Search Results for author: Shuhei Yokoo

Found 7 papers, 4 papers with code

The Effects of Short Video-Sharing Services on Video Copy Detection

no code implementations26 Mar 2024 rintaro yanagi, Yamato Okamoto, Shuhei Yokoo, Shin'ichi Satoh

From the experimental results focusing on segment-level and video-level situations, we can see that three effects: "Segment-level VCD in short video-sharing services is more difficult than those in general video-sharing services", "Video-level VCD in short video-sharing services is easier than those in general video-sharing services", "The video alignment component mainly suppress the detection performance in short video-sharing services".

Copy Detection Video Alignment

Leveraging Image-Text Similarity and Caption Modification for the DataComp Challenge: Filtering Track and BYOD Track

no code implementations23 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.

text similarity

3rd Place Solution to Meta AI Video Similarity Challenge

1 code implementation24 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.

Copy Detection Video Similarity

Contrastive Learning with Large Memory Bank and Negative Embedding Subtraction for Accurate Copy Detection

2 code implementations8 Dec 2021 Shuhei Yokoo

Copy detection, which is a task to determine whether an image is a modified copy of any image in a database, is an unsolved problem.

Contrastive Learning Copy Detection +1

Two-stage Discriminative Re-ranking for Large-scale Landmark Retrieval

2 code implementations25 Mar 2020 Shuhei Yokoo, Kohei Ozaki, Edgar Simo-Serra, Satoshi Iizuka

Due to the variance of the images, which include extreme viewpoint changes such as having to retrieve images of the exterior of a landmark from images of the interior, this is very challenging for approaches based exclusively on visual similarity.

Image Retrieval Landmark Recognition +3

Large-scale Landmark Retrieval/Recognition under a Noisy and Diverse Dataset

1 code implementation10 Jun 2019 Kohei Ozaki, Shuhei Yokoo

Besides, we devise a discriminative re-ranking method to address the diversity of the dataset for landmark retrieval.

Landmark Recognition Metric Learning +2

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