Multiple Object Recognition with Visual Attention — mentioned by radarsat1

Wed, 13 Jan 2016 13:15:06 GMT

This would be quite a cool problem to attack using RNN. Perhaps using an attention-following mechanism like the one used for house numbers [1]. It's fairly well-defined. You would need a ton of example data though. [1] http://arxiv.org/abs/1412.7755

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

Multiple Object Recognition with Visual Attention · HackerPapers discussions

Multiple Object Recognition with Visual Attention — mentioned by radarsat1