{"published":"2016-02-02 12:52:12","blog_url":"https://pdfangeltop1.hatenablog.com/","categories":[],"description":"1 Inroduction In the past, the image caption model can only be trained on paired image-sentence corpora. To address this limitation, the author proposed a Deep Compositional Captioner that can generate descriptions about objects which don't appear in paired corpora ,but are present in unpaired image\u2026","author_name":"PDFangeltop1","height":"190","width":"100%","image_url":"http://cdn-ak.f.st-hatena.com/images/fotolife/P/PDFangeltop1/20160201/20160201171229.png","version":"1.0","provider_name":"Hatena Blog","title":"Deep Compositional Captioning: Describe Novel Object Categories without Paired Training Data","type":"rich","blog_title":"PDFangeltop1\u306e\u65e5\u8a18","author_url":"https://blog.hatena.ne.jp/PDFangeltop1/","provider_url":"https://hatena.blog","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fpdfangeltop1.hatenablog.com%2Fentry%2F2016%2F02%2F02%2F125212\" title=\"Deep Compositional Captioning: Describe Novel Object Categories without Paired Training Data - PDFangeltop1\u306e\u65e5\u8a18\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","url":"https://pdfangeltop1.hatenablog.com/entry/2016/02/02/125212"}