Skip to main content

Makale: Deep Fragment Embeddings for Bidirectional Image-Sentence Mapping

We train a multi-modal embedding to associate fragments of images (objects) and sentences (noun and verb phrases) with a structured, max-margin objective. Our model enables efficient and interpretible retrieval of images from sentence descriptions (and vice versa).

Çalışma Eki

Ferhat Kurt

NVIDIA Deep Learning Institute Sertifikalı eğitmen.

Bir Cevap Yazın

This site uses Akismet to reduce spam. Learn how your comment data is processed.

%d blogcu bunu beğendi: