Interesting. This approach shares a lot of ideas, at the high level, with the approach we're pursuing, that builds a scene graph from the patterns mined from the state of a DeSTIN-like deep NN.... The contextual biasing of object recognition is an important part of our approach and they are doing that too, in their own way...
ben On Sat, Jan 14, 2017 at 10:18 PM, Yuhuang Hu <[email protected]> wrote: > The paper is here: https://arxiv.org/pdf/1701.02426v1.pdf > > Super interesting results, one can take an image and then generate a full > scene graph for inference. > A great step to fix sub-symbolic-symbolic gap. > > Yuhuang. > > -- > You received this message because you are subscribed to the Google Groups > "opencog" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to [email protected]. > To post to this group, send email to [email protected]. > Visit this group at https://groups.google.com/group/opencog. > To view this discussion on the web visit > https://groups.google.com/d/msgid/opencog/3c7646b3-613c-4e80-9fed-df09eeb80984%40googlegroups.com. > For more options, visit https://groups.google.com/d/optout. -- Ben Goertzel, PhD http://goertzel.org “I tell my students, when you go to these meetings, see what direction everyone is headed, so you can go in the opposite direction. Don’t polish the brass on the bandwagon.” – V. S. Ramachandran -- You received this message because you are subscribed to the Google Groups "opencog" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To post to this group, send email to [email protected]. Visit this group at https://groups.google.com/group/opencog. To view this discussion on the web visit https://groups.google.com/d/msgid/opencog/CACYTDBeH4xaUSFEkgTYHdjM3r%3DnEJQTmu3KPcubGWf0GT11c3Q%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
