Projection of Different Encoders Into the Shared Embedding Space

Student: Natalya Ilina

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

Educational Programme: Master of Computer Vision (Master)

Year of Graduation: 2024

In this study, two prevalent techniques for constructing multimodal data representations - late fusion and early fusion - were examined and compared in classification tasks, with a focus on different data types such as texts and images. The study also introduced a model that is intermediate between late and early fusion - middle fusion. The experiments were carried out using the COCO and MMIMDB datasets, revealing the importance of a data fusion strategy in enhancing the efficiency of multimodal models.

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