved great stylization quality, but exp…

cs.CV2021★ 4 cited

Learning Semantic Person Image Generation by Region-Adaptive Normalization

Zhengyao Lv, Xiaoming Li, Xin Li +4

Human pose transfer has received great attention due to its wide applications, yet is still a challenging task that is not well solved. Recent works have achieved great success to…