We present QueryInst, a new perspective for instance segmentation. QueryInst is a multi-
stage end-to-end system that treats instances of interest as learnable queries, enabling …

Abstract The task of Human-Object Interaction (HOI) detection could be divided into two core
problems, ie, human-object association and interaction understanding. In this paper, we …

Two-stage methods have dominated Human-Object Interaction~(HOI) detection for several
years. Recently, one-stage HOI detection methods have become popular. In this paper, we …

Abstract Human-Object Interaction (HOI) detection is the process of estimating the
interaction between a human and an object in an image. The first attempts at HOI involved …

Abstract Scene Graph Generation (SGG) remains a challenging visual understanding task
due to its compositional property. Most previous works adopt a bottom-up two-stage or a …

Recent state-of-the-art methods for HOI detection typically build on transformer architectures
with two decoder branches, one for human-object pair detection and the other for interaction …

Abstract The task of Human-Object Interaction (HOI) detection targets fine-grained visual
parsing of humans interacting with their environment, enabling a broad range of …

Recent developments in transformer models for visual data have led to significant
improvements in recognition and detection tasks. In particular, using learnable queries in …

Abstract Recent high-performing Human-Object Interaction (HOI) detection techniques have
been highly influenced by Transformer-based object detector (ie, DETR). Nevertheless, most …

Recently, the DETR framework has emerged as the dominant approach for human--object
interaction (HOI) research. In particular, two-stage transformer-based HOI detectors are …