Shuhei M Yoshida — accepted AI-conference papers

2025

Action-Agnostic Point-Level Supervision for Temporal Action Detection

Shuhei M. Yoshida, Takashi Shibata, Makoto Terao, Takayuki Okatani, Masashi Sugiyama

AAAI 2025technical

We propose action-agnostic point-level (AAPL) supervision for temporal action detection to achieve accurate action instance detection with a lightly annotated dataset. In the proposed scheme, a small portion of video frames is sampled in an unsupervised manner and presented to human annotators, who…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2021

Lower-Bounded Proper Losses for Weakly Supervised Classification

Shuhei M Yoshida, Takashi Takenouchi, Masashi Sugiyama

ICML 2021spotlight

This paper discusses the problem of weakly supervised classification, in which instances are given weak labels that are produced by some label-corruption process. The goal is to derive conditions under which loss functions for weak-label learning are proper and lower-bounded—two essential requiremen…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