Hara, Kensho

9 publications

ICCV 2025 VideoSetDiff: Identifying and Reasoning Similarities and Differences in Similar Videos Yue Qiu, Yanjun Sun, Takuma Yagi, Shusaku Egami, Natsuki Miyata, Ken Fukuda, Kensho Hara, Ryusuke Sagawa

ECCV 2024 Formula-Supervised Visual-Geometric Pre-Training Ryosuke Yamada, Kensho Hara, Hirokatsu Kataoka, Koshi Makihara, Nakamasa Inoue, Rio Yokota, Yutaka Satoh

ICCVW 2023 Estimation of Human Condition at Disaster Site Using Aerial Drone Images Tomoki Arai, Kenji Iwata, Kensho Hara, Yutaka Satoh

WACV 2023 VirtualHome Action Genome: A Simulated Spatio-Temporal Scene Graph Dataset with Consistent Relationship Labels Yue Qiu, Yoshiki Nagasaki, Kensho Hara, Hirokatsu Kataoka, Ryota Suzuki, Kenji Iwata, Yutaka Satoh

WACV 2022 Spatiotemporal Initialization for 3D CNNs with Generated Motion Patterns Hirokatsu Kataoka, Kensho Hara, Ryusuke Hayashi, Eisuke Yamagata, Nakamasa Inoue

CVPRW 2021 Rethinking Training Data for Mitigating Representation Biases in Action Recognition Kensho Hara, Yuchi Ishikawa, Hirokatsu Kataoka

ECCVW 2018 Learning Spatiotemporal 3D Convolution with Video Order Self-Supervision Tomoyuki Suzuki, Takahiro Itazuri, Kensho Hara, Hirokatsu Kataoka

ECCVW 2018 Recognizing People in Blind Spots Based on Surrounding Behavior Kensho Hara, Hirokatsu Kataoka, Masaki Inaba, Kenichi Narioka, Yutaka Satoh

ICCVW 2017 Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition Kensho Hara, Hirokatsu Kataoka, Yutaka Satoh