Image Captioning with Deep Bidirectional LSTMs

Understand

This work presents an end-to-end trainable deep bidirectional LSTM (Long-Short Term Memory) model for image captioning.

• Our model builds on a deep convolutional neural network (CNN) and two separate LSTM networks.
• It is capable of learning long term visual-language interactions by making use of history and future context information at high level semantic space.
• Two novel deep bidirectional variant models, in which we increase the depth of nonlinearity transition in different way, are proposed to learn hierarchical visual-language embeddings.