Generating Cross-domain Visual Description via Adversarial Learning

碩士 === 國立清華大學 === 電機工程學系所 === 105 === Impressive image captioning results are achieved in domains with plenty of training image and sentence pairs (e.g., MSCOCO). However, transferring to a target domain with significant domain shifts but no paired training data (referred to as cross-domain image ca...

Full description

Bibliographic Details
Main Authors: Chen, Tseng-Hung, 陳增鴻
Other Authors: Sun, Min
Format: Others
Language:en_US
Published: 2017
Online Access:http://ndltd.ncl.edu.tw/handle/r8k45f

Similar Items