RNIC-A retrospect network for image captioning

As cross-domain research combining computer vision and natural language processing, the current image captioning mainly considers how to improve visual features; less attention has been paid utilizing inherent properties of boost performance. Facing this challenge, we proposed a textual mechanism, which can obtain semantic relevance between words by scanning all generated words. The retrospect network for (RNIC) in paper aims input prediction process using attention. Concretely, mechanism is applied model simultaneously with provide maximum information required generating captions. In way, our learn collaboratively attend on both features. Moreover, obtained used as basis prediction, so that decoder simulate human system better make predictions based already contents. We evaluate effectiveness COCO datasets achieve superior performance over previous methods.