Explain Images with Multimodal Recurrent Neural Networks · HackerPapers discussions

Explain Images with Multimodal Recurrent Neural Networks — mentioned by nl

Mon, 02 Feb 2015 22:53:17 GMT

There's a difference between the kind of things you are referring to as "projects" and the kind of things Ng is referring to as "tech". A "project" is usually an application of existing technology done in an innovative way. It may well end up being the next Facebook, but it isn't something that usually requires breakthroughs in scientific fields. Ng's (and Baidu's) "tech" is a much more basic level of research. Baidu isn't interested in funding research into translating English into Latin because - while it is novel - it is unlikely to impact 100 million users. OTOH: Chinese/English…

Paper and discussion history. A mention is not an endorsement.

Explain Images with Multimodal Recurrent Neural Networks — mentioned by tfgg

Tue, 18 Nov 2014 15:11:24 GMT

ArXiv abstract links, which are preferable to direct links to the PDF: http://arxiv.org/abs/1411.2539 http://arxiv.org/abs/1410.1090 http://arxiv.org/abs/1411.4389

Paper and discussion history. A mention is not an endorsement.

Explain Images with Multimodal Recurrent Neural Networks — mentioned by karpathy

Tue, 18 Nov 2014 01:24:44 GMT

Hi all, I'm the author on the Stanford article, so I can answer any more detailed/technical questions. The article doesn't mention this, but closely related work I've only very recently become aware of (if anyone is interested) are additionally: From UofT: http://arxiv.org/pdf/1411.2539v1.pdf From Baidu/UCLA: http://arxiv.org/pdf/1410.1090v1.pdf From Google: http://googleresearch.blogspot.com/2014/11/a-picture-is-wort... From Stanford (our work): http://cs.stanford.edu/people/karpathy/deepimagesent/ Edit: And seemingly also from Berkeley http://arxiv.org/pdf/1411.4389v1.pdf At least from my…

Paper and discussion history. A mention is not an endorsement.