TY  - JOUR
SN  - 2169-3536
EP  - 1
A1  - Jamil, Azhar
A1  - Rehman, Saif Ur
A1  - Mahmood, Khalid
A1  - Gracia Villar, Mónica
A1  - Prola, Thomas
A1  - Diez, Isabel De La Torre
A1  - Samad, Md Abdus
A1  - Ashraf, Imran
SP  - 1
AV  - public
KW  - Image captioning
KW  -  deep learning
KW  -  image processing
KW  -  artificial intelligence
Y1  - 2024/02//
TI  - Deep Learning Approaches for Image Captioning: Opportunities, Challenges and Future Potential
JF  - IEEE Access
ID  - uninipr11065
N2  - 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.
UR  - http://doi.org/10.1109/ACCESS.2024.3365528
ER  -