Výsledky vyhledávání - "Florea, Adina"

Report

ViTmiX: Vision Transformer Explainability Augmented by Mixed Visualization Methods

Autor: Hogea, Eduard, Onchis, Darian M., Coporan, Ana, Florea, Adina Magda, Istin, Codruta

Recent advancements in Vision Transformers (ViT) have demonstrated exceptional results in various visual recognition tasks, owing to their ability to capture long-range dependencies in images through self-attention mechanisms. However, the complex na

Externí odkaz: http://arxiv.org/abs/2412.14231

Zobrazit plný text záznamu

Report

Iterative Knowledge Exchange Between Deep Learning and Space-Time Spectral Clustering for Unsupervised Segmentation in Videos

Autor: Haller, Emanuela, Florea, Adina Magda, Leordeanu, Marius

We propose a dual system for unsupervised object segmentation in video, which brings together two modules with complementary properties: a space-time graph that discovers objects in videos and a deep network that learns powerful object features. The

Externí odkaz: http://arxiv.org/abs/2012.07123

Zobrazit plný text záznamu

Report

Spacetime Graph Optimization for Video Object Segmentation

Autor: Haller, Emanuela, Florea, Adina Magda, Leordeanu, Marius

We address the challenging task of foreground object discovery and segmentation in video. We introduce an efficient solution, suitable for both unsupervised and supervised scenarios, based on a spacetime graph representation of the video sequence. We

Externí odkaz: http://arxiv.org/abs/1907.03326

Zobrazit plný text záznamu