# Zero-Shot Human-Object Interaction Recognition via Affordance Graphs

arXiv: https://arxiv.org/abs/2009.01039 · HTML: https://mlsanity.com/paper/2009.01039/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Sep 2020.

## Built on by (most cited first, 3 of 3)

- [A Review of Human-Object Interaction Detection](https://mlsanity.com/paper/2408.10641/) (2024)
- [DML-RAM: Deep Multimodal Learning Framework for Robotic Arm Manipulation using Pre-trained Models](https://mlsanity.com/paper/2504.03423/) (2025)
- [Funnel-HOI: Top-Down Perception for Zero-Shot HOI Detection](https://mlsanity.com/paper/2507.12628/) (2025)

## Abstract (arXiv)

We propose a new approach for Zero-Shot Human-Object Interaction Recognition in the challenging setting that involves interactions with unseen actions (as opposed to just unseen combinations of seen actions and objects). Our approach makes use of knowledge external to the image content in the form of a graph that models affordance relations between actions and objects, i.e., whether an action can be performed on the given object or not. We propose a loss function with the aim of distilling the knowledge contained in the graph into the model, while also using the graph to regularise learnt representations by imposing a local structure on the latent space. We evaluate our approach on several datasets (including the popular HICO and HICO-DET) and show that it outperforms the current state of the art.