no code implementations • 11 May 2024 • Volodymyr Fedynyak, Yaroslav Romanus, Oles Dobosevych, Igor Babin, Roman Riazantsev
Namely, we focus on integrating scene global motion knowledge to improve large-scale semi-supervised Video Object Segmentation.
no code implementations • 11 May 2024 • Volodymyr Fedynyak, Yaroslav Romanus, Bohdan Hlovatskyi, Bohdan Sydor, Oles Dobosevych, Igor Babin, Roman Riazantsev
For short-term local propagation, we propose a novel attention mechanism ADVA (Adaptive Deformable Video Attention), allowing the adaption of similarity search region to query-specific semantic features, which ensures robust tracking of complex shape and scale changes.
1 code implementation • CVPR 2022 • Ruslan Partsey, Erik Wijmans, Naoki Yokoyama, Oles Dobosevych, Dhruv Batra, Oleksandr Maksymets
However, for PointNav in a realistic setting (RGB-D and actuation noise, no GPS+Compass), this is an open question; one we tackle in this paper.
1 code implementation • 19 Apr 2022 • Ostap Viniavskyi, Mariia Dobko, Dmytro Mishkin, Oles Dobosevych
We present OpenGlue: a free open-source framework for image matching, that uses a Graph Neural Network-based matcher inspired by SuperGlue \cite{sarlin20superglue}.
1 code implementation • 5 Jan 2022 • Taras Rumezhak, Oles Dobosevych, Rostyslav Hryniv, Vladyslav Selotkin, Volodymyr Karpiv, Mykola Maksymenko
3D scanning is a complex multistage process that generates a point cloud of an object typically containing damaged parts due to occlusions, reflections, shadows, scanner motion, specific properties of the object surface, imperfect reconstruction algorithms, etc.
2 code implementations • 17 Nov 2020 • Yaroslava Lochman, Oles Dobosevych, Rostyslav Hryniv, James Pritts
This paper proposes minimal solvers that use combinations of imaged translational symmetries and parallel scene lines to jointly estimate lens undistortion with either affine rectification or focal length and absolute orientation.
no code implementations • 17 Oct 2020 • Yunchao Wei, Shuai Zheng, Ming-Ming Cheng, Hang Zhao, LiWei Wang, Errui Ding, Yi Yang, Antonio Torralba, Ting Liu, Guolei Sun, Wenguan Wang, Luc van Gool, Wonho Bae, Junhyug Noh, Jinhwan Seo, Gunhee Kim, Hao Zhao, Ming Lu, Anbang Yao, Yiwen Guo, Yurong Chen, Li Zhang, Chuangchuang Tan, Tao Ruan, Guanghua Gu, Shikui Wei, Yao Zhao, Mariia Dobko, Ostap Viniavskyi, Oles Dobosevych, Zhendong Wang, Zhenyuan Chen, Chen Gong, Huanqing Yan, Jun He
The purpose of the Learning from Imperfect Data (LID) workshop is to inspire and facilitate the research in developing novel approaches that would harness the imperfect data and improve the data-efficiency during training.
1 code implementation • 1 Jul 2020 • Ostap Viniavskyi, Mariia Dobko, Oles Dobosevych
First, we generate pseudo segmentation labels of abnormal regions in the training images through a supervised classification model enhanced with a regularization procedure.
no code implementations • 13 Jun 2020 • Mariia Dobko, Ostap Viniavskyi, Oles Dobosevych
We propose a novel approach to weakly supervised semantic segmentation, which consists of three consecutive steps.
1 code implementation • 23 Jan 2020 • Mariia Dobko, Bohdan Petryshak, Oles Dobosevych
For stenosis score classification, the method shows improved performance comparing to previous works, achieving 80% accuracy on the patient level.
no code implementations • NeurIPS Workshop Document_Intelligen 2019 • Kostiantyn Liepieshov, Oles Dobosevych
We introduce the largest (among publicly available) dataset for Cyrillic Handwritten Text Recognition and the first dataset for Cyrillic Text in the Wild Recognition, as well as suggest a method for recognizing Cyrillic Handwritten Text and Text in the Wild.