Image instance segmentation involves labeling pixels of images with classes and instances,
which is one of the pivotal technologies in many domains, such as natural scenes …

In this work, we introduce Panoptic-DeepLab, a simple, strong, and fast system for panoptic
segmentation, aiming to establish a solid baseline for bottom-up methods that can achieve …

Image segmentation is the task of associating pixels in an image with their respective object
class labels. It has a wide range of applications in many industries including healthcare …

Segmenting highly-overlapping objects is challenging, because typically no distinction is
made between real object contours and occlusion boundaries. Unlike previous two-stage …

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 …

A comprehensive semantic understanding of a scene is important for many applications-but
in what space should diverse semantic information (eg, objects, scene categories, material …

We develop a new edge detection algorithm that addresses two critical issues in this long-
standing vision problem:(1) holistic image training; and (2) multi-scale feature learning. Our …

Perceiving and manipulating 3D articulated objects in diverse environments is essential for
home-assistant robots. Recent studies have shown that point-level affordance provides …

We study the problem of understanding hand-object interactions from 2D images in the wild.
This requires reconstructing both the hand and the object in 3D, which is challenging …

Spatiotemporal data mining (STDM) discovers useful patterns from the dynamic interplay
between space and time. Several available surveys capture STDM advances and report a …