[Adapt] [Seminar][Generating Image Descriptions]

[zhiyi Luo]

Dear Adapters,

Our seminar will take place today at 4:30p.m. at SEIEE3-528.

I will talk about a new topic I've investigated recently, that is
generating the text descriptions for images. I will mainly focus on
Karpathy's recent work on this area: Deep Visual-Semantic Alignments for
Generating Image Descriptions. Instead of deriving complex formulas for the
deep models, I will show you some vivid results from their approaches.

Hope you enjoy the talk!

Best,
Jessie (Zhiyi Luo)
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20161019/d2b2efb5/attachment.html>