20 citations · 54 across the 15 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.CV2023
Towards Imbalanced Motion: Part-Decoupling Network for Video Portrait Segmentation
Tianshu Yu, Changqun Xia, Jia Li
Video portrait segmentation (VPS), aiming at segmenting prominent foreground portraits from video frames, has received much attention in recent years. However, simplicity of existi…
cs.CV2023
Rethinking Lightweight Salient Object Detection via Network Depth-Width Tradeoff
Jia Li, Shengye Qiao, Zhirui Zhao +3
Existing salient object detection methods often adopt deeper and wider networks for better performance, resulting in heavy computational burden and slow inference speed. This inspi…