Search Results for author: Yoichi Sato

Found 30 papers, 5 papers with code

Spatio-Temporal Perturbations for Video Attribution

no code implementations1 Sep 2021 Zhenqiang Li, Weimin WANG, Zuoyue Li, Yifei HUANG, Yoichi Sato

The attribution method provides a direction for interpreting opaque neural networks in a visual way by identifying and visualizing the input regions/pixels that dominate the output of a network.

Video Understanding

EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2021: Team M3EM Technical Report

no code implementations18 Jun 2021 Lijin Yang, Yifei HUANG, Yusuke Sugano, Yoichi Sato

In this report, we describe the technical details of our submission to the 2021 EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition.

Action Recognition Unsupervised Domain Adaptation

Towards Visually Explaining Video Understanding Networks with Perturbation

1 code implementation1 May 2020 Zhenqiang Li, Weimin WANG, Zuoyue Li, Yifei HUANG, Yoichi Sato

''Making black box models explainable'' is a vital problem that accompanies the development of deep learning networks.

Video Understanding

Manipulation-skill Assessment from Videos with Spatial Attention Network

no code implementations9 Jan 2019 Zhenqiang Li, Yifei Huang, Minjie Cai, Yoichi Sato

Recent advances in computer vision have made it possible to automatically assess from videos the manipulation skills of humans in performing a task, which breeds many important applications in domains such as health rehabilitation and manufacturing.

Mutual Context Network for Jointly Estimating Egocentric Gaze and Actions

no code implementations7 Jan 2019 Yifei Huang, Zhenqiang Li, Minjie Cai, Yoichi Sato

In this work, we address two coupled tasks of gaze prediction and action recognition in egocentric videos by exploring their mutual context.

Action Recognition Gaze Prediction

Understanding hand-object manipulation by modeling the contextual relationship between actions, grasp types and object attributes

no code implementations22 Jul 2018 Minjie Cai, Kris Kitani, Yoichi Sato

In the proposed model, we explore various semantic relationships between actions, grasp types and object attributes, and show how the context can be used to boost the recognition of each component.

Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition

2 code implementations ECCV 2018 Yifei Huang, Minjie Cai, Zhenqiang Li, Yoichi Sato

We present a new computational model for gaze prediction in egocentric videos by exploring patterns in temporal shift of gaze fixations (attention transition) that are dependent on egocentric manipulation tasks.

Gaze Prediction Saliency Prediction

Future Person Localization in First-Person Videos

1 code implementation CVPR 2018 Takuma Yagi, Karttikeya Mangalam, Ryo Yonetani, Yoichi Sato

We present a new task that predicts future locations of people observed in first-person videos.

From RGB to Spectrum for Natural Scenes via Manifold-Based Mapping

no code implementations ICCV 2017 Yan Jia, Yinqiang Zheng, Lin Gu, Art Subpa-Asa, Antony Lam, Yoichi Sato, Imari Sato

Spectral analysis of natural scenes can provide much more detailed information about the scene than an ordinary RGB camera.

Dimensionality Reduction

Fast Multi-frame Stereo Scene Flow with Motion Segmentation

no code implementations CVPR 2017 Tatsunori Taniai, Sudipta N. Sinha, Yoichi Sato

This unified framework benefits all four tasks - stereo, optical flow, visual odometry and motion segmentation leading to overall higher accuracy and efficiency.

Motion Segmentation Optical Flow Estimation +3

Hierarchical Gaussian Descriptors with Application to Person Re-Identification

no code implementations14 Jun 2017 Tetsu Matsukawa, Takahiro Okabe, Einoshin Suzuki, Yoichi Sato

To solve this problem, we describe a local region in an image via hierarchical Gaussian distribution in which both means and covariances are included in their parameters.

Image Classification Person Re-Identification

Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption

no code implementations ICCV 2017 Ryo Yonetani, Vishnu Naresh Boddeti, Kris M. Kitani, Yoichi Sato

We propose a privacy-preserving framework for learning visual classifiers by leveraging distributed private image data.

Ego-Surfing: Person Localization in First-Person Videos Using Ego-Motion Signatures

no code implementations15 Jun 2016 Ryo Yonetani, Kris M. Kitani, Yoichi Sato

We envision a future time when wearable cameras are worn by the masses and recording first-person point-of-view videos of everyday life.

