We introduce a novel method using a new generative model that automatically learns
effective representations of the target and background appearance to detect, segment and …

Video instance segmentation (VIS) is a new and critical task in computer vision. To date, top-
performing VIS methods extend the two-stage Mask R-CNN by adding a tracking branch …

This paper investigates the principles of embedding learning to tackle the challenging semi-
supervised video object segmentation. Different from previous practices that only explore the …

In this article, we introduce SiamMask, a framework to perform both visual object tracking
and video object segmentation, in real-time, with the same simple method. We improve the …

This paper investigates the principles of embedding learning to tackle the challenging semi-
supervised video object segmentation. Unlike previous practices that focus on exploring the …

Modeling temporal visual context across frames is critical for video instance segmentation
(VIS) and other video understanding tasks. In this paper, we propose a fast online VIS model …

Zero-shot semantic segmentation aims to recognize the semantics of pixels from unseen
categories with zero training samples. Previous practice [1] proposed to train the classifiers …

Modern one-stage video instance segmentation networks suffer from two limitations. First,
convolutional features are neither aligned with anchor boxes nor with ground-truth bounding …

Existing methods for instance segmentation in videos typically involve multi-stage pipelines
that follow the tracking-by-detection paradigm and model a video clip as a sequence of …

In this paper, we investigate how to achieve a high-performance yet lightweight
segmentation network for real-time applications. By analyzing three typical segmentation …