Image description is a comprehensive task combining natural language processing and computer vision. This paper proposes a model improved by GRU for the lack of long-term memory due to use of ordinary RNN in m-RNN. The new model can predict the words at the next moment based on the information at the previous moment, and generates a complete image description sentence. Moreover, using the MSCOCO2014 dataset, our model was trained and tested, and the indicators such as BLEU, METEOR and CIDEr are used as evaluation criteria. The experimental comparison with the original model and other models is carried out to further verify the validity of our model.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    An improved Image Description Method Using Recurrent Neural Network with Gated Recurrent Unit


    Contributors:
    Wang, Haiyong (author) / Li, Kezheng (author)


    Publication date :

    2019-10-01


    Size :

    230182 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Minimal gated unit for recurrent neural networks

    Zhou, G. B. / Wu, J. / Zhang, C. L. et al. | British Library Online Contents | 2016


    Vehicle speed prediction using a convolutional neural network combined with a gated recurrent unit with attention

    Zhang, Dongxue / Wang, Zhennan / Jiao, Xiaohong et al. | SAGE Publications | 2025


    Multipath Detection from GNSS Observables Using Gated Recurrent Unit

    Geragersian, Patrick / Petrunin, Ivan / Guo, Weisi et al. | IEEE | 2022