Dimitris Samaras

Stony Brook University — United States

Computer Science · Physical Sciences

54h-index9.8kcitations311works1.62yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Vision and Imaging(48), Face recognition and analysis(43), Visual Attention and Saliency Detection(42), Generative Adversarial Networks and Image Synthesis(33), Advanced Image and Video Retrieval Techniques(31)

Publications311 total

What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards
arXiv (Cornell University)·2025Open Access
Reward Modeling of Goal-directed Gaze Control
2025Open Access
Editorial: Introduction to the Special Section on Best of CVPR'2022
IEEE Transactions on Pattern Analysis and Machine Intelligence·2025
Talking Head Generation via AU-Guided Landmark Prediction
arXiv (Cornell University)·2025Open Access
PathSegDiff: Pathology Segmentation Using Diffusion Model Representations
Lecture notes in computer science·2025
Pathology Image Compression with Pre-trained Autoencoders
Lecture notes in computer science·2025
Label-Efficient Deep Color Deconvolution of Brightfield Multiplex IHC Images
IEEE Transactions on Medical Imaging·2025
Measuring and predicting where and when pathologists focus their visual attention while grading whole slide images of cancer
Medical Image Analysis·2025
Multi-view Gaze Target Estimation
arXiv (Cornell University)·2025Open Access
Measuring and Predicting Where and When Pathologists Focus their Visual Attention while Grading Whole Slide Images of Cancer
arXiv (Cornell University)·2025Open Access
Few-shot Personalized Scanpath Prediction
2025
2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification
2025· 13 cited
ZoomLDM: Latent Diffusion Model for multi-scale image generation
2025· 3 cited
TopoCellGen: Generating Histopathology Cell Topology with a Diffusion Model
2025· 2 cited
Low-Rank Head Avatar Personalization with Registers
arXiv (Cornell University)·2025Open Access
Adaptive Multitask Neural Network for High-Fidelity Wake Flow Modeling of Wind Farms
Energies·2025Open Access
GeoMaNO: Geometric Mamba Neural Operator for Partial Differential Equations
arXiv (Cornell University)·2025Open Access
PathSegDiff: Pathology Segmentation using Diffusion model representations
arXiv (Cornell University)·2025Open Access
Few-shot Personalized Scanpath Prediction
arXiv (Cornell University)·2025Open Access
GECKO: Gigapixel Vision-Concept Contrastive Pretraining in Histopathology
arXiv (Cornell University)·2025Open Access
page 1 of 16Next →

Frequent Co-authors

Minh Hoai(8), Zhixin Shu(6), Nikos Paragios(5), Gregory J. Zelinsky(5), Tomás F. Yago Vicente(4), Hieu Lê(4), Xianfeng Gu(4), Vu Nguyen(3), Zhibo Yang(3), Huidong Liu(3), Yang Wang(3), Dimitris Metaxas(3), Kiwon Yun(2), Jean Honorio(2), Tamara L. Berg(2), Sunil Hadap(2), Eli Shechtman(2), Le Hou(2), Jianyuan Deng(2), Iwao Ojima(2)