<![CDATA[jiang6869732的博客]]>https://blog.youkuaiyun.com/jiang6869732zh-cnhttps://blog.youkuaiyun.com/<![CDATA[《Multi-level Attention Networks for Visual Question Answering》阅读笔记]]>https://blog.youkuaiyun.com/jiang6869732/article/details/81532197https://blog.youkuaiyun.com/jiang6869732/article/details/81532197jiang6869732Thu, 09 Aug 2018 10:36:42 +0800<![CDATA[转载《Fast R-CNN》的相关原理及解释]]>https://blog.youkuaiyun.com/jiang6869732/article/details/81453952https://blog.youkuaiyun.com/jiang6869732/article/details/81453952jiang6869732Mon, 06 Aug 2018 14:38:26 +0800<![CDATA[《Visual Question Generation as Dual Task of Visual Question Answering》阅读笔记]]>https://blog.youkuaiyun.com/jiang6869732/article/details/81412426https://blog.youkuaiyun.com/jiang6869732/article/details/81412426jiang6869732Sat, 04 Aug 2018 16:31:43 +0800<![CDATA[《MUTAN: Multimodal Tucker Fusion for Visual Question Answering》阅读笔记]]>https://blog.youkuaiyun.com/jiang6869732/article/details/81409668https://blog.youkuaiyun.com/jiang6869732/article/details/81409668jiang6869732Sat, 04 Aug 2018 12:26:06 +0800<![CDATA[《iVQA: Inverse Visual Question Answering》读书笔记]]>https://blog.youkuaiyun.com/jiang6869732/article/details/81392761https://blog.youkuaiyun.com/jiang6869732/article/details/81392761jiang6869732Fri, 03 Aug 2018 18:43:33 +0800