Natural Language Person Retrieval

Abstract

Following the recent progress in image classification and image captioning using deep learning, we developed a novel person retrieval system using natural language, which to our knowledge is first of its kind. Our system employs a state-of-the-art deep learning based natural language object retrieval framework to detect and retrieve people in images. Quantitative experimental results show significant improvement over state-of-the-art meth- ods for generic object retrieval. This line of research provides great advantages for searching large amounts of video surveil- lance footage and it can also be utilized in other domains, such as human-robot interaction.

Cite

Text

Zhou and Yu. "Natural Language Person Retrieval." AAAI Conference on Artificial Intelligence, 2017. doi:10.1609/AAAI.V31I1.11083

Markdown

[Zhou and Yu. "Natural Language Person Retrieval." AAAI Conference on Artificial Intelligence, 2017.](https://mlanthology.org/aaai/2017/zhou2017aaai-natural/) doi:10.1609/AAAI.V31I1.11083

BibTeX

@inproceedings{zhou2017aaai-natural,
  title     = {{Natural Language Person Retrieval}},
  author    = {Zhou, Tao and Yu, Jie},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2017},
  pages     = {5023-5024},
  doi       = {10.1609/AAAI.V31I1.11083},
  url       = {https://mlanthology.org/aaai/2017/zhou2017aaai-natural/}
}