Question about usage of RCNN

[Taeksoo Kim]

Hello, I recently read your paper, and very much appreciate about you sharing your codes here.

By the way, on your paper it is indicated that you first extracted top regions of obtained by RCNN and then get the CNN features, however I do not see that object detection part in your implementation. Either in training and test phase, it seems not using object detection functionality. Is it because it still works fine using the holistic image?

Thank you.

[Andrej]

Yeah I didn't fold this code into the code release that is NeuralTalk. I only took a small chunk of my paper, the one that predicts sequence of words for a block of pixels (whole image here).

[mlguy]

@karpathy Hi Andrej, Thank you very much for sharing the code. Do you plan to share the code for the object detection part sometime in the future?

Thanks

[xhl]

@jazzsaxmafia i have same question with you .Have you known how to detect object in images in order to generate a set of h-dimentional representation for every image

[xhl]

@mlguy i have same question with you .Have you known how to detect object in images in order to generate a set of h-dimentional representation for every image

[xhl]

@karpathy Hi Andrej, Thank you very much for sharing the code. Can you share the code for the object detection so that I can generate a set of h-dimentional representation for every image

Thanks