Picture for Yutaka Satoh

Yutaka Satoh

Estimation of Human Condition at Disaster Site Using Aerial Drone Images

Add code
Aug 08, 2023
Viaarxiv icon

Describing and Localizing Multiple Changes with Transformers

Add code
Mar 25, 2021
Figure 1 for Describing and Localizing Multiple Changes with Transformers
Figure 2 for Describing and Localizing Multiple Changes with Transformers
Figure 3 for Describing and Localizing Multiple Changes with Transformers
Figure 4 for Describing and Localizing Multiple Changes with Transformers
Viaarxiv icon

Pre-training without Natural Images

Add code
Jan 21, 2021
Figure 1 for Pre-training without Natural Images
Figure 2 for Pre-training without Natural Images
Figure 3 for Pre-training without Natural Images
Figure 4 for Pre-training without Natural Images
Viaarxiv icon

Weakly Supervised Dataset Collection for Robust Person Detection

Add code
May 01, 2020
Figure 1 for Weakly Supervised Dataset Collection for Robust Person Detection
Figure 2 for Weakly Supervised Dataset Collection for Robust Person Detection
Figure 3 for Weakly Supervised Dataset Collection for Robust Person Detection
Figure 4 for Weakly Supervised Dataset Collection for Robust Person Detection
Viaarxiv icon

Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?

Add code
Apr 10, 2020
Figure 1 for Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?
Figure 2 for Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?
Figure 3 for Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?
Figure 4 for Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?
Viaarxiv icon

Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB

Add code
Apr 08, 2018
Figure 1 for Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB
Figure 2 for Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB
Figure 3 for Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB
Figure 4 for Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB
Viaarxiv icon

Drive Video Analysis for the Detection of Traffic Near-Miss Incidents

Add code
Apr 07, 2018
Figure 1 for Drive Video Analysis for the Detection of Traffic Near-Miss Incidents
Figure 2 for Drive Video Analysis for the Detection of Traffic Near-Miss Incidents
Figure 3 for Drive Video Analysis for the Detection of Traffic Near-Miss Incidents
Figure 4 for Drive Video Analysis for the Detection of Traffic Near-Miss Incidents
Viaarxiv icon

Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?

Add code
Apr 02, 2018
Figure 1 for Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
Figure 2 for Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
Figure 3 for Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
Figure 4 for Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
Viaarxiv icon

Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition

Add code
Aug 25, 2017
Figure 1 for Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition
Figure 2 for Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition
Figure 3 for Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition
Figure 4 for Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition
Viaarxiv icon

Collaborative Descriptors: Convolutional Maps for Preprocessing

Add code
May 10, 2017
Figure 1 for Collaborative Descriptors: Convolutional Maps for Preprocessing
Figure 2 for Collaborative Descriptors: Convolutional Maps for Preprocessing
Figure 3 for Collaborative Descriptors: Convolutional Maps for Preprocessing
Viaarxiv icon