Object detection, as of one the most fundamental and challenging problems in computer
vision, has received great attention in recent years. Over the past two decades, we have …

Recent years have witnessed enormous progress in AI-related fields such as computer
vision, machine learning, and autonomous vehicles. As with any rapidly growing field, it …

We propose and study a task we name panoptic segmentation (PS). Panoptic segmentation
unifies the typically distinct tasks of semantic segmentation (assign a class label to each …

Action recognition has typically treated actions and activities as monolithic events that occur
in videos. However, there is evidence from Cognitive Science and Neuroscience that people …

We tackle the challenging problem of human-object interaction (HOI) detection. Existing
methods either recognize the interaction of each human-object pair in isolation or perform …

Non-maximum suppression is an integral part of the object detection pipeline. First, it sorts
all detection boxes on the basis of their scores. The detection box M with the maximum score …

Understanding a visual scene goes beyond recognizing individual objects in isolation.
Relationships between objects also constitute rich semantic information about the scene. In …

Detecting individual pedestrians in a crowd remains a challenging problem since the
pedestrians often gather together and occlude each other in real-world scenarios. In this …

Visual relations, such as" person ride bike" and" bike next to car", offer a comprehensive
scene understanding of an image, and have already shown their great utility in connecting …

This paper develops a novel framework for semantic image retrieval based on the notion of
a scene graph. Our scene graphs represent objects (" man"," boat"), attributes of objects (" …