Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Ginzburg, Dvir"'
Autor:
Malkiel, Itzik, Ginzburg, Dvir, Barkan, Oren, Caciularu, Avi, Weill, Jonathan, Koenigstein, Noam
Recently, there has been growing interest in the ability of Transformer-based models to produce meaningful embeddings of text with several applications, such as text similarity. Despite significant progress in the field, the explanations for similari
Externí odkaz:
http://arxiv.org/abs/2208.06612
We present MetricBERT, a BERT-based model that learns to embed text under a well-defined similarity metric while simultaneously adhering to the ``traditional'' masked-language task. We focus on downstream tasks of learning similarities for recommenda
Externí odkaz:
http://arxiv.org/abs/2208.06610
Autor:
Ginzburg, Dvir, Raviv, Dan
We present a novel non-iterative learnable method for partial-to-partial 3D shape registration. The partial alignment task is extremely complex, as it jointly tries to match between points and identify which points do not appear in the corresponding
Externí odkaz:
http://arxiv.org/abs/2201.11379
Image translation across domains for unpaired datasets has gained interest and great improvement lately. In medical imaging, there are multiple imaging modalities, with very different characteristics. Our goal is to use cross-modality adaptation betw
Externí odkaz:
http://arxiv.org/abs/2201.09693
We present a new method for real-time non-rigid dense correspondence between point clouds based on structured shape construction. Our method, termed Deep Point Correspondence (DPC), requires a fraction of the training data compared to previous techni
Externí odkaz:
http://arxiv.org/abs/2110.08636
We present a novel model for the problem of ranking a collection of documents according to their semantic similarity to a source (query) document. While the problem of document-to-document similarity ranking has been studied, most modern methods are
Externí odkaz:
http://arxiv.org/abs/2106.01186
Autor:
Ginzburg, Dvir, Raviv, Dan
We present a new paradigm for rigid alignment between point clouds based on learnable weighted consensus which is robust to noise as well as the full spectrum of the rotation group. Current models, learnable or axiomatic, work well for constrained or
Externí odkaz:
http://arxiv.org/abs/2105.02714
Autor:
Ginzburg, Dvir, Raviv, Dan
Publikováno v:
In Virtual Reality & Intelligent Hardware February 2024 6(1):30-42
Alignment between non-rigid stretchable structures is one of the most challenging tasks in computer vision, as the invariant properties are hard to define, and there is no labeled data for real datasets. We present unsupervised neural network archite
Externí odkaz:
http://arxiv.org/abs/2012.10685
Autor:
Ginzburg, Dvir, Raviv, Dan
We provide a novel new approach for aligning geometric models using a dual graph structure where local features are mapping probabilities. Alignment of non-rigid structures is one of the most challenging computer vision tasks due to the high number o
Externí odkaz:
http://arxiv.org/abs/2011.14723