Video Retrieval

Exploiting Spectral-Spatial Correlation for Coded Hyperspectral Image Restoration

no code implementations CVPR 2016 Ying Fu, Yinqiang Zheng, Imari Sato, Yoichi Sato

In this paper, we propose an effective method for coded hyperspectral image restoration, which exploits extensive structure sparsity in the hyperspectral image.

Image Restoration

Recognizing Micro-Actions and Reactions From Paired Egocentric Videos

no code implementations CVPR 2016 Ryo Yonetani, Kris M. Kitani, Yoichi Sato

We aim to understand the dynamics of social interactions between two people by recognizing their actions and reactions using a head-mounted camera.

Video Summarization

Hierarchical Gaussian Descriptor for Person Re-Identification

no code implementations CVPR 2016 Tetsu Matsukawa, Takahiro Okabe, Einoshin Suzuki, Yoichi Sato

In both steps, unlike the hierarchical covariance descriptor, the proposed descriptor can model both the mean and the covariance information of pixel features properly.

Image Classification Person Re-Identification

Continuous 3D Label Stereo Matching using Local Expansion Moves

2 code implementations28 Mar 2016 Tatsunori Taniai, Yasuyuki Matsushita, Yoichi Sato, Takeshi Naemura

The local expansion moves extend traditional expansion moves by two ways: localization and spatial propagation.

Patch Matching Stereo Matching +1

Separating Fluorescent and Reflective Components by Using a Single Hyperspectral Image

no code implementations ICCV 2015 Yinqiang Zheng, Ying Fu, Antony Lam, Imari Sato, Yoichi Sato

This paper introduces a novel method to separate fluorescent and reflective components in the spectral domain.

Adaptive Spatial-Spectral Dictionary Learning for Hyperspectral Image Denoising

no code implementations ICCV 2015 Ying Fu, Antony Lam, Imari Sato, Yoichi Sato

Hyperspectral imaging is beneficial in a diverse range of applications from diagnostic medicine, to agriculture, to surveillance to name a few.

Dictionary Learning Hyperspectral Image Denoising +1

Illumination and Reflectance Spectra Separation of a Hyperspectral Image Meets Low-Rank Matrix Factorization

no code implementations CVPR 2015 Yinqiang Zheng, Imari Sato, Yoichi Sato

This paper addresses the illumination and reflectance spectra separation (IRSS) problem of a hyperspectral image captured under general spectral illumination.

Uncalibrated Photometric Stereo Based on Elevation Angle Recovery From BRDF Symmetry of Isotropic Materials

no code implementations CVPR 2015 Feng Lu, Imari Sato, Yoichi Sato

This sort of symmetry can be observed in a 1D BRDF slice from a subset of surface normals with the same azimuth angle, and we use it to devise an efficient modeling and solution method to constrain and recover the elevation angles of surface normals accurately.

Ego-Surfing First-Person Videos

no code implementations CVPR 2015 Ryo Yonetani, Kris M. Kitani, Yoichi Sato

We incorporate this feature into our proposed approach that computes the motion correlation over supervoxel hierarchies to localize target instances in observer videos.

Reflectance and Fluorescent Spectra Recovery based on Fluorescent Chromaticity Invariance under Varying Illumination

no code implementations CVPR 2014 Ying Fu, Antony Lam, Yasuyuki Kobashi, Imari Sato, Takahiro Okabe, Yoichi Sato

We then show that given the spectral reflectance and fluorescent chromaticity, the fluorescence absorption and emission spectra can also be estimated.

3D Reconstruction

Shape-Preserving Half-Projective Warps for Image Stitching

no code implementations CVPR 2014 Che-Han Chang, Yoichi Sato, Yung-Yu Chuang

It provides good alignment accuracy as projective warps while preserving the perspective of individual image as similarity warps.

Image Stitching

Learning-by-Synthesis for Appearance-based 3D Gaze Estimation

no code implementations CVPR 2014 Yusuke Sugano, Yasuyuki Matsushita, Yoichi Sato

Unlike existing appearance-based methods that assume person-specific training data, we use a large amount of cross-subject training data to train a 3D gaze estimator.

3D Reconstruction Gaze Estimation

Uncalibrated Photometric Stereo for Unknown Isotropic Reflectances

no code implementations CVPR 2013 Feng Lu, Yasuyuki Matsushita, Imari Sato, Takahiro Okabe, Yoichi Sato

We propose an uncalibrated photometric stereo method that works with general and unknown isotropic reflectances.

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