IEICE Technical Committee

Human Communication Group-Multimedia and Virtual Environment(Date:2023/03/15)

Presentation

Applicability of Motion Transfer to Generation of Knee Joint Lateral Thrust Video

Yusuke Okamura(KUTE-TOKYO), Dan Mikami(KUTE-TOKYO), Takuya Ibara(TMDU), Koji Fujita(TMDU),

[Date]2023-03-17
[Paper #]IMQ2022-76,IE2022-153,MVE2022-106

Improvement of cross-attention modules for image captioning using pixel-wise semantic information

Zhihao Chen(Chukyo Univ.), Keisuke Doman(Chukyo Univ.), Yoshito Mekada(Chukyo Univ.),

[Date]2023-03-17
[Paper #]IMQ2022-84,IE2022-161,MVE2022-114

A Study on Image Inpainting Considering Local Appearance Consistency

Tianxiang Zhang(Chukyo Univ.), Keisuke Doman(Chukyo Univ.), Yoshito Mekada(Chukyo Univ.),

[Date]2023-03-17
[Paper #]IMQ2022-77,IE2022-154,MVE2022-107

Creation of human gaze heat maps using skeletal estimation

Satoki Nakamura(Kogakuin Univ.), Dan Mikami(Kogakuin Univ.),

[Date]2023-03-17
[Paper #]IMQ2022-68,IE2022-145,MVE2022-98

Estimation of the level between two people in cooperative behavior based on RGB-D images

Runyu Tian(U-Tsukuba), Hidehiko Shishido(U-Tsukuba), Yoshinari Kameda(U-Tsukuba),

[Date]2023-03-17
[Paper #]IMQ2022-70,IE2022-147,MVE2022-100

Haunted House as a Co-Creation Media

Sumaru Niida(KDDI Research), Ryo Terui(KDDI Research), Satoshi Naruse(VIVIWARE), Masatoshi Imai(VIVIWARE), Shozaburo Shimada(VIVIWARE), Takahito Kamihira(Senshu Univ.),

[Date]2023-03-17
[Paper #]IMQ2022-89,IE2022-166,MVE2022-119

Time-domain Monaural Speech Separation of Introducing Discriminative Loss between Speakers

Shaoxiang Dang(Nagoya Univ.), Tetsuya Matsumoto(Nagoya Univ.), Yoshinori Takeuchi(Daido Univ.), Hiroaki Kudo(Nagoya Univ.),

[Date]2023-03-17
[Paper #]IMQ2022-91,IE2022-168,MVE2022-121

A copyright management system using blockchain and edge computing

ZHE TAN(UEC), Celimuge Wu(UEC),

[Date]2023-03-17
[Paper #]CQ2022-106

Development of a low-stress light stimulation device for daily Alzheimer's disease treatment

Yuki Yamaoka(NAIST), Monica Perusquia-Hernandez(NAIST), Naoya Isoyama(NAIST), Hideaki Uchiyama(NAIST), Kiyoshi Kiyokawa(NAIST), Takeshi Morimoto(OU),

[Date]2023-03-17
[Paper #]IMQ2022-90,IE2022-167,MVE2022-120

Proposed pseudo-rewinding system to be used offline to improve comprehension.

Gai Matsumaru(Meiji Univ), Hidenori Takei(Meiji Univ), Ayumi Isobe(Meiji Univ), Kenta Ohnaka(Meiji Univ), Kousuke Kitabatake(Meiji Univ), Minoru Kobayashi(Meiji Univ), Ayumi Isobe(Meiji Univ),

[Date]2023-03-17
[Paper #]IMQ2022-71,IE2022-148,MVE2022-101

A Data Collection Tool and Analysis for Avatar Animation

Ryosuke Miyawaki(NAIST), Monica Perusquia-Hernandez(NAIST), Naoya Isoyama(NAIST), Hideaki Uchiyama(NAIST), Kiyoshi Kiyokawa(NAIST),

[Date]2023-03-17
[Paper #]IMQ2022-72,IE2022-149,MVE2022-102

Examination of a Proposal Method to Reduce Wasted Energy caused by Hesitation when Entering a Room

Ayumi Isobe(Meiji Univ.), Kanan Abe(Meiji Univ.), Minoru Kobayashi(Meiji Univ.),

[Date]2023-03-17
[Paper #]IMQ2022-73,IE2022-150,MVE2022-103

A Study on Offset Coding of Patch Data in Video-based Point Cloud Compression (V-PCC)

Emi Myoudou(KDDI Research.), Yoshitaka Kidani(KDDI Research.), Kei Kawamura(KDDI Research.),

[Date]2023-03-17
[Paper #]IMQ2022-78,IE2022-155,MVE2022-108

A study of the encoding runtime reduction for CU partition with intra prediction information in VVC

Yuta Saito(KDDI Research, Inc.), Yoshitaka Kidani(KDDI Research, Inc.), Haruhisa Kato(KDDI Research, Inc.), Kei Kawamura(KDDI Research, Inc.),

[Date]2023-03-17
[Paper #]IMQ2022-79,IE2022-156,MVE2022-109