# A Graph-based Interactive Reasoning for Human-Object Interaction Detection

arXiv: https://arxiv.org/abs/2007.06925 · HTML: https://mlsanity.com/paper/2007.06925/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jul 2020.

## Built on by (most cited first, 12 of 12)

- [QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information](https://mlsanity.com/paper/2103.05399/) (2021)
- [GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection](https://mlsanity.com/paper/2203.13954/) (2022)
- [Mining the Benefits of Two-stage and One-stage HOI Detection](https://mlsanity.com/paper/2108.05077/) (2021)
- [HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models](https://mlsanity.com/paper/2303.15786/) (2023)
- [Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection](https://mlsanity.com/paper/2404.06194/) (2024)
- [Iwin: Human-Object Interaction Detection via Transformer with Irregular Windows](https://mlsanity.com/paper/2203.10537/) (2022)
- [Video-based Human-Object Interaction Detection from Tubelet Tokens](https://mlsanity.com/paper/2206.01908/) (2022)
- [HODN: Disentangling Human-Object Feature for HOI Detection](https://mlsanity.com/paper/2308.10158/) (2023)
- [Agglomerative Transformer for Human-Object Interaction Detection](https://mlsanity.com/paper/2308.08370/) (2023)
- [Open-Vocabulary HOI Detection with Interaction-aware Prompt and Concept Calibration](https://mlsanity.com/paper/2508.03207/) (2025)
- [Parallel Reasoning Network for Human-Object Interaction Detection](https://mlsanity.com/paper/2301.03510/) (2023)
- [RR-Net: Injecting Interactive Semantics in Human-Object Interaction Detection](https://mlsanity.com/paper/2104.15015/) (2021)

## Abstract (arXiv)

Human-Object Interaction (HOI) detection devotes to learn how humans interact with surrounding objects via inferring triplets of < human, verb, object >. However, recent HOI detection methods mostly rely on additional annotations (e.g., human pose) and neglect powerful interactive reasoning beyond convolutions. In this paper, we present a novel graph-based interactive reasoning model called Interactive Graph (abbr. in-Graph) to infer HOIs, in which interactive semantics implied among visual targets are efficiently exploited. The proposed model consists of a project function that maps related targets from convolution space to a graph-based semantic space, a message passing process propagating semantics among all nodes and an update function transforming the reasoned nodes back to convolution space. Furthermore, we construct a new framework to assemble in-Graph models for detecting HOIs, namely in-GraphNet. Beyond inferring HOIs using instance features respectively, the framework dynamically parses pairwise interactive semantics among visual targets by integrating two-level in-Graphs, i.e., scene-wide and instance-wide in-Graphs. Our framework is end-to-end trainable and free from costly annotations like human pose. Extensive experiments show that our proposed framework outperforms existing HOI detection methods on both V-COCO and HICO-DET benchmarks and improves the baseline about 9.4% and 15% relatively, validating its efficacy in detecting HOIs.