285 citations · 1.2k across the 56 of their papers we have counts for
57 papers
InstMove: Instance Motion for Object-centric Video Segmentation
Qihao Liu, Junfeng Wu, Yi Jiang +3
Despite significant efforts, cutting-edge video segmentation methods still remain sensitive to occlusion and rapid movement, due to their reliance on the appearance of objects in t…
SRFormerV2: Taking a Closer Look at Permuted Self-Attention for Image Super-Resolution
Yupeng Zhou, Zhen Li, Chun-Le Guo +3
Previous works have shown that increasing the window size for Transformer-based image super-resolution models (e.g., SwinIR) can significantly improve the model performance. Still,…
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
Henghui Ding, Chang Liu, Shuting He +3
Video object segmentation (VOS) aims at segmenting a particular object throughout the entire video clip sequence. The state-of-the-art VOS methods have achieved excellent performan…
The Runner-up Solution for YouTube-VIS Long Video Challenge 2022
Junfeng Wu, Yi Jiang, Qihao Liu +2
This technical report describes our 2nd-place solution for the ECCV 2022 YouTube-VIS Long Video Challenge. We adopt the previously proposed online video instance segmentation metho…
Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation
Qihao Liu, Yi Zhang, Song Bai +1
Occlusion poses a great threat to monocular multi-person 3D human pose estimation due to large variability in terms of the shape, appearance, and position of occluders. While exist…
In Defense of Online Models for Video Instance Segmentation
Junfeng Wu, Qihao Liu, Yi Jiang +3
In recent years, video instance segmentation (VIS) has been largely advanced by offline models, while online models gradually attracted less attention possibly due to their inferio…