convnet models 1data augmentation 1dermoscopic imaging 1dialogue systems 1expressive tts 1out-of-domain generalization 1prosody 1russian language 1skin cancer classification 1speech corpus 1
From the 2 of 3 linked papers with an AI index.
3 papers
cs.CV2026
Searching for Robust Augmentations to Improve Out-of-Domain Generalization in Dermoscopic Skin Cancer Classification
Alexander Kozachok, Ilya Latyshev, Evgeny Karpulevich +3
The paper evaluates how different data augmentation strategies, especially photometric transformations and a mixed augmentation policy, can improve the out-of-domain robustness of…
eess.AS2026
Dialogs: a studio-quality expressive conversational Russian speech corpus for dialog assistants
Ilya Shigabeev, Ilya Latyshev
The paper presents Dialogs, a high-quality Russian conversational speech corpus recorded in a studio, featuring expressive prosody, turn‑taking, and emotion/style annotations, and…
cs.CV2026
Cascade Classification of Dermoscopic Images of Skin Neoplasms with Controllable Sensitivity and External Clinical Validation
Elena S. Kozachok, Sergey S. Seregin, Aleksandr V. Kozachok +2
Purpose. To compare deep learning architectures and classification schemes for dermoscopic images of skin neoplasms and assess their generalization on transfer from open internatio…