Image Captioning

Student: Durinov Mikhail

Supervisor: Ivan Grechikhin

Faculty: Faculty of Informatics, Mathematics, and Computer Science (HSE Nizhny Novgorod)

Educational Programme: Applied Mathematics and Information Science (Bachelor)

Final Grade: 8

Year of Graduation: 2019

This paper discusses one of the actual problems of machine learning - Image captioning. This paper studies the current state of the art solutions based on the combination of two types of neural networks, convolutional and recurrent. Several attempts have been made to improve the quality of the model for solving this problem, by means of changing the architecture of convolutional and recurrent neural networks. A number of experiments were carried out to check the viability of these changes. The relevance of this work is due to the fact that a high-quality solution of such a task can help people in many areas of life, namely in building autopilots, helping blind people and interpreting medical tests such as ultrasound and MRI

Full text (added May 23, 2019)

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses