Search Results for author: Ryo Hachiuma

Found 13 papers, 2 papers with code

Weakly Semi-supervised Tool Detection in Minimally Invasive Surgery Videos

no code implementations5 Jan 2024 Ryo Fujii, Ryo Hachiuma, Hideo Saito

We further propose a co-occurrence loss, which considers a characteristic that some tool pairs often co-occur together in an image to leverage image-level labels.

Surgical tool detection

Toward Unsupervised 3D Point Cloud Anomaly Detection using Variational Autoencoder

1 code implementation7 Apr 2023 Mana Masuda, Ryo Hachiuma, Ryo Fujii, Hideo Saito, Yusuke Sekikawa

We propose a deep variational autoencoder-based unsupervised anomaly detection network adapted to the 3D point cloud and an anomaly score specifically for 3D point clouds.

Unsupervised Anomaly Detection

Deep Selection: A Fully Supervised Camera Selection Network for Surgery Recordings

no code implementations28 Mar 2023 Ryo Hachiuma, Tomohiro Shimizu, Hideo Saito, Hiroki Kajita, Yoshifumi Takatsume

Recording surgery in operating rooms is an essential task for education and evaluation of medical treatment.

Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling

no code implementations CVPR 2023 Ryo Hachiuma, Fumiaki Sato, Taiki Sekii

A point cloud deep-learning paradigm is introduced to the action recognition, and a unified framework along with a novel deep neural network architecture called Structured Keypoint Pooling is proposed.

Action Recognition Data Augmentation +5

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

no code implementations CVPR 2023 Fumiaki Sato, Ryo Hachiuma, Taiki Sekii

Particularly, during the training phase using normal samples, the method models the distribution of skeleton features of the normal actions while freezing the weights of the DNNs and estimates the anomaly score using this distribution in the inference phase.

Action Recognition Zero-Shot Learning

A Two-Block RNN-based Trajectory Prediction from Incomplete Trajectory

no code implementations14 Mar 2022 Ryo Fujii, Jayakorn Vongkulbhisal, Ryo Hachiuma, Hideo Saito

However, most works rely on a key assumption that each video is successfully preprocessed by detection and tracking algorithms and the complete observed trajectory is always available.

Imputation Trajectory Prediction +1

RGB-D Image Inpainting Using Generative Adversarial Network with a Late Fusion Approach

no code implementations14 Oct 2021 Ryo Fujii, Ryo Hachiuma, Hideo Saito

We expand conventional image inpainting method to RGB-D image inpainting to jointly restore the texture and geometry of missing regions from a pair of RGB and depth images.

Generative Adversarial Network Image Inpainting +3

Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimation

1 code implementation NeurIPS 2021 Zhengyi Luo, Ryo Hachiuma, Ye Yuan, Kris Kitani

By comparing the pose instructed by the kinematic model against the pose generated by the dynamics model, we can use their misalignment to further improve the kinematic model.

Egocentric Pose Estimation Human-Object Interaction Detection +2

Kinematics-Guided Reinforcement Learning for Object-Aware 3D Ego-Pose Estimation

no code implementations10 Nov 2020 Zhengyi Luo, Ryo Hachiuma, Ye Yuan, Shun Iwase, Kris M. Kitani

We propose a method for incorporating object interaction and human body dynamics into the task of 3D ego-pose estimation using a head-mounted camera.

Human-Object Interaction Detection Object +4

DetectFusion: Detecting and Segmenting Both Known and Unknown Dynamic Objects in Real-time SLAM

no code implementations22 Jul 2019 Ryo Hachiuma, Christian Pirchheim, Dieter Schmalstieg, Hideo Saito

We present DetectFusion, an RGB-D SLAM system that runs in real-time and can robustly handle semantically known and unknown objects that can move dynamically in the scene.

Instance Segmentation object-detection +4

Cannot find the paper you are looking for? You can Submit a new open access paper.