Deep learning techniques have led to remarkable breakthroughs in the field of generic
object detection and have spawned a lot of scene-understanding tasks in recent years …

Abstract We present Open Images V4, a dataset of 9.2 M images with unified annotations for
image classification, object detection and visual relationship detection. The images have a …

Abstract Scene Graph Generation, which generally follows a regular encoder-decoder
pipeline, aims to first encode the visual contents within the given image and then parse them …

Deep learning techniques have led to remarkable breakthroughs in the field of object
detection and have spawned a lot of scene-understanding tasks in recent years. Scene …

Scene graphs are powerful representations that parse images into their abstract semantic
elements, ie, objects and their interactions, which facilitates visual comprehension and …

Abstract General Purpose Vision (GPV) systems are models that are designed to solve a
wide array of visual tasks without requiring architectural changes. Today, GPVs primarily …

We propose a novel approach to animate human hair in a still portrait photo. Existing work
has largely studied the animation of fluid elements such as water and fire. However, hair …

Visual relationship reasoning is a crucial yet challenging task for understanding rich
interactions across visual concepts. For example, a relationship\man, open, door\involves a …

Abstract Visual Relationship Detection (VRD) aims to describe the relationship between two
objects by providing a structural triplet shown as. Existing graph-based methods mainly …

In visual relationship detection, human-notated relationships can be regarded as
determinate relationships. However, there are still large amount of unlabeled data, such as …