Hirokatsu Kataoka

University of Oxford — United Kingdom

Computer Science · Physical Sciences

22h-index4.5kcitations225works0.92yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Human Pose and Action Recognition(58), Advanced Neural Network Applications(39), Video Surveillance and Tracking Methods(39), Advanced Image and Video Retrieval Techniques(35), Multimodal Machine Learning Applications(30)

Publications225 total

3D sans 3D Scans: Scalable Pre-training from Video-Generated Point Clouds
ArXiv.org·2025Open Access
3D sans 3D Scans: Scalable Pre-training from Video-Generated Point Clouds
arXiv (Cornell University)·2025Open Access
HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics
arXiv (Cornell University)·2025Open Access
PowerCLIP: Powerset Alignment for Contrastive Pre-Training
arXiv (Cornell University)·2025Open Access
Approximate Domain Unlearning for Vision-Language Models
arXiv (Cornell University)·2025Open Access
Viewpoint-Dependent 3D Visual Grounding for Mobile Robots
2025
Japanese mayfly family classification with a vision transformer model
Limnology·2025
CLIP-like Model as a Foundational Density Ratio Estimator
ArXiv.org·2025Open Access
Industrial Synthetic Segment Pre-training
arXiv (Cornell University)·2025Open Access
Simple Visual Artifact Detection in Sora-Generated Videos
arXiv (Cornell University)·2025Open Access
Formula-Supervised Sound Event Detection: Pre-Training Without Real Data
arXiv (Cornell University)·2025Open Access
Is ImageNet Pre-Training Fair in Image Classification?
Journal of the Japan Society for Precision Engineering·2025
Pre-training with 3D Synthetic Data: Learning 3D Point Cloud Instance Segmentation from 3D Synthetic Scenes
arXiv (Cornell University)·2025Open Access
Leveraging LLMs with Iterative Loop Structure for Enhanced Social Intelligence in Video Question Answering
arXiv (Cornell University)·2025Open Access
Classifying microfossil radiolarians on fractal pre-trained vision transformers
Scientific Reports·2025· 2 citedOpen Access
Continuously Visual Pre-training with Artificially Generated and Real Images
Journal of the Japan Society for Precision Engineering·2025Open Access
MoireDB: Formula-generated Interference-fringe Image Dataset
arXiv (Cornell University)·2025Open Access
Efficient Load Interference Detection with Limited Labeled Data
2025
Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding
arXiv (Cornell University)·2025Open Access
A Comprehensive Analysis of a Social Intelligence Dataset and Response Tendencies Between Large Language Models (LLMs) and Humans
Sensors·2025· 2 citedOpen Access
page 1 of 12Next →

Frequent Co-authors

Yutaka Satoh(29), Kenji Iwata(12), Kensho Hara(11), Nakamasa Inoue(9), Yoshimitsu Aoki(8), Ryosuke Yamada(7), Akio Nakamura(7), Yue Qiu(6), Ryota Suzuki(6), Kodai Nakashima(4), Asato Matsumoto(4), Eisuke Yamagata(4), Yasuhiro Matsui(4), Rio Yokota(4), Shoko Oikawa(3), Ryo Hayamizu(3), Sora Takashima(3), Risa Shinoda(3), Yuchi Ishikawa(2), Tomoyuki Suzuki(2)