Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Sulc, Milan"'
We introduce a new, challenging benchmark and a dataset, FungiTastic, based on fungal records continuously collected over a twenty-year span. The dataset is labeled and curated by experts and consists of about 350k multimodal observations of 5k fine-
Externí odkaz:
http://arxiv.org/abs/2408.13632
Autor:
Šimsa, Štěpán, Šulc, Milan, Uřičář, Michal, Patel, Yash, Hamdi, Ahmed, Kocián, Matěj, Skalický, Matyáš, Matas, Jiří, Doucet, Antoine, Coustaty, Mickaël, Karatzas, Dimosthenis
This paper introduces the DocILE benchmark with the largest dataset of business documents for the tasks of Key Information Localization and Extraction and Line Item Recognition. It contains 6.7k annotated business documents, 100k synthetically genera
Externí odkaz:
http://arxiv.org/abs/2302.05658
The lack of data for information extraction (IE) from semi-structured business documents is a real problem for the IE community. Publications relying on large-scale datasets use only proprietary, unpublished data due to the sensitive nature of such d
Externí odkaz:
http://arxiv.org/abs/2301.12394
We introduce GLAMI-1M: the largest multilingual image-text classification dataset and benchmark. The dataset contains images of fashion products with item descriptions, each in 1 of 13 languages. Categorization into 191 classes has high-quality annot
Externí odkaz:
http://arxiv.org/abs/2211.14451
Cross entropy loss has served as the main objective function for classification-based tasks. Widely deployed for learning neural network classifiers, it shows both effectiveness and a probabilistic interpretation. Recently, after the success of self
Externí odkaz:
http://arxiv.org/abs/2211.03646
Autor:
Olejniczak, Krzysztof, Šulc, Milan
Detection and recognition of text from scans and other images, commonly denoted as Optical Character Recognition (OCR), is a widely used form of automated document processing with a number of methods available. Yet OCR systems still do not achieve 10
Externí odkaz:
http://arxiv.org/abs/2210.07903
Information extraction from semi-structured documents is crucial for frictionless business-to-business (B2B) communication. While machine learning problems related to Document Information Extraction (IE) have been studied for decades, many common pro
Externí odkaz:
http://arxiv.org/abs/2206.11229
In many computer vision classification tasks, class priors at test time often differ from priors on the training set. In the case of such prior shift, classifiers must be adapted correspondingly to maintain close to optimal performance. This paper an
Externí odkaz:
http://arxiv.org/abs/2106.11695
Autor:
Picek, Lukáš, Šulc, Milan, Matas, Jiří, Heilmann-Clausen, Jacob, Jeppesen, Thomas S., Læssøe, Thomas, Frøslev, Tobias
We introduce a novel fine-grained dataset and benchmark, the Danish Fungi 2020 (DF20). The dataset, constructed from observations submitted to the Atlas of Danish Fungi, is unique in its taxonomy-accurate class labels, small number of errors, highly
Externí odkaz:
http://arxiv.org/abs/2103.10107
Autor:
Sulc, Milan, Matas, Jiri
The problem of different training and test set class priors is addressed in the context of CNN classifiers. We compare two different approaches to estimating the new priors: an existing Maximum Likelihood Estimation approach (optimized by an EM algor
Externí odkaz:
http://arxiv.org/abs/1805.08235