Search Results for author: Vacit Oguz Yazici

Found 4 papers, 3 papers with code

Main Product Detection with Graph Networks for Fashion

no code implementations25 Jan 2022 Vacit Oguz Yazici, LongLong Yu, Arnau Ramisa, Luis Herranz, Joost Van de Weijer

Computer vision has established a foothold in the online fashion retail industry.

Visual Transformers with Primal Object Queries for Multi-Label Image Classification

1 code implementation10 Dec 2021 Vacit Oguz Yazici, Joost Van de Weijer, LongLong Yu

However, inputting the same set of object queries to different decoder layers hinders the training: it results in lower performance and delays convergence.

Decoder Multi-Label Classification +4

Cannot find the paper you are looking for? You can Submit a new open access paper.