ERNet: An Efficient and Reliable Human-Object Interaction Detection Network

Junyi Lim, Vishnu Monn Baskaran, Joanne Mun-Yee Lim, Koksheik Wong, John See, Massimo Tistarelli

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)


Human-Object Interaction (HOI) detection recognizes how persons interact with objects, which is advantageous in autonomous systems such as self-driving vehicles and collaborative robots. However, current HOI detectors are often plagued by model inefficiency and unreliability when making a prediction, which consequently limits its potential for real-world scenarios. In this paper, we address these challenges by proposing ERNet, an end-to-end trainable convolutional-transformer network for HOI detection. The proposed model employs an efficient multi-scale deformable attention to effectively capture vital HOI features. We also put forward a novel detection attention module to adaptively generate semantically rich instance and interaction tokens. These tokens undergo pre-emptive detections to produce initial region and vector proposals that also serve as queries which enhances the feature refinement process in the transformer decoders. Several impactful enhancements are also applied to improve the HOI representation learning. Additionally, we utilize a predictive uncertainty estimation framework in the instance and interaction classification heads to quantify the uncertainty behind each prediction. By doing so, we can accurately and reliably predict HOIs even under challenging scenarios. Experiment results on the HICO-Det, V-COCO, and HOI-A datasets demonstrate that the proposed model achieves state-of-the-art performance in detection accuracy and training efficiency. Codes are publicly available at
Original languageEnglish
Pages (from-to)964-979
Number of pages16
JournalIEEE Transactions on Image Processing
Publication statusPublished - 26 Jan 2023


  • Human-object interaction detection
  • deformable attention
  • transformer
  • uncertainty estimation

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'ERNet: An Efficient and Reliable Human-Object Interaction Detection Network'. Together they form a unique fingerprint.

Cite this