TO
Takehiko Ohkawa
cs.CVcs.LGcs.ROcs.AIcs.CL
On Valency
published · living versionsW_6uwgxvck·v1 · currentpublished
AIRoA-0: Long-Horizon, Precise, Cross-Embodiment Manipulation from Handheld Data
with Yueh-Hua Wu, Kei Ota, Hanlong Li, Hayata Yuasa +15
1 version
W_msxfpq5v·v1published
Preprints & journals
24 papers in the corpus · 2020–2026DewHand: Direct Metric World-Space Hand Motion Reconstruction from Egocentric Videos2610.29936v1 · Naru Suzuki, Satoshi Ikehata, Takehiko Ohkawa et al.2026 · 0 citationsarXivon Valency
YUBI-Real2Sim: 3DGS Scene Verification for Reliable Policy Evaluation2610.17521v1 · Hiroki Nishizawa, Takehiko Ohkawa, Nicola Scianca et al.2026 · 0 citationsarXiv
RoboPace: Contact-Aware Time-Optimal Retiming for Action-Chunk Policies2610.09696v1 · Mimo Shirasaka, Takehiko Ohkawa, Takuya Okubo et al.2026 · 0 citationsarXiv
YUBI-STAG: Contact and Semantic-Rich Alignment for VLAs via Automated Video-Language Grounding2610.09718v1 · Masatoshi Tateno, Takehiko Ohkawa, Yueh-Hua Wu et al.2026 · 0 citationsarXiv
SiMDex: Mining Similar Egocentric Videos for Cross-Embodiment Dexterous Manipulation2608.04196v2 · Nie Lin, Takehiko Ohkawa, Sijin Chen et al.2026 · 0 citationsarXiv
YUBI: Yielding Universal Bidigital Interface for Bimanual Dexterous Manipulation at Scale2606.10244v1 · Takehiko Ohkawa, Jumpei Arima, Yuki Noguchi et al.2026 · 0 citationsarXiv
DF-Mamba: Deformable State Space Modeling for 3D Hand Pose Estimation in Interactions2512.02727v1 · Yifan Zhou, Takehiko Ohkawa, Guwenxiao Zhou et al.2025 · 1 citationarXiv
Affordance-Guided Diffusion Prior for 3D Hand Reconstruction2510.00506v3 · Naru Suzuki, Takehiko Ohkawa, Tatsuro Banno et al.2025 · 0 citationsarXiv
AssemblyHands-X: Modeling 3D Hand-Body Coordination for Understanding Bimanual Human Activities2509.23888v1 · Tatsuro Banno, Takehiko Ohkawa, Ruicong Liu et al.2025 · 0 citationsarXiv
Generative Modeling of Shape-Dependent Self-Contact Human Poses2509.23393v1 · Takehiko Ohkawa, Jihyun Lee, Shunsuke Saito et al.2025 · 1 citationarXiv
Leveraging RGB Images for Pre-Training of Event-Based Hand Pose Estimation2509.16949v1 · Ruicong Liu, Takehiko Ohkawa, Tze Ho Elden Tse et al.2025 · 0 citationsarXiv
EmoSign: A Multimodal Dataset for Understanding Emotions in American Sign Language2505.17090v1 · Phoebe Chua, Cathy Mengying Fang, Takehiko Ohkawa et al.2025 · 0 citationsarXiv
SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training2502.15251v3 · Nie Lin, Takehiko Ohkawa, Yifei Huang et al.2025 · 0 citationsarXiv
Pre-Training for 3D Hand Pose Estimation with Contrastive Learning on Large-Scale Hand Images in the Wild2409.09714v1 · Nie Lin, Takehiko Ohkawa, Mingfang Zhang et al.2024 · 1 citationarXiv
Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects2403.16428v2 · Zicong Fan, Takehiko Ohkawa, Linlin Yang et al.2024 · 17 citationsarXiv
Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation2403.04381v2 · Ruicong Liu, Takehiko Ohkawa, Mingfang Zhang et al.2024 · 15 citationsarXiv
Generative Hierarchical Temporal Transformer for Hand Pose and Action Modeling2311.17366v3 · Yilin Wen, Hao Pan, Takehiko Ohkawa et al.2023 · 0 citationsarXiv
Exo2EgoDVC: Dense Video Captioning of Egocentric Procedural Activities Using Web Instructional Videos2311.16444v4 · Takehiko Ohkawa, Takuma Yagi, Taichi Nishimura et al.2023 · 4 citationsarXiv
AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation2304.12301v1 · Takehiko Ohkawa, Kun He, Fadime Sener et al.2023 · 72 citationsarXiv
Efficient Annotation and Learning for 3D Hand Pose Estimation: A Survey2206.02257v3 · Takehiko Ohkawa, Ryosuke Furuta, Yoichi Sato2022 · 23 citationsarXiv
Domain Adaptive Hand Keypoint and Pixel Localization in the Wild2203.08344v5 · Takehiko Ohkawa, Yu-Jhe Li, Qichen Fu et al.2022 · 19 citationsarXiv
Background Mixup Data Augmentation for Hand and Object-in-Contact Detection2202.13941v2 · Koya Tango, Takehiko Ohkawa, Ryosuke Furuta et al.2022 · 5 citationsarXiv
Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation2107.02718v4 · Takehiko Ohkawa, Takuma Yagi, Atsushi Hashimoto et al.2021 · 9 citationsarXiv
Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation2003.00187v2 · Takehiko Ohkawa, Naoto Inoue, Hirokatsu Kataoka et al.2020 · 6 citationsarXiv
Career total: 28 works. 24 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.