Autogenerate Video Descriptions

Student: Ivan Kovalenok

Educational Programme: Data Science and Business Analytics (Bachelor)

Year of Graduation: 2024

Video-to-text summarization is a significant method for multimedia content analysis that allows to effectively understand and reсieve content from enormous video libraries. In this work, we provide a comprehensive examination of video-to-text summarizing, focusing on the development with afterwards testing of a corresponding pipeline capable of automatically generating informative time-framed textual summaries from video input. Our pipeline combines methods from audio processing, natural language processing and computer vision including important modules or processes like keyframe selection, image captioning, video transcription and text summarization. The pipeline uses the features of multiple modalities to provide coherence and semantic relevance in the final summary.

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