no code implementations • 13 Dec 2019 • Zheng-cong Fei
Recent neural network models for image captioning usually employ an encoder-decoder architecture, where the decoder adopts a recursive sequence decoding way.
no code implementations • 4 Dec 2019 • Zheng-cong Fei
It takes into account the hierarchical interactions between different abstraction levels of visual information in the images and their bounding-boxes.