Techniques are provided for training and operation of a topic-guided image captioning system. A methodology implementing the techniques according to an embodiment includes generating image feature vectors, for an image to be captioned, based on application of a convolutional neural network (CNN) to the image. The method further includes generating the caption based on application of a recurrent neural network (RNN) to the image feature vectors. The RNN is configured as a long short-term memory (LSTM) RNN. The method further includes training the LSTM RNN with training images and associated training captions. The training is based on a combination of: feature vectors of the training image; feature vectors of the associated training caption; and a multimodal compact bilinear (MCB) pooling of the training caption feature vectors and an estimated topic of the training image. The estimated topic is generated by an application of the CNN to the training image.