Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

universal HOI detector

A universal HOI detector is a computer vision framework designed to localize and classify human-object interactions across open-world and open-vocabulary scenarios rather than a fixed set of predefined categories. While standard human-object interaction detection is restricted to recognizing specific, pre-annotated triplets of humans, verbs, and objects, a universal detector generalizes to arbitrary interactions by leveraging pre-trained vision-language foundation models and semantic prompts. It aligns visual representations of human and object pairs with rich linguistic descriptions, enabling the recognition of complex, zero-shot, or previously unseen relational behaviors across diverse real-world scenes.

1 item

Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models

Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models

Yichao Cao, Qingfei Tang, Xiu Su, Song Chen, Shan You, Xiaobo Lu, Chang Xu

OrganizationsNanjing Enbo Tech.SenseTimeSoutheast UniversityUniversity of Sydney

Why you should read this

Proposes UniHOI, a framework that integrates vision-language foundation models with language-model-generated knowledge via spatial prompt learning to advance open-world and zero-shot human-object interaction detection.

Human-object interaction (HOI) detection aims to comprehend the intricate relationships between humans and objects, predicting < human, action, object > triplets, and serving as the foundation for numerous computer vision tasks. The complexity and diversity of human-object interactions in the real world, however, pose significant challenges for both annotation and recognition, particularly in recognizing interactions within an open world context. This study explores the universal interaction recognition in an open-world setting through the use of Vision-Language (VL) foundation models and large language models (LLMs). The proposed method is dubbed as UniHOI. We conduct a deep analysis of the three hierarchical features inherent in visual HOI detectors and propose a method for high-level relation extraction aimed at VL foundation models, which we call HO prompt-based learning. Our design includes an HO Prompt-guided Decoder (HOPD), facilitates the association of high-level relation representations in the foundation model with various HO pairs within the image. Furthermore, we utilize a LLM (i.e. GPT) for interaction interpretation, generating a richer linguistic understanding for complex HOIs. For open-category interaction recognition, our method supports either of two input types: interaction phrase or interpretive sentence. Our efficient architecture design and learning methods effectively unleash the potential of the VL foundation models and LLMs, allowing UniHOI to surpass all existing methods with a substantial margin, under both supervised and zero-shot settings. The code and pre-trained weights are available at: https://github.com/Caoyichao/UniHOI.

Added

2026-09-26