Multi-object tracking is a fundamental vision problem that has been studied for a long time.
As deep learning brings excellent performances to object detection algorithms, Tracking by …

Abstract Human-Object Interaction (HOI) Detection is an important problem to understand
how humans interact with objects. In this paper, we explore Interactiveness Knowledge …

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 …

Instance segmentation requires a large number of training samples to achieve satisfactory
performance and benefits from proper data augmentation. To enlarge the training set and …

Existing image-based activity understanding methods mainly adopt direct map**, ie from
image to activity concepts, which may encounter performance bottleneck since the huge …

Abstract Human-Object Interaction (HOI) detection lies at the core of action understanding.
Besides 2D information such as human/object appearance and locations, 3D pose is also …

Learning methods are challenged when there is not enough labelled data. It gets worse
when the existing learning data have different distributions in different domains. To deal with …

Human parsing is for pixel-wise human semantic understanding. As human bodies are
underlying hierarchically structured, how to model human structures is the central theme in …

In this paper, we propose a novel top-down instance segmentation framework based on
explicit shape encoding, named ESE-Seg. It largely reduces the computational consumption …

Attributes and objects can compose diverse compositions. To model the compositional
nature of these general concepts, it is a good choice to learn them through transformations …