3 papers
cs.CV2026
Ukrainian Visual Word Sense Disambiguation Benchmark
Yurii Laba, Yaryna Mohytych, Ivanna Rohulia +4
This study presents a benchmark for evaluating the Visual Word Sense Disambiguation (Visual-WSD) task in Ukrainian. The main goal of the Visual-WSD task is to identify, with minima…
cs.CV2024
DeVOS: Flow-Guided Deformable Transformer for Video Object Segmentation
Volodymyr Fedynyak, Yaroslav Romanus, Bohdan Hlovatskyi +4
The recent works on Video Object Segmentation achieved remarkable results by matching dense semantic and instance-level features between the current and previous frames for long-ti…
cs.CV2024
Global Motion Understanding in Large-Scale Video Object Segmentation
Volodymyr Fedynyak, Yaroslav Romanus, Oles Dobosevych +2
In this paper, we show that transferring knowledge from other domains of video understanding combined with large-scale learning can improve robustness of Video Object Segmentation…