no code implementations • 15 Apr 2024 • Peifei Zhu, Tsubasa Takahashi, Hirokatsu Kataoka
Diffusion Models (DMs) have shown remarkable capabilities in various image-generation tasks.
no code implementations • 7 Nov 2023 • Yamato Okamoto, Osada Genki, Iu Yahiro, Rintaro Hasegawa, Peifei Zhu, Hirokatsu Kataoka
In recent years, document processing has flourished and brought numerous benefits.
no code implementations • 23 Oct 2023 • Shuhei Yokoo, Peifei Zhu, Yuchi Ishikawa, Mikihiro Tanaka, Masayoshi Kondo, Hirokatsu Kataoka
Our solution adopts large multimodal models CLIP and BLIP-2 to filter and modify web crawl data, and utilize external datasets along with a bag of tricks to improve the data quality.
1 code implementation • 24 Apr 2023 • Shuhei Yokoo, Peifei Zhu, Junki Ishikawa, Rintaro Hasegawa
This paper presents our 3rd place solution in both Descriptor Track and Matching Track of the Meta AI Video Similarity Challenge (VSC2022), a competition aimed at detecting video copies.
no code implementations • ICCV 2023 • Peifei Zhu, Genki Osada, Hirokatsu Kataoka, Tsubasa Takahashi
We observe that existing spatial attacks cause large degradation in image quality and find the loss of high-frequency detailed components might be its major reason.