Training data for video segmentation are expensive to annotate. This imp...
3D-aware GANs offer new capabilities for creative content editing, such ...
The tracking-by-detection paradigm today has become the dominant method ...
Scaling object taxonomies is one of the important steps toward a robust
...
Recently, handling long videos of complex and occluded sequences has eme...
Recently, memory-based approaches show promising results on semi-supervi...
Recent studies made great progress in video matting by extending the suc...
The key to video inpainting is to use correlation information from as ma...
We introduce a novel paradigm for offline Video Instance Segmentation (V...
Recently, both long-tailed recognition and object tracking have made gre...
For online video instance segmentation (VIS), fully utilizing the inform...
We present Hierarchical Memory Matching Network (HMMN) for semi-supervis...
We propose a novel end-to-end solution for video instance segmentation (...
In this paper, we propose a novel learning-based polygonal point set tra...
We extend panoptic segmentation to the open-world and introduce an open-...
Panoptic segmentation, which is a novel task of unifying instance
segmen...
We propose an attention-based networks for transferring motions between
...
Video super-resolution (VSR) and frame interpolation (FI) are traditiona...
We propose a novel memory-based tracker via part-level dense memory and
...
With more advanced deep network architectures and learning schemes such ...
We present a novel deep learning based algorithm for video inpainting. V...
We propose the onion-peel networks for video completion. Given a set of
...
We present a deep learning method for the interactive video object
segme...
We propose a novel solution for semi-supervised video object segmentatio...
Computational color constancy refers to the problem of computing the
ill...