Author

Taiki Sekii

Observed name: Sekii, Taiki

Observed institutions: Panasonic (Japan), CyberAgent (Japan), Konica Minolta (Japan), Panasonic System Networks Co., Ltd. (Japan), Kobe University, Nara Institute of Science and Technology

ORCID: 0000-0002-1895-3075

Observed ORCID: 0000-0002-1895-3075

OpenAlex ID: A5076468808

Unified Keypoint-Based Action Recognition Framework via Structured Keypoint Pooling

2023 · Ryo Hachiuma, Fumiaki Sato, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 60

PDF

Prompt-Guided Zero-Shot Anomaly Action Recognition using Pretrained Deep Skeleton Features

2023 · Fumiaki Sato, Ryo Hachiuma, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 49

PDF

Pose Proposal Networks

2018 · Taiki Sekii · Lecture notes in computer science · 49

Robust, Real-Time 3D Tracking of Multiple Objects with Similar Appearances

2016 · Taiki Sekii · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 20

Skeleton-based Zero-Shot Spatio-Temporal Action Localization via Weakly-Supervised Pretraining

2026 · Nagano, Koshiro, Sato, Fumiaki, et al. · arXiv (Cornell University)

PDF

A2O: LLM-based Agentic Learning of Action-to-Object Features for Video Action Recognition

2026 · Association for Computational Linguistics 2026, Sato, Fumiaki, et al. · Underline Science Inc.

Learning from Synthetic Data via Provenance-Based Input Gradient Guidance

2026 · Nagano, Koshiro, Fujii, Ryo, et al. · arXiv (Cornell University)

PDF

A2O: LLM-based Agentic Learning of Action-to-Object Features for Video Action Recognition

2026 · Taiki Sekii, Fumiaki Sato · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)

PDF

3D Visual Prompting: Empowering 3D-Aware Visual Generation via In-Context Self-Refinement

2026 · Reina Ishikawa, Fumiaki Sato, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)

PDF

Frozen Network Few-Shot Object Detection

2025 · Koshiro Nagano, Fumiaki Sato, et al. · Proceedings - International Conference on Image Processing

Text2Traj2Text: Learning-by-Synthesis Framework for Contextual Captioning of Human Movement Trajectories

2024 · Hikaru Asano, Ryo Yonetani, et al. · International Conference on Natural Language Generation

PDF

6-DOF Camera Pose Estimation Using Reference Points on an Aerial Image without Altitude Information

2013 · Taiki Sekii, Tomokazu Sato, et al. · IPSJ Transactions on Computer Vision and Applications

PDF

Shape from Motion and Local Plane Assumption

2010 · Toshio Ito, Taiki Sekii, et al. · 대한전자공학회 기타 간행물

Super-resolution Reconstruction Using Wavelet Transform

2008 · Toshio Ito, Hiroki Kobayashi, et al. · 15th World Congress on Intelligent Transport Systems and ITS America's 2008 Annual MeetingITS AmericaERTICOITS JapanTransCore

Works count: 14

Citation count: 178

H-index: 4

I10-index: 4