Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
PRMU, IPSJ-CVIM, IPSJ-DCC, IPSJ-CGVI |
2023-11-17 14:40 |
Tottori |
(Primary: On-site, Secondary: Online) |
A context dependent character sequence recognition using DNN regressing class scores for possible rotation angles Shu Kimoto, Koji Kamma, Toshikazu Wada (Wakayama Univ.) |
[more] |
|
PRMU, IPSJ-CVIM, IPSJ-DCC, IPSJ-CGVI |
2023-11-17 14:40 |
Tottori |
(Primary: On-site, Secondary: Online) |
An image based barcode reading using Hough transform and 1-D super resolution Hiroki Egawa, Koji Kamma, Toshikazu Wada (Wakayama Univ.) |
[more] |
|
PRMU, IBISML, IPSJ-CVIM [detail] |
2023-03-02 09:40 |
Hokkaido |
Future University Hakodate (Primary: On-site, Secondary: Online) |
Pruning for Producing Efficient DNNs: Neuron Selection and Reconstruction based on Final Layer Error Koji Kamma, Toshikazu Wada (Wakayama Univ.) PRMU2022-66 IBISML2022-73 |
Deep Neural Networks (DNNs) are dominant in the field of machine learning. However, because DNN models have large comput... [more] |
PRMU2022-66 IBISML2022-73 pp.42-47 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2023-03-02 17:30 |
Hokkaido |
Future University Hakodate (Primary: On-site, Secondary: Online) |
A Study on Data Augmentation by Pixel Value Transformation for Product Image Retrieval DNN Yu Okamoto, Masaki Kishibe, Toshikazu Wada (Wakayama Univ.) PRMU2022-94 IBISML2022-101 |
We are developing a product image retrieval DNN for supporting shelving allocation tasks. To train the DNN, product imag... [more] |
PRMU2022-94 IBISML2022-101 pp.181-186 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2023-03-03 17:00 |
Hokkaido |
Future University Hakodate (Primary: On-site, Secondary: Online) |
Continual learning combining Replay and Parameter Isolation Methods Ryota Adachi, Toshikazu Wada (Wakayama Univ.) PRMU2022-121 IBISML2022-128 |
Deep Neural Networks (DNN) are used for various tasks such as image classification, but when a new task is trained on a ... [more] |
PRMU2022-121 IBISML2022-128 pp.335-340 |
PRMU |
2022-12-15 10:45 |
Toyama |
Toyama International Conference Center (Primary: On-site, Secondary: Online) |
DN4C
-- An Interactive Image Segmentation System Combining Deep Neural Network and Nearest Neighbor Classifier -- Toshikazu Wada, Koji Kamma (Wakayama University) PRMU2022-35 |
Color/texture based image segmentation can be widely applied to the images for product and/or medical inspection, remote... [more] |
PRMU2022-35 pp.19-24 |
PRMU |
2022-12-15 14:25 |
Toyama |
Toyama International Conference Center (Primary: On-site, Secondary: Online) |
A DNN compression method based on output error of activation functions Koji Kamma, Toshikazu Wada (Wakayama Univ.) PRMU2022-38 |
Deep Neural Networks (DNNs) are dominant in the field of machine learning. However, because DNN models have large comput... [more] |
PRMU2022-38 pp.34-39 |
PRMU |
2022-12-16 10:00 |
Toyama |
Toyama International Conference Center (Primary: On-site, Secondary: Online) |
Image Transformation Simulating the Height Change of Wide-angle Ceiling Camera for People Detection Hayato Kitao, Toshikazu Wada (Wakayama Univ.) PRMU2022-43 |
In recent years, surveillance cameras have been widely installed inside the buildings. Especially, wide-angle ceiling ca... [more] |
PRMU2022-43 pp.57-62 |
PRMU |
2022-12-16 14:10 |
Toyama |
Toyama International Conference Center (Primary: On-site, Secondary: Online) |
Sampling Strategies in Data Pruning Ryota Higashi, Toshikazu Wada (Wakayama Univ.) PRMU2022-48 |
