神戸大学附属図書館デジタルアーカイブ
入力補助
English
カテゴリ
学内刊行物
ランキング
アクセスランキング
ダウンロードランキング
https://hdl.handle.net/20.500.14094/90004749
このアイテムのアクセス数:
9
件
(
2024-05-08
23:20 集計
)
閲覧可能ファイル
ファイル
フォーマット
サイズ
閲覧回数
説明
90004749 (fulltext)
pdf
3.73 MB
5
メタデータ
ファイル出力
メタデータID
90004749
アクセス権
open access
出版タイプ
Version of Record
タイトル
Uncertainty Flow Facilitates Zero-Shot Multi-Label Learning in Affective Facial Analysis
著者
Bai, Wenjun ; Quan, Changqin ; Luo, Zhiwei
著者名
Bai, Wenjun
著者ID
A1010
研究者ID
1000000749898
KUID
https://kuid-rm-web.ofc.kobe-u.ac.jp/search/detail?systemId=af361d61575aed42520e17560c007669
著者名
Quan, Changqin
全, 昌勤
ゼン, ショウキン
所属機関名
システム情報学研究科
著者名
Luo, Zhiwei
収録物名
Applied Sciences
巻(号)
8(2)
ページ
300-300
出版者
MDPI
刊行日
2018-02-19
公開日
2018-04-05
抄録
To lower the single-label dependency on affective facial analysis, it urges the fruition of multi-label affective learning. The impediment to practical implementation of existing multi-label algorithms pertains to scarcity of scalable multi-label training datasets. To resolve this, an inductive transfer learning based framework, i.e., Uncertainty Flow, is put forward in this research to allow knowledge transfer from a single labelled emotion recognition task to a multi-label affective recognition task. I.e., the model uncertainty-which can be quantified in Uncertainty Flow-is distilled from a single-label learning task. The distilled model uncertainty ensures the later efficient zero-shot multi-label affective learning. On the theoretical perspective, within our proposed Uncertainty Flow framework, the feasibility of applying weakly informative priors, e.g., uniform and Cauchy prior, is fully explored in this research. More importantly, based on the derived weight uncertainty, three sets of prediction related uncertainty indexes, i.e., soft-max uncertainty, pure uncertainty and uncertainty plus are proposed to produce reliable and accurate multi-label predictions. Validated on our manual annotated evaluation dataset, i.e., the multi-label annotated FER2013, our proposed Uncertainty Flow in multi-label facial expression analysis exhibited superiority to conventional multi-label learning algorithms and multi-label compatible neural networks. The success of our proposed Uncertainty Flow provides a glimpse of future in continuous, uncertain, and multi-label affective computing.
キーワード
affective computing
Bayesian neural network
Multiple Label Learning
transfer learning
カテゴリ
システム情報学研究科
学術雑誌論文
権利
©2018 by the authors. Licensee MDPI, Basel, Switzerland.
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
詳細を表示
資源タイプ
journal article
言語
English (英語)
eISSN
2076-3417
OPACで所蔵を検索
CiNiiで学外所蔵を検索
関連情報
DOI
https://doi.org/10.3390/app8020300
ホームへ戻る