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 …
L Ke, YW Tai, CK Tang - … of the IEEE/CVF conference on …, 2021 - openaccess.thecvf.com
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 …
S Xie, Z Tu - … of the IEEE international conference on …, 2015 - openaccess.thecvf.com
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 …
R Wu, K Cheng, Y Zhao, C Ning… - Advances in Neural …, 2024 - proceedings.neurips.cc
Perceiving and manipulating 3D articulated objects in diverse environments is essential for home-assistant robots. Recent studies have shown that point-level affordance provides …
Z Cao, I Radosavovic… - Proceedings of the …, 2021 - openaccess.thecvf.com
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 …