Get started
Author

Savas Ozkan

Observed name: Ozkan, Savas
ORCID: 0009-0006-0450-0645
Observed ORCID: 0009-0006-0450-0645
OpenAlex ID: A5103889759
Accurate Scene Text Recognition with Efficient Model Scaling and Cloze Self-Distillation
2025 · Andrea Maracani, Savas Ozkan, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 6
PDF
Efficient and Accurate Scene Text Recognition with Cascaded-Transformers
2025 · Savas Ozkan, Andrea Maracani, et al. · ACM Multimedia Systems Conference (MMSys) · 1
Multi-Task Pre-Finetuning of Lightweight Transformer Encoders for Text Classification and NER
2025 · Junyi Zhu, Savas Ozkan, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 1
PDF
Improving Privacy-Utility Trade-Off with Learnable Privacy Mechanism in Machine Learning Tasks
2026 · Savas Ozkan, Sinan Mutlu, et al. · Proceedings - International Conference on Image Processing
DuoMem: Towards Capable On-Device Memory Agents via Dual-Space Distillation
2026 · Hosseini, Peyman, Bohdal, Ondrej, et al. · arXiv (Cornell University)
PDF
Decoding Text Spans for Efficient and Accurate Named-Entity Recognition
2026 · Association for Computational Linguistics 2026, Maracani, Andrea, et al. · Underline Science Inc.
Decoding Text Spans for Efficient and Accurate Named-Entity Recognition
2026 · Maracani, Andrea, Ozkan, Savas, et al. · arXiv (Cornell University)
PDF
Improving Cross-Domain Generalization of Lightweight Transformers for Named Entity Recognition Using Self-Training
2026 · Junyi Zhu, Andrea Maracani, et al. · IEEE International Conference on Acoustics Speech and Signal Processing
Latent Space Orthonormalization for Hyper-Finetuning of Language Models
2026 · Savas Ozkan, Taha Ceritli, et al. · IEEE International Conference on Acoustics Speech and Signal Processing
3D Motion Synthesis from Sparse Tracking with Autoregressive Temporal Windows
2026 · Georgios Fotios Angelis, Savas Ozkan, et al. · IEEE International Conference on Acoustics Speech and Signal Processing
Mem-MLP: Real-Time 3D Human Motion Generation from Sparse Inputs
2026 · Sinan Mutlu, Georgios F. Angelis, et al. · IEEE Winter Conference on Applications of Computer Vision
Geometrically Consistent Multi-view Scene Generation from Freehand Sketches
2026 · Ahmed Bourouis, Savas Ozkan, et al. · Lecture notes in computer science
PDF
Decoding Text Spans for Efficient and Accurate Named-Entity Recognition
2026 · Andrea Maracani, Savas Ozkan, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Guided Model Merging for Hybrid Data Learning: Leveraging Centralized Data to Refine Decentralized Models
2025 · Zhu, Junyi, Yao, Ruicong, et al. · Lirias
Efficient 3D Full-Body Motion Generation from Sparse Tracking Inputs with Temporal Windows
2025 · Angelis, Georgios Fotios, Ozkan, Savas, et al. · arXiv (Cornell University)
PDF
Works count: 15
Citation count: 8
H-index: 1
I10-index:
Year
Topic
Type