HICO: A Benchmark for Recognizing Human-Object Interactions in Images

Abstract

We introduce a new benchmark "Humans Interacting with Common Objects" (HICO) for recognizing human-object interactions (HOI). We demonstrate the key features of HICO: a diverse set of interactions with common object categories, a list of well-defined, sense-based HOI categories, and an exhaustive labeling of co-occurring interactions with an object category in each image. We perform an in-depth analysis of representative current approaches and show that DNNs enjoy a significant edge. In addition, we show that semantic knowledge can significantly improve HOI recognition, especially for uncommon categories.

Cite

Text

Chao et al. "HICO: A Benchmark for Recognizing Human-Object Interactions in Images." International Conference on Computer Vision, 2015. doi:10.1109/ICCV.2015.122

Markdown

[Chao et al. "HICO: A Benchmark for Recognizing Human-Object Interactions in Images." International Conference on Computer Vision, 2015.](https://mlanthology.org/iccv/2015/chao2015iccv-hico/) doi:10.1109/ICCV.2015.122

BibTeX

@inproceedings{chao2015iccv-hico,
  title     = {{HICO: A Benchmark for Recognizing Human-Object Interactions in Images}},
  author    = {Chao, Yu-Wei and Wang, Zhan and He, Yugeng and Wang, Jiaxuan and Deng, Jia},
  booktitle = {International Conference on Computer Vision},
  year      = {2015},
  doi       = {10.1109/ICCV.2015.122},
  url       = {https://mlanthology.org/iccv/2015/chao2015iccv-hico/}
}