Picture for Masataka Yamaguchi

Masataka Yamaguchi

Batch Uniformization for Minimizing Maximum Anomaly Score of DNN-based Anomaly Detection in Sounds

Add code
Jul 19, 2019
Figure 1 for Batch Uniformization for Minimizing Maximum Anomaly Score of DNN-based Anomaly Detection in Sounds
Figure 2 for Batch Uniformization for Minimizing Maximum Anomaly Score of DNN-based Anomaly Detection in Sounds
Figure 3 for Batch Uniformization for Minimizing Maximum Anomaly Score of DNN-based Anomaly Detection in Sounds
Figure 4 for Batch Uniformization for Minimizing Maximum Anomaly Score of DNN-based Anomaly Detection in Sounds
Viaarxiv icon

AdaFlow: Domain-Adaptive Density Estimator with Application to Anomaly Detection and Unpaired Cross-Domain Translation

Add code
Dec 14, 2018
Figure 1 for AdaFlow: Domain-Adaptive Density Estimator with Application to Anomaly Detection and Unpaired Cross-Domain Translation
Figure 2 for AdaFlow: Domain-Adaptive Density Estimator with Application to Anomaly Detection and Unpaired Cross-Domain Translation
Figure 3 for AdaFlow: Domain-Adaptive Density Estimator with Application to Anomaly Detection and Unpaired Cross-Domain Translation
Figure 4 for AdaFlow: Domain-Adaptive Density Estimator with Application to Anomaly Detection and Unpaired Cross-Domain Translation
Viaarxiv icon

Spatio-temporal Person Retrieval via Natural Language Queries

Add code
Aug 22, 2017
Figure 1 for Spatio-temporal Person Retrieval via Natural Language Queries
Figure 2 for Spatio-temporal Person Retrieval via Natural Language Queries
Figure 3 for Spatio-temporal Person Retrieval via Natural Language Queries
Figure 4 for Spatio-temporal Person Retrieval via Natural Language Queries
Viaarxiv icon

Dense Image Representation with Spatial Pyramid VLAD Coding of CNN for Locally Robust Captioning

Add code
Mar 30, 2016
Figure 1 for Dense Image Representation with Spatial Pyramid VLAD Coding of CNN for Locally Robust Captioning
Figure 2 for Dense Image Representation with Spatial Pyramid VLAD Coding of CNN for Locally Robust Captioning
Figure 3 for Dense Image Representation with Spatial Pyramid VLAD Coding of CNN for Locally Robust Captioning
Figure 4 for Dense Image Representation with Spatial Pyramid VLAD Coding of CNN for Locally Robust Captioning
Viaarxiv icon