[CV]《Connecting What to Say With Where to Look by Modeling Human Attention Traces》Z Meng, L Yu, N Zhang, T Berg, B Damavandi, V Singh, A Bearman [University of Wisconsin Madison & Facebook AI] (2021) 网页链接 view:网页链接 GitHub:https:// ...
展开
评论
点赞
![[呲牙]](http://lf3-cdn-tos.bytescm.com/obj/static/xitu_juejin_web/img/jj_emoji_2.cd1e2bd.png)
![[流泪]](http://lf3-cdn-tos.bytescm.com/obj/static/xitu_juejin_web/img/jj_emoji_6.dde0d83.png)
![[惊喜]](http://lf3-cdn-tos.bytescm.com/obj/static/xitu_juejin_web/img/jj_emoji_93.5ee641b.png)