no code implementations • 9 Nov 2022 • Geri Skenderi, Christian Joppi, Matteo Denitto, Marco Cristani
The fashion industry is one of the most active and competitive markets in the world, manufacturing millions of products and reaching large audiences every year.
1 code implementation • 22 Jul 2022 • Christian Joppi, Geri Skenderi, Marco Cristani
We propose a data-centric pipeline able to generate exogenous observation data for the New Fashion Product Performance Forecasting (NFPPF) problem, i. e., predicting the performance of a brand-new clothing probe with no available past observations.
Ranked #1 on New Product Sales Forecasting on VISUELLE
1 code implementation • 14 Apr 2022 • Geri Skenderi, Christian Joppi, Matteo Denitto, Berniero Scarpa, Marco Cristani
SO-fore assumes that the season has started and a set of new products is on the shelves of the different stores.
Short-observation new product sales forecasting Time Series Analysis
1 code implementation • 6 Oct 2021 • Marco Godi, Christian Joppi, Geri Skenderi, Marco Cristani
Retrieving clothes which are worn in social media videos (Instagram, TikTok) is the latest frontier of e-fashion, referred to as "video-to-shop" in the computer vision literature.
Ranked #1 on Video-to-Shop on MovingFashion
1 code implementation • 20 Sep 2021 • Geri Skenderi, Christian Joppi, Matteo Denitto, Marco Cristani
In particular, we propose a neural network-based approach, where an encoder learns a representation of the exogenous time series, while the decoder forecasts the sales based on the Google Trends encoding and the available visual and metadata information.
Ranked #3 on New Product Sales Forecasting on VISUELLE
1 code implementation • 29 Aug 2019 • Marco Godi, Christian Joppi, Andrea Giachetti, Fabio Pellacini, Marco Cristani
It first individuates texels, characterizing them with individual attributes; subsequently, texels are grouped and characterized through layout attributes, which give the Texel-Att representation.
no code implementations • 29 Aug 2019 • Christian Joppi, Marco Godi, Andrea Giachetti, Fabio Pellacini, Marco Cristani
Capturing the essence of a textile image in a robust way is important to retrieve it in a large repository, especially if it has been acquired in the wild (by taking a photo of the textile of interest).
no code implementations • 15 Apr 2019 • Marco Godi, Christian Joppi, Andrea Giachetti, Marco Cristani
We present SIMCO, the first agnostic multi-class object counting approach.