40 citations · 48 across the 5 of their papers we have counts for
7 papers
GLAMI-1M: A Multilingual Image-Text Fashion Dataset
Vaclav Kosar, Antonín Hoskovec, Milan Šulc +1
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 o…
Contrastive Classification and Representation Learning with Probabilistic Interpretation
Rahaf Aljundi, Yash Patel, Milan Sulc +2
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 an…
Text Detection Forgot About Document OCR
Krzysztof Olejniczak, Milan Šulc
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…
Business Document Information Extraction: Towards Practical Benchmarks
Matyáš Skalický, Štěpán Šimsa, Michal Uřičář +1
Information extraction from semi-structured documents is crucial for frictionless business-to-business (B2B) communication. While machine learning problems related to Document Info…
The Hitchhiker's Guide to Prior-Shift Adaptation
Tomas Sipka, Milan Sulc, Jiri Matas
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 c…
Danish Fungi 2020 -- Not Just Another Image Recognition Dataset
Lukáš Picek, Milan Šulc, Jiří Matas +4
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…
Improving CNN classifiers by estimating test-time priors
Milan Sulc, Jiri Matas
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 exi…