# Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer

arXiv: https://arxiv.org/abs/2112.01838 · HTML: https://mlsanity.com/paper/2112.01838/

## Key facts

- Cited by 91 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 29 references that are in the map.
- First posted on arXiv 3 Dec 2021.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Learning to Detect Human-Object Interactions](https://mlsanity.com/paper/1702.05448/) (2017)
- [Understanding the Difficulty of Training Transformers](https://mlsanity.com/paper/2004.08249/) (2020)
- [Detecting and Recognizing Human-Object Interactions](https://mlsanity.com/paper/1704.07333/) (2017)
- [Visual Semantic Role Labeling](https://mlsanity.com/paper/1505.04474/) (2015)
- [HOTR: End-to-End Human-Object Interaction Detection with Transformers](https://mlsanity.com/paper/2104.13682/) (2021)
- [Learning Human-Object Interactions by Graph Parsing Neural Networks](https://mlsanity.com/paper/1808.07962/) (2018)
- [QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information](https://mlsanity.com/paper/2103.05399/) (2021)
- [PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection](https://mlsanity.com/paper/1912.12898/) (2019)
- [End-to-End Human Object Interaction Detection with HOI Transformer](https://mlsanity.com/paper/2103.04503/) (2021)
- [Visual Compositional Learning for Human-Object Interaction Detection](https://mlsanity.com/paper/2007.12407/) (2020)
- [DRG: Dual Relation Graph for Human-Object Interaction Detection](https://mlsanity.com/paper/2008.11714/) (2020)
- [VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions](https://mlsanity.com/paper/2003.05541/) (2020)
- [Reformulating HOI Detection as Adaptive Set Prediction](https://mlsanity.com/paper/2103.05983/) (2021)
- [Detailed 2D-3D Joint Representation for Human-Object Interaction](https://mlsanity.com/paper/2004.08154/) (2020)
- [Spatially Conditioned Graphs for Detecting Human-Object Interactions](https://mlsanity.com/paper/2012.06060/) (2020)
- [HOI Analysis: Integrating and Decomposing Human-Object Interaction](https://mlsanity.com/paper/2010.16219/) (2020)
- [Detecting Human-Object Interaction via Fabricated Compositional Learning](https://mlsanity.com/paper/2103.08214/) (2021)
- [Affordance Transfer Learning for Human-Object Interaction Detection](https://mlsanity.com/paper/2104.02867/) (2021)

## Built on by (most cited first, 30 of 91)

- [Panoptic Scene Graph Generation](https://mlsanity.com/paper/2207.11247/) (2022)
- [Exploring Predicate Visual Context in Detecting Human-Object Interactions](https://mlsanity.com/paper/2308.06202/) (2023)
- [RLIPv2: Fast Scaling of Relational Language-Image Pre-training](https://mlsanity.com/paper/2308.09351/) (2023)
- [ViPLO: Vision Transformer based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detection](https://mlsanity.com/paper/2304.08114/) (2023)
- [Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memory](https://mlsanity.com/paper/2309.03696/) (2023)
- [Knowledge Composition using Task Vectors with Learned Anisotropic Scaling](https://mlsanity.com/paper/2407.02880/) (2024)
- [Relational Context Learning for Human-Object Interaction Detection](https://mlsanity.com/paper/2304.04997/) (2023)
- [Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models](https://mlsanity.com/paper/2311.03799/) (2023)
- [EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection](https://mlsanity.com/paper/2410.23904/) (2024)
- [Exploring Conditional Multi-Modal Prompts for Zero-shot HOI Detection](https://mlsanity.com/paper/2408.02484/) (2024)
- [Neural-Logic Human-Object Interaction Detection](https://mlsanity.com/paper/2311.09817/) (2023)
- [Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection](https://mlsanity.com/paper/2404.06194/) (2024)
- [CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection](https://mlsanity.com/paper/2302.06294/) (2023)
- [Boosting Human-Object Interaction Detection with Text-to-Image Diffusion Model](https://mlsanity.com/paper/2305.12252/) (2023)
- [Category Query Learning for Human-Object Interaction Classification](https://mlsanity.com/paper/2303.14005/) (2023)
- [Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions](https://mlsanity.com/paper/2311.17048/) (2023)
- [Learning from Observer Gaze:Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognition](https://mlsanity.com/paper/2405.09931/) (2024)
- [Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models](https://mlsanity.com/paper/2410.20155/) (2024)
- [Exploiting Multimodal Synthetic Data for Egocentric Human-Object Interaction Detection in an Industrial Scenario](https://mlsanity.com/paper/2306.12152/) (2023)
- [Nonverbal Interaction Detection](https://mlsanity.com/paper/2407.08133/) (2024)
- [Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection](https://mlsanity.com/paper/2307.13529/) (2023)
- [Locality-Aware Zero-Shot Human-Object Interaction Detection](https://mlsanity.com/paper/2505.19503/) (2025)
- [HOLa: Zero-Shot HOI Detection with Low-Rank Decomposed VLM Feature Adaptation](https://mlsanity.com/paper/2507.15542/) (2025)
- [Egocentric Human-Object Interaction Detection Exploiting Synthetic Data](https://mlsanity.com/paper/2204.07061/) (2022)
- [Weakly-supervised HOI Detection via Prior-guided Bi-level Representation Learning](https://mlsanity.com/paper/2303.01313/) (2023)
- [Diagnosing Human-object Interaction Detectors](https://mlsanity.com/paper/2308.08529/) (2023)
- [DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation](https://mlsanity.com/paper/2403.14886/) (2024)
- [Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection](https://mlsanity.com/paper/2403.17709/) (2024)
- [Unseen No More: Unlocking the Potential of CLIP for Generative Zero-shot HOI Detection](https://mlsanity.com/paper/2408.05974/) (2024)
- [Distance Matters in Human-Object Interaction Detection](https://mlsanity.com/paper/2207.01869/) (2022)

## Abstract (arXiv)

Recent developments in transformer models for visual data have led to significant improvements in recognition and detection tasks. In particular, using learnable queries in place of region proposals has given rise to a new class of one-stage detection models, spearheaded by the Detection Transformer (DETR). Variations on this one-stage approach have since dominated human-object interaction (HOI) detection. However, the success of such one-stage HOI detectors can largely be attributed to the representation power of transformers. We discovered that when equipped with the same transformer, their two-stage counterparts can be more performant and memory-efficient, while taking a fraction of the time to train. In this work, we propose the Unary-Pairwise Transformer, a two-stage detector that exploits unary and pairwise representations for HOIs. We observe that the unary and pairwise parts of our transformer network specialise, with the former preferentially increasing the scores of positive examples and the latter decreasing the scores of negative examples. We evaluate our method on the HICO-DET and V-COCO datasets, and significantly outperform state-of-the-art approaches. At inference time, our model with ResNet50 approaches real-time performance on a single GPU.