March 20, 1940 – May 25, 2015
DATA-DRIVEN ENVIRONMENTALLY RESPONSIVE GRAPHIC DESIGN
2015年马萨诸塞大学达特茅斯艺术学院 MFA 学位创作报告
by Canguo Liu
University of Massachusetts Dartmouth, M.F.A. Thesis 2015
THE ELEMENTS AND INFORMATION MODEL OF THE IMAGE
by Canguo Liu
Beijing Film Academy, M.F.A/M.A Thesis 2010
Semantics, in design, means to understand the subject in all its aspects; to relate the subject to the sender and the receiver in such a way that it makes sense to both. It means to design something that has a meaning, that is not arbitrary, that has a reason for being, something in which every detail carries the meaning or has a precise purpose aimed at a precise target.
– Massimo Vignelli
Show and Tell: A Neural Image Caption Generator
Automatically describing the content of an image is a fundamental problem in artificial intelligence that connects computer vision and natural language processing. In this paper, we present a generative model based on a deep recurrent architecture that combines recent advances in computer vision and machine translation and that can be used to generate natural sentences describing an image. The model is trained to maximize the likelihood of the target description sentence given the training image. Experiments on several datasets show the accuracy of the model and the fluency of the language it learns solely from image descriptions.