7 papers
ODE-Based Transformer Decoders for Iterative Sign Language Translation
Tuğçe Kızıltepe, Hacer Yalim Keles
Sign language translation has achieved strong results with Transformer architectures, yet recent improvements largely rely on scaling model capacity at the cost of increased comput…
Canonical equivalence relations on
Tan Özalp
Answering a question of Todorcevic, we prove higher-dimensional canonization theorems for the topological Ramsey space . Our results build upon the work…
AV-SLP: Alignment-Aware Variational Modeling for Disentangled Sign Language Production
Sümeyye Meryem TaÅyürek, Enis Mücahid Ä°skender, Hacer Yalim Keles
Building upon recent structural disentanglement frameworks for sign language production, we propose AV-SLP, an alignment-aware variational framework that learns articulator-w…
Meta-Transfer Derm-Diagnosis: Exploring Few-Shot Learning and Transfer Learning for Skin Disease Classification in Long-Tail Distribution
Zeynep Ãzdemir, Hacer Yalim Keles, Ãmer Ãzgür Tanrıöver
Building accurate models for rare skin diseases remains challenging due to the lack of sufficient labeled data and the inherently long-tailed distribution of available samples. The…
Disentangle and Regularize: Sign Language Production with Articulator-Based Disentanglement and Channel-Aware Regularization
Sumeyye Meryem Tasyurek, Tugce Kiziltepe, Hacer Yalim Keles
In this work, we propose DARSLP, a simple gloss-free, transformer-based sign language production (SLP) framework that directly maps spoken-language text to sign pose sequences. We…
CLoE: Curriculum Learning on Endoscopic Images for Robust MES Classification
Zeynep Ozdemir, Hacer Yalim Keles, Omer Ozgur Tanriover
Estimating disease severity from endoscopic images is essential in assessing ulcerative colitis, where the Mayo Endoscopic Subscore (MES) is widely used to grade inflammation. Howe…