Natsuki Miyata — accepted AI-conference papers

2025

VideoSetDiff: Identifying and Reasoning Similarities and Differences in Similar Videos

Yue Qiu, Yanjun Sun, Takuma Yagi, Shusaku Egami, Natsuki Miyata, Ken Fukuda +2

ICCV 2025poster

Recognizing subtle similarities and differences among sets of similar activities is central to many real-world applications, including skill acquisition, sports performance evaluation, and anomaly detection. Humans excel at such fine-grained analysis, which requires comprehensive video understanding…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

DailySTR: A Daily Human Activity Pattern Recognition Dataset for Spatio-temporal Reasoning

Yue Qiu, Shusaku Egami, Ken Fukuda, Natsuki Miyata, Takuma Yagi, Kensho Hara +2

IROS 2024poster

Recognizing daily human activities is essential for domestic robots to assist humans effectively in indoor environments. These activities typically involve sequences of interactions between humans and objects across different locations and times within a household. Identifying these events and under…

Cited by 0 Source ↗Scholar ↗