文字描述生成视频的开源项目

文字condition 视频

Attentive Semantic Video Generation using Captions

Tensorflow implementation for the paper Attentive Semantic Video Generation using Captions by Tanya Marwah*, Gaurav Mittal* and Vineeth N. Balasubramanian accepted at International Conference on Computer Vision 2017 (ICCV 2017) (*Equal Contribution).

Proposed network architecture for attentive semantic video generation with captions.

Results

digit 6 is moving up and down	digit 3 is moving left and right

person 4 is walking left to right

Example of Spatio Temporal Style Transfer

Caption 1: digit 4 is moving up and down Caption 2: digit 4 is moving left and right

Caption 1: digit 4 is moving up and down Caption 2: digit 9 is moving left and right	Caption 1: digit 5 is moving left and right Caption 2: digit 9 is moving up and down

Caption 1: person 10 is walking left to right Caption 2: person 10 is walking right to left

人物行走请阅读原文访问github看原图片

招聘公众号回复招聘