Mining Instance-Centric Vision-Language Contexts for Human-Object Interaction Detection

TL;DR

This paper introduces InCoM-Net, a novel framework that enhances human-object interaction detection by integrating semantic knowledge from vision-language models with instance-specific features for improved contextual reasoning.

Contribution

InCoM-Net uniquely combines semantic priors with instance features through a dual-component system for superior HOI detection performance.

Findings

Achieves state-of-the-art results on HICO-DET and V-COCO benchmarks.

Effectively models intra-instance, inter-instance, and scene-level contexts.

Outperforms previous methods in human-object interaction detection.

Abstract

Human-Object Interaction (HOI) detection aims to localize human-object pairs and classify their interactions from a single image, a task that demands strong visual understanding and nuanced contextual reasoning. Recent approaches have leveraged Vision-Language Models (VLMs) to introduce semantic priors, significantly improving HOI detection performance. However, existing methods often fail to fully capitalize on the diverse contextual cues distributed across the entire scene. To overcome these limitations, we propose the Instance-centric Context Mining Network (InCoM-Net)-a novel framework that effectively integrates rich semantic knowledge extracted from VLMs with instance-specific features produced by an object detector. This design enables deeper interaction reasoning by modeling relationships not only within each detected instance but also across instances and their surrounding scene context. InCoM-Net comprises two core components: Instancecentric Context Refinement (ICR), which separately extracts intra-instance, inter-instance, and global contextual cues from VLM-derived features, and Progressive Context Aggregation (ProCA), which iteratively fuses these multicontext features with instance-level detector features to support high-level HOI reasoning. Extensive experiments on the HICO-DET and V-COCO benchmarks show that InCoM-Net achieves state-of-the-art performance, surpassing previous HOI detection methods. Code is available at https://github.com/nowuss/InCoM-Net.