Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page

Yosuke Yamaguchi

dblp:192/0310 · DBLP profile ↗
← Back
2ranked-venue papers
1as first author
1since 2021 · last 2024
—ORCID · conflict

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 2 · 1 first-author · 1 since 2021Graphics, computer vision, multimedia, augmented reality and games · 1 · 1 since 2021

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
1 paper
Representation and self-supervised learning · 77% Generative modeling · 23%

Topics — the 2 heaviest of 3, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Machine learning › Representation and self-supervised learning › representation learning › visual representation learning
discriminative visual representation
0.812024
Do Text-Free Diffusion Models Learn Discriminative Visual Representations? · ECCV (60) 2024
Machine learning › Generative modeling
diffusion model
0.212024
Do Text-Free Diffusion Models Learn Discriminative Visual Representations? · ECCV (60) 2024

Methods — techniques the papers use, named apart from their topics

representation probing · 0.8diffusion model · 0.8
YearPublicationVenuePosition
2024 Do Text-Free Diffusion Models Learn Discriminative Visual Representations?
Soumik Mukhopadhyay 0001, Matthew Gwilliam, Yosuke Yamaguchi, Vatsal Agarwal, Namitha Padmanabhan, Archana Swaminathan, Tianyi Zhou 0001, Jun Ohya, Abhinav Shrivastava
ECCV (60)3
2016 Real-time Analysis of Baseball Pitching Using Image Processing on Smartphone
abstract
Pitching is one of the most important elements of baseball. Therefore, both professional and amateur players are interested in measuring their pitching performance, particularly their pitch speed. Conventional equipment such as radar speed guns can be used to measure pitch speed; however this approach is unpopular among amateur players because of its cost. Therefore, we proposed a vision-based speed-measuring method for baseball pitches and developed a smartphone application called iPhoneSG, which can measure the speed of pitched baseballs on a real baseball diamond in near-real-time using a standalone image-processing technique on the smartphone. Relative to conventional radar speed guns, which must be placed on the extended line of the ball trajectory, iPhoneSG widens the possible area of data acquisition. Considering the popularity of smartphones, iPhoneSG provides players with a convenient means of measuring pitch speeds. We confirmed the basic viability of the proposed method as implemented in our iPhoneSG application.
Yosuke Yamaguchi, Motoki Miura
KES1