Data Pruning is a method of selecting the training data out of an entire training dataset so as to keep the accuracy aft... [more] |
PRMU2022-48 pp.85-90 |
PRMU |
2022-09-14 15:45 |
Kanagawa |
(Primary: On-site, Secondary: Online) |
Human Pose Transfer with Reduced Color Transfer by Occlusion for Person Re-Identification Masaki Kishibe, Toshikazu Wada (Wakayama Univ.) PRMU2022-15 |
Human pose transfer is the task that transforms a person image from the source pose to a given target pose, and is usefu... [more] |
PRMU2022-15 pp.31-36 |
PRMU |
2022-09-14 16:00 |
Kanagawa |
(Primary: On-site, Secondary: Online) |
Convolutional Skip Connection for Compressing DNNs with Branched Architectures Koji Kamma, Toshikazu Wada (Wakayama Univ.) PRMU2022-16 |
Although Deep Neural Network (DNN) is a core technology in Computer Vision, it is difficult to implement DNN models beca... [more] |
PRMU2022-16 pp.37-42 |
PRMU |
2021-12-16 16:30 |
Online |
Online |
Recurrent Tracknet : Continuous ball detection using Deep Neural Network Gen Maesako, Toshikazu Wada (Wakayama Univ.) PRMU2021-38 |
[more] |
PRMU2021-38 pp.77-82 |
PRMU |
2021-12-16 16:30 |
Online |
Online |
Examination of facial pattern structure estimation using GCN Naoya Maruoka, Toshikazu Wada (Wkayama Univ.) PRMU2021-41 |
[more] |
PRMU2021-41 pp.92-97 |
PRMU |
2021-12-17 14:45 |
Online |
Online |
Data Selection for Efficient Deep Learning Ryota Higashi, Toshikazu Wada (Wakayama Univ.) PRMU2021-51 |
We are investigating the method to sample the important data from the whole dataset for efficient training of Deep Neura... [more] |
PRMU2021-51 pp.148-153 |
PRMU |
2021-12-17 15:00 |
Online |
Online |
Toward high-accuracy CNN learning using dropout. Hirokazu Akiba, Toshikazu Wada (Wakayama Univ.) PRMU2021-52 |
(To be available after the conference date) [more] |
PRMU2021-52 pp.154-159 |
PRMU |
2020-12-17 10:45 |
Online |
Online |
Simultaneous pose-region estimation for people tracking Kazuhiko Watanabe, Toshikazu Wada (Wakayama Univ.) PRMU2020-41 |
Bottom-up pose estimation often make an incorrect connection between body parts in a crowded situation like group photo.... [more] |
PRMU2020-41 pp.18-23 |
PRMU |
2020-12-18 10:15 |
Online |
Online |
Corner point detection with reliability metric for homography warping of planer objects Hiroya Fujiura, Toshikazu Wada (Wakayama Univ) PRMU2020-54 |
When classifying flat and rectangle objects, such as product packages on shelves, from a slanted image taken at an angle... [more] |
PRMU2020-54 pp.93-98 |
PRMU |
2020-12-18 11:15 |
Online |
Online |
Supervised disentangled representation learning
-- Disentangling features using classifier -- Shujiro Kuroda, Toshikazu Wada (Wakayama Univ.) PRMU2020-58 |
VAE is a DNN model for unsupervised representation learning. VAE learns to extract features from the input data as laten... [more] |
PRMU2020-58 pp.116-121 |
PRMU |
2020-12-18 14:55 |
Online |
Online |
Regularization Using Knowledge Distillation in Learning Small Datasets Ryota Higashi, Toshikazu Wada (Wakayama Univ.) PRMU2020-61 |
Knowledge distillation is a method mainly used for compressing deep learning models, but it has recently gained attentio... [more] |
PRMU2020-61 pp.133-138 |
PRMU, IPSJ-CVIM |
2020-05-14 13:15 |
Online |
Online |
Biorthogonal System Based Channel Selection Algorithm for Neural Network Pruning Koji Kamma, Toshikazu Wada (Wakayama Univ.) PRMU2020-2 |
[more] |
PRMU2020-2 pp.7-12 |