Blog(1)

• Mobile Twin Recognition

  Almost all of us has one or more smartphones, where we keep our personal data such as credit card information, photos, business contacts and so on. It is therefore important to protect this valuable information from unauthorized access.

Research Areas(0)

Publications(64)

• Architecture-Agnostic Test-Time Adaptation via Backprop-Free Embedding Alignment

  AuthorYoung D. Kwon

  PublishedInternational Conference on Learning Representation (ICLR)

  Date2026-04-23

• Normalization is All You Need: Robust Full-Range Contactless SpO2 Estimation Across Users

  AuthorLi Zhu,Mohsin Ahmed,Korosh Vatanparvar,Migyeong Gwak,Nafiul Rashid,Jungmok Bae,Jilong Kuang

  PublishedIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

  Date2024-04-14

• Token Fusion: Bridging the Gap between Token Pruning and Token Merging

  AuthorShangqian Gao,Yen-Chang Hsu,Yilin Shen,Hongxia Jin

  PublishedIEEE Winter Conference on Applications of Computer Vision (WACV)

  Date2024-01-03

View More

News(5)

• Samsung R&D Institute Ukraine's Visual Intelligence Team Wins the Runner-Up Prize at ICCV 2025 Perception Test Challenge

  Samsung R&D Institute Ukraine's Visual Intelligence Team secured the runner-up prize at the ICCV 2025 Perception Test Challenge, a prestigious competition in visual perception. The team excelled in joint object and point tracking, leveraging advanced CNN and transformer models, including SAM2 segmentation tracker and LocoTrack for precise tracking. SRUKR innovative approach achieved high accuracy and robustness, particularly in handling occlusions and small objects.

• [Blog] Task Generalizable Spatial and Texture Aware Image Downsizing Network

  Convolutional neural networks (CNNs) are widely used today in various vision tasks such as classification, detection and segmentation.

• [Blog] Dynamic Multi-scale Network for Dual-pixel Images Defocus Deblurring with Transformer

  Recent works achieve excellent results in defocus deblurring task based on dual-pixel data using convolutional neural network (CNN), while the scarcity of data limits the exploration and attempt of vision transformer in this task.

View More

Others(0)