Multilabel Deep Visual-Semantic Embedding

Mei Chen Yeh, Yi Nan Li

研究成果: 雜誌貢獻文章同行評審

1 引文 斯高帕斯(Scopus)

摘要

Inspired by the great success from deep convolutional neural networks (CNNs) for single-label visual-semantic embedding, we exploit extending these models for multilabel images. We propose a new learning paradigm for multilabel image classification, in which labels are ranked according to its relevance to the input image. In contrast to conventional CNN models that learn a latent vector representation (i.e., the image embedding vector), the developed visual model learns a mapping (i.e., a transformation matrix) from an image in an attempt to differentiate between its relevant and irrelevant labels. Despite the conceptual simplicity of our approach, the proposed model achieves state-of-the-art results on three public benchmark datasets.

原文英語
文章編號8691414
頁(從 - 到)1530-1536
頁數7
期刊IEEE Transactions on Pattern Analysis and Machine Intelligence
42
發行號6
DOIs
出版狀態已發佈 - 2020 六月 1
對外發佈Yes

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

指紋 深入研究「Multilabel Deep Visual-Semantic Embedding」主題。共同形成了獨特的指紋。

引用此