The visual world can be parsimoniously characterized in terms of distinct entities with sparse
interactions. Discovering this compositional structure in dynamic visual scenes has proven …

Video segmentation—partitioning video frames into multiple segments or objects—plays a
critical role in a broad range of practical applications, from enhancing visual effects in movie …

In this paper, we present a novel end-to-end learning neural network, ie, MATNet, for zero-
shot video object segmentation (ZVOS). Motivated by the human visual attention behavior …

We introduce a novel network, called as CO-attention Siamese Network (COSNet), to
address the unsupervised video object segmentation task from a holistic view. We …

How to make a segmentation model efficiently adapt to a specific video as well as online
target appearance variations is a fundamental issue in the field of video object …

Animals have evolved highly functional visual systems to understand motion, assisting
perception even under complex environments. In this paper, we work towards develo** a …

This work proposes a novel attentive graph neural network (AGNN) for zero-shot video
object segmentation (ZVOS). The suggested AGNN recasts this task as a process of iterative …

In this article, we model a set of pixelwise object segmentation tasks—automatic video
segmentation (AVS), image co-segmentation (ICS) and few-shot semantic segmentation …

We introduce an unsupervised, geodesic distance based, salient video object segmentation
method. Unlike traditional methods, our method incorporates saliency as prior for object via …

This paper conducts a systematic study on the role of visual attention in Unsupervised Video
Object Segmentation (UVOS) tasks. By elaborately annotating three popular video …