GitHub - v-dvorak/academic-work: Notes, reports, papers, publications and other stuff that I have accumulated over the years.

Notes, reports, papers, publications and other stuff that I have accumulated over the years ...

Staff Layout Analysis Using the YOLO Platform (publication, 🇬🇧, 2024)

Vojtěch Dvořák, Jan jr. Hajič, and Jiří Mayer. Staff Layout Analysis Using the YOLO Platform. In Jorge Calvo-Zaragoza, Alexander Pacha, and Elona Shatri, editors, Proceedings of the 6th International Workshop on Reading Music Systems, pages 18-22, Online, 2024. https://arxiv.org/abs/2411.15741
In this paper, we bring an update on the performance of OMR layout analysis with the state-of-the-art YOLO platform. Compared to the MeasureDetector (the main publicly available tool for layout analysis), it achieves a similar or better accuracy across both in-domain and out-of-domain tests over three different datasets that we harmonized, it is more than 20x faster, and requires more than 4 times less memory.

lecturer: Jakub Lokoč
some parts are incomplete and unclear
lots of images
introduction to video formats, saving and distribution of multimedia, video compression
similarity search, global image descriptor, local image descriptors
detection of cuts in video
introduction to neural networks, multi-modal search, temporal query
interactive search, visualisation (this chapter is, in my opinion, very well written)

final project for Non-procedural programming course
proposed in 1993, this conjecture states that every pairing in an n-dimensional hypercube graph can be extended to a Hamiltonian cycle
to prove the conjecture for a specific dimension, the program generates the hypercube, finds all possible matchings, and checks if they can be extended to Hamiltonian cycles

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
README.md		README.md