> It is not for lack of trying that all the top papers in visual question answering end up doing this as a classification task. Results are really poor when it is used as RNN generation
I'd be curious to know if you have a reference for this. Given that the answers are one word, a word-level RNN language model output should basically be the same thing as a straight 1000-way softmax.
I'd be curious to know if you have a reference for this. Given that the answers are one word, a word-level RNN language model output should basically be the same thing as a straight 1000-way softmax.