• 研究課題をさがす
  • 研究者をさがす
  • KAKENの使い方
  1. 課題ページに戻る

2016 年度 実施状況報告書

Fast, effective and robust person re-identification for large-scale real applications

研究課題

研究課題/領域番号 15K16024
研究機関奈良先端科学技術大学院大学

研究代表者

伍 洋  奈良先端科学技術大学院大学, 研究推進機構, 特任助教 (30750559)

研究期間 (年度) 2015-04-01 – 2018-03-31
キーワードPerson re-identification / Metric learning / Deep learning / Dictionary learning / Scalable
研究実績の概要

In this year, we have published 2 journal papers and 1 conference paper, and there are 1 journal paper and 1 conference paper currently under review.

In the paper of "Joint Hierarchical Category Structure Learning and Large Scale Image Classification", we built a novel tree structure model together with deep features for scalable and effective image classification. It is a general model which can be applied to person re-identification too. In another journal paper entitled "Re-identification by Neighborhood Structure Metric Learning" we explored a new metric learning model for person re-identification. We showed an enhanced and more effective learning model in our conference paper.

現在までの達成度 (区分)
現在までの達成度 (区分)

1: 当初の計画以上に進展している

理由

We have made significant progress in the 2nd year on exploring effective and scalable recognition models and we were able to publish 2 journal papers and 1 conference paper, with another 1 journal paper and 1 conference paper submitted for reviewing.

Besides the originally planned model, we were able to explore more promising new models (using end-to-end deep learning), which are presented in our papers under reviewing.

今後の研究の推進方策

Since we have already got much progress on exploring the effectiveness and scalability, we will focus more on the efficiency in the last year, and try to integrate things together. We will also do the planned experiments on transfer learning for testing the generalization ability of our models.

次年度使用額が生じた理由

The planned hardware purchasing plan has been mainly covered by other budgets of our lab. In the 2nd year we didn't have much travelling cost and publication cost,but we have more ongoing work to be published in the last year. So the budget is saved for the last year.

次年度使用額の使用計画

We will have more students working on extending the work and we will publish more papers. So the budget will be used for supporting these students, as well as publishing and presenting our research outcomes.

  • 研究成果

    (4件)

すべて 2017 2016 その他

すべて 国際共同研究 (1件) 雑誌論文 (2件) (うち国際共著 2件、 査読あり 2件、 謝辞記載あり 2件) 学会発表 (1件)

  • [国際共同研究] Xiamen University/Southeast University(China)

    • 国名
      中国
    • 外国機関名
      Xiamen University/Southeast University
  • [雑誌論文] Joint Hierarchical Category Structure Learning and Large Scale Image Classification2017

    • 著者名/発表者名
      Yanyun Qu, Li Lin, Fumin Shen, Chang Lu, Yang Wu, Yuan Xie, Dacheng Tao
    • 雑誌名

      IEEE Transactions on Image Processing

      巻: 印刷中 ページ: 印刷中

    • DOI

      10.1109/TIP.2016.2615423

    • 査読あり / 国際共著 / 謝辞記載あり
  • [雑誌論文] Re-identification by Neighborhood Structure Metric Learning2017

    • 著者名/発表者名
      Wei Li, Yang Wu, Jianqing Li
    • 雑誌名

      Pattern Recognition

      巻: 61 ページ: 327-338

    • DOI

      10.1016/j.patcog.2016.08.001

    • 査読あり / 国際共著 / 謝辞記載あり
  • [学会発表] Dictionary Co-learning for Multiple-shot Person Re-identification2016

    • 著者名/発表者名
      Yang Wu, Dong Yang, Ru Zhou, Dong Wang
    • 学会等名
      Chinese Conference on Biometric Recognition
    • 発表場所
      Chengdu, China
    • 年月日
      2016-10-14 – 2016-10-16

URL: 

公開日: 2018-01-16  

サービス概要 検索マニュアル よくある質問 お知らせ 利用規程 科研費による研究の帰属

Powered by NII kakenhi