@article{uninimx11065,
          author = {Azhar Jamil and Saif Ur Rehman and Khalid Mahmood and M{\'o}nica Gracia Villar and Thomas Prola and Isabel De La Torre Diez and Md Abdus Samad and Imran Ashraf},
           month = {Febrero},
           title = {Deep Learning Approaches for Image Captioning: Opportunities, Challenges and Future Potential},
           pages = {1--1},
            year = {2024},
         journal = {IEEE Access},
        abstract = {Generative intelligence relies heavily on the integration of vision and language. Much of the research has focused on image captioning, which involves describing images with meaningful sentences. Typically, when generating sentences that describe the visual content, a language model and a vision encoder are commonly employed. Because of the incorporation of object areas, properties, multi-modal connections, attentive techniques, and early fusion approaches like bidirectional encoder representations from transformers (BERT), these components have experienced substantial advancements over the years. This research offers a reference to the body of literature, identifies emerging trends in an area that blends computer vision as well as natural language processing in order to maximize their complementary effects, and identifies the most significant technological improvements in architectures employed for image captioning. It also discusses various problem variants and open challenges. This comparison allows for an objective assessment of different techniques, architectures, and training strategies by identifying the most significant technical innovations, and offers valuable insights into the current landscape of image captioning research.},
             url = {http://repositorio.unini.edu.mx/id/eprint/11065/},
        keywords = {Image captioning, deep learning, image processing, artificial intelligence}
}