Face Video Retrieval via Deep Learning of Binary Hash Representations

Zhen Dong, Su Jia, Tianfu Wu, Mingtao Pei

AAAI 2016 pp. 3471-3477

doi:10.1609/AAAI.V30I1.10445 /aaai/2016/dong2016aaai-face/

Abstract

Retrieving faces from large mess of videos is an attractive research topic with wide range of applications. Its challenging problems are large intra-class variations, and tremendous time and space complexity. In this paper, we develop a new deep convolutional neural network (deep CNN) to learn discriminative and compact binary representations of faces for face video retrieval. The network integrates feature extraction and hash learning into a unified optimization framework for the optimal compatibility of feature extractor and hash functions. In order to better initialize the network, the low-rank discriminative binary hashing is proposed to pre-learn hash functions during the training procedure. Our method achieves excellent performances on two challenging TV-Series datasets.

PDF AAAI Semantic Scholar

Cite

Text

Dong et al. "Face Video Retrieval via Deep Learning of Binary Hash Representations." AAAI Conference on Artificial Intelligence, 2016. doi:10.1609/AAAI.V30I1.10445

Markdown

[Dong et al. "Face Video Retrieval via Deep Learning of Binary Hash Representations." AAAI Conference on Artificial Intelligence, 2016.](https://mlanthology.org/aaai/2016/dong2016aaai-face/) doi:10.1609/AAAI.V30I1.10445

BibTeX

@inproceedings{dong2016aaai-face,
  title     = {{Face Video Retrieval via Deep Learning of Binary Hash Representations}},
  author    = {Dong, Zhen and Jia, Su and Wu, Tianfu and Pei, Mingtao},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2016},
  pages     = {3471-3477},
  doi       = {10.1609/AAAI.V30I1.10445},
  url       = {https://mlanthology.org/aaai/2016/dong2016aaai-face/}
}