SGE NET: VIDEO OBJECT DETECTION WITH SQUEEZED GRU AND INFORMATION ENTROPY MAP

Rui Su*, Wenjing Huang, Haoyu Ma, Xiaowei Song, Jinglu Hu

*この研究の対応する著者

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

Recently, deep learning based video object detection has attracted more and more attention. Compared with object detection of static images, video object detection is more challenging due to the motion of objects, while providing rich temporal information. The RNN-based algorithm is an effective way to enhance detection performance in videos with temporal information. However, most studies in this area only focus on accuracy while ignoring the calculation cost and the number of parameters. In this paper, we propose an efficient method that combines channel-reduced convolutional GRU (Squeezed GRU), and Information Entropy map for video object detection (SGE-Net). The experimental results validate the accuracy improvement, computational savings of the Squeezed GRU, and superiority of the information entropy attention mechanism on the classification performance. The mAP has increased by 3.7 contrasted with the baseline, and the number of parameters has decreased from 6.33 million to 0.67 million compared with the standard GRU.

本文言語English
ホスト出版物のタイトル2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings
出版社IEEE Computer Society
ページ689-693
ページ数5
ISBN(電子版)9781665441155
DOI
出版ステータスPublished - 2021
イベント2021 IEEE International Conference on Image Processing, ICIP 2021 - Anchorage, United States
継続期間: 2021 9月 192021 9月 22

出版物シリーズ

名前Proceedings - International Conference on Image Processing, ICIP
2021-September
ISSN(印刷版)1522-4880

Conference

Conference2021 IEEE International Conference on Image Processing, ICIP 2021
国/地域United States
CityAnchorage
Period21/9/1921/9/22

ASJC Scopus subject areas

  • ソフトウェア
  • コンピュータ ビジョンおよびパターン認識
  • 信号処理

フィンガープリント

「SGE NET: VIDEO OBJECT DETECTION WITH SQUEEZED GRU AND INFORMATION ENTROPY MAP」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル