# Diagnosing Rarity in Human-Object Interaction Detection

arXiv: https://arxiv.org/abs/2006.05728 · HTML: https://mlsanity.com/paper/2006.05728/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jun 2020.

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

- [Diagnosing Human-object Interaction Detectors](https://mlsanity.com/paper/2308.08529/) (2023)
- [An Image-like Diffusion Method for Human-Object Interaction Detection](https://mlsanity.com/paper/2503.18134/) (2025)
- [B-RIGHT: Benchmark Re-evaluation for Integrity in Generalized Human-Object Interaction Testing](https://mlsanity.com/paper/2501.16724/) (2025)

## Abstract (arXiv)

Human-object interaction (HOI) detection is a core task in computer vision. The goal is to localize all human-object pairs and recognize their interactions. An interaction defined by a <verb, noun> tuple leads to a long-tailed visual recognition challenge since many combinations are rarely represented. The performance of the proposed models is limited especially for the tail categories, but little has been done to understand the reason. To that end, in this paper, we propose to diagnose rarity in HOI detection. We propose a three-step strategy, namely Detection, Identification and Recognition where we carefully analyse the limiting factors by studying state-of-the-art models. Our findings indicate that detection and identification steps are altered by the interaction signals like occlusion and relative location, as a result limiting the recognition accuracy.