4 papers
Un-Doubling Diffusion: LLM-guided Disambiguation of Homonym Duplication
Evgeny Kaskov, Elizaveta Petrova, Petr Surovtsev +4
Homonyms are words with identical spelling but distinct meanings, which pose challenges for many generative models. When a homonym appears in a prompt, diffusion models may generat…
Training Strategies for Isolated Sign Language Recognition
Karina Kvanchiani, Roman Kraynov, Elizaveta Petrova +3
Accurate recognition and interpretation of sign language are crucial for enhancing communication accessibility for deaf and hard of hearing individuals. However, current approaches…
Bukva: Russian Sign Language Alphabet
Karina Kvanchiani, Petr Surovtsev, Alexander Nagaev +2
This paper investigates the recognition of the Russian fingerspelling alphabet, also known as the Russian Sign Language (RSL) dactyl. Dactyl is a component of sign languages where…
PHNet: Patch-based Normalization for Portrait Harmonization
Karen Efremyan, Elizaveta Petrova, Evgeny Kaskov +1
A common problem for composite images is the incompatibility of their foreground and background components. Image harmonization aims to solve this problem, making the whole image l…