Semantic segmentation has a broad range of applications in a variety of domains including
land coverage analysis, autonomous driving, and medical image analysis. Convolutional …

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 …

We propose MinVIS, a minimal video instance segmentation (VIS) framework that achieves
state-of-the-art VIS performance with neither video-based architectures nor training …

Transformer models have shown great success handling long-range interactions, making
them a promising tool for modeling video. However, they lack inductive biases and scale …

We introduce a novel paradigm for offline Video Instance Segmentation (VIS), based on the
hypothesis that explicit object-oriented information can be a strong clue for understanding …

Video segmentation aims to segment and track every pixel in diverse scenarios accurately.
In this paper, we present Tube-Link, a versatile framework that addresses multiple core tasks …

The discrimination of instance embeddings plays a vital role in associating instances across
time for online video instance segmentation (VIS). Instance embedding learning is directly …

Existing Siamese tracking methods, which are built on pair-wise matching between two
single frames, heavily rely on additional sophisticated mechanism to exploit temporal …

Referring video object segmentation aims to segment a referent throughout a video
sequence according to a natural language expression. It requires aligning the natural …

The handling of long videos with complex and occluded sequences has recently emerged
as a new challenge in the video instance segmentation (VIS) community. However, existing …