IWAIT Papers by Sessions

List of IWAIT papers by Sessions

DAY-1, JAN 9 : S-1A, S-1B, S-2A, S-2B, SS-1, SS-2, P-1, P-2, P-3

DAY-2, JAN 10 :S-3A, S-3B, S-3C, S-4A, S-4B, S-4C, P-4, P-5

DAY 1, JAN 9

IWAIT Session1A : Best Paper Session I – Image Processing
Chair: Prof. Masayuki Tanimoto / Nagoya Univ., Japan

#AuthorsTitle
10Thuy Pham, Truong Mai and Chul LeeModel-Driven Deep Unfolding Approach to Underwater Image Enhancement
13Jie Jiang, Hock Soon Seah and Hong Ze LiewStroke-based painting
33Jiaxin Li, Yasutomo Kawanishi, Daisuke Deguchi and Hiroshi MuraseA Preliminary Study on View Independent Panoptic Scene Change Detection
53Chun Zhao and Byeungwoo JeonPerspective effect enhancement for light field refocusing using depth-guided optimization
59Yuduo Zhang, Vinh Van Duong, Jonghoon Yim and Byeungwoo JeonLight Field Image Super-Resolution using Selective Kernel Convolution
67Wei-Ting Chen, Der-Lor Way and Zen-Chung ShihPhysically-Based Cloth Simulation with Level of Detail

Go to list

IWAIT Session 1B : Best Paper Session II – Virtual Reality
Chair: Prof. Tokiichiro Takahashi / Tokyo Denki Univ., Japan

#AuthorsTitle
18Jingwen Qin, Hisatoshi Toriya, Hidehiko Shishido, Youhei Kawamura and Itaru KitaharaAn image-capturing system to generate 3D borehole models using multiple fiberscope cameras
19Teruhisa Yamashiro, Yuki Honma, Ren Togo, Takahiro Ogawa and Miki HaseyamaCustomer Interest Estimation Method in Real Store Using Re-Identification and 3D Posture Estimation Models
26Teppei Jodo and Yuji SakamotoFast Calculation System for Head-mounted Display