1 code implementation • 15 Apr 2024 • Amir Erfan Eshratifar, Joao V. B. Soares, Kapil Thadani, Shaunak Mishra, Mikhail Kuznetsov, Yueh-Ning Ku, Paloma de Juan
Generating background scenes for salient objects plays a crucial role across various domains including creative design and e-commerce, as it enhances the presentation and context of subjects by integrating them into tailored environments.
1 code implementation • 1 Apr 2024 • Maxim Nikolaev, Mikhail Kuznetsov, Dmitry Vetrov, Aibek Alanov
Our paper addresses the complex task of transferring a hairstyle from a reference image to an input photo for virtual hair try-on.
no code implementations • 28 Jul 2023 • Yueh-Ning Ku, Mikhail Kuznetsov, Shaunak Mishra, Paloma de Juan
In addition, we show how our staging approach can enable animations of moving products leading to a video ad from a product image.
1 code implementation • 7 Jun 2023 • Anastasia Martynova, Mikhail Kuznetsov, Vadim Porvatov, Vladislav Tishin, Andrey Kuznetsov, Natalia Semenova, Ksenia Kuznetsova
Parking guidance systems have recently become a popular trend as a part of the smart cities' paradigm of development.
Ranked #1 on Parking Space Occupancy on PKLot (F1-score metric)
no code implementations • 5 Aug 2021 • Shaunak Mishra, Mikhail Kuznetsov, Gaurav Srivastava, Maxim Sviridenko
Motivated by our observations in logged data on ad image search queries (given ad text), we formulate a keyword extraction problem, where a keyword extracted from the ad text (or its augmented version) serves as the ad image query.
2 code implementations • 23 Sep 2020 • Kalina Jasinska-Kobus, Marek Wydmuch, Krzysztof Dembczynski, Mikhail Kuznetsov, Robert Busa-Fekete
We first introduce the PLT model and discuss training and inference procedures and their computational costs.
no code implementations • 1 Jun 2019 • Robert Busa-Fekete, Krzysztof Dembczynski, Alexander Golovnev, Kalina Jasinska, Mikhail Kuznetsov, Maxim Sviridenko, Chao Xu
First, we show that finding a tree with optimal training cost is NP-complete, nevertheless there are some tractable special cases with either perfect approximation or exact solution that can be obtained in linear time in terms of the number of labels $m$.
1 code implementation • NeurIPS 2018 • Marek Wydmuch, Kalina Jasinska, Mikhail Kuznetsov, Róbert Busa-Fekete, Krzysztof Dembczyński
Extreme multi-label classification (XMLC) is a problem of tagging an instance with a small subset of relevant labels chosen from an extremely large pool of possible labels.