# No-Frills Human-Object Interaction Detection: Factorization, Layout Encodings, and Training Techniques

arXiv: https://arxiv.org/abs/1811.05967 · HTML: https://mlsanity.com/paper/1811.05967/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Nov 2018.

## Built on by (most cited first, 8 of 8)

- [GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection](https://mlsanity.com/paper/2203.13954/) (2022)
- [Glance and Gaze: Inferring Action-aware Points for One-Stage Human-Object Interaction Detection](https://mlsanity.com/paper/2104.05269/) (2021)
- [Interactiveness Field in Human-Object Interactions](https://mlsanity.com/paper/2204.07718/) (2022)
- [Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries](https://mlsanity.com/paper/2105.02170/) (2021)
- [Highlighting Object Category Immunity for the Generalization of Human-Object Interaction Detection](https://mlsanity.com/paper/2202.09492/) (2022)
- [Human-Object Interaction Detection via Weak Supervision](https://mlsanity.com/paper/2112.00492/) (2021)
- [Human Object Interaction Detection using Two-Direction Spatial Enhancement and Exclusive Object Prior](https://mlsanity.com/paper/2105.03089/) (2021)
- [Effective Actor-centric Human-object Interaction Detection](https://mlsanity.com/paper/2202.11998/) (2022)

## Abstract (arXiv)

We show that for human-object interaction detection a relatively simple factorized model with appearance and layout encodings constructed from pre-trained object detectors outperforms more sophisticated approaches. Our model includes factors for detection scores, human and object appearance, and coarse (box-pair configuration) and optionally fine-grained layout (human pose). We also develop training techniques that improve learning efficiency by: (1) eliminating a train-inference mismatch; (2) rejecting easy negatives during mini-batch training; and (3) using a ratio of negatives to positives that is two orders of magnitude larger than existing approaches. We conduct a thorough ablation study to understand the importance of different factors and training techniques using the challenging HICO-Det dataset.