The understanding of body measurements and body shapes in and between populations is
important and has many applications in medicine, surveying, the fashion industry, fitness …

Deep learning (DL) training algorithms utilize nondeterminism to improve models' accuracy
and training efficiency. Hence, multiple identical training runs (eg, identical training data …

Current semantic segmentation methods focus only on mining" local" context, ie,
dependencies between pixels within individual images, by context-aggregation modules …

This paper studies the problem of learning semantic segmentation from image-level
supervision only. Current popular solutions leverage object localization maps from …

Multi-person pose estimation is fundamental to many computer vision tasks and has made
significant progress in recent years. However, few previous methods explored the problem …

Labeling pixel-level masks for fine-grained semantic segmentation tasks, eg, human
parsing, remains a challenging task. The ambiguous boundary between different semantic …

The design of neural network architectures is an important component for achieving state-of-
the-art performance with machine learning systems across a broad array of tasks. Much …

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

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 …

We present Sapiens, a family of models for four fundamental human-centric vision tasks–2D
pose estimation, body-part segmentation, depth estimation, and surface normal prediction …