@inproceedings{633a66fd0ce442a2a17f2a070900d436,
title = "UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detection",
abstract = "Recent advances in deep neural networks have achieved significant progress in detecting individual objects from an image. However, object detection is not sufficient to fully understand a visual scene. Towards a deeper visual understanding, the interactions between objects, especially humans and objects are essential. Most prior works have obtained this information with a bottom-up approach, where the objects are first detected and the interactions are predicted sequentially by pairing the objects. This is a major bottleneck in HOI detection inference time. To tackle this problem, we propose UnionDet, a one-stage meta-architecture for HOI detection powered by a novel union-level detector that eliminates this additional inference stage by directly capturing the region of interaction. Our one-stage detector for human-object interaction shows a significant reduction in interaction prediction time (4 × ∼ 14 ×) while outperforming state-of-the-art methods on two public datasets: V-COCO and HICO-DET.",
keywords = "Human-object interaction detection, Object detection, Real-time detection, Visual relationships",
author = "Bumsoo Kim and Taeho Choi and Jaewoo Kang and Kim, {Hyunwoo J.}",
note = "Funding Information: Acknowledgement. This work was supported by the National Research Council of Science & Technology (NST) grant by the Korea government (MSIT)(No.CAP-18-03-ETRI), National Research Foundation of Korea (NRF-2017M3C4A7065887), and Samsung Electronics, Co. Ltd. Publisher Copyright: {\textcopyright} 2020, Springer Nature Switzerland AG.; 16th European Conference on Computer Vision, ECCV 2020 ; Conference date: 23-08-2020 Through 28-08-2020",
year = "2020",
doi = "10.1007/978-3-030-58555-6_30",
language = "English",
isbn = "9783030585549",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "498--514",
editor = "Andrea Vedaldi and Horst Bischof and Thomas Brox and Jan-Michael Frahm",
booktitle = "Computer Vision – ECCV 2020 - 16th European Conference, 2020, Proceedings",
address = "Germany",
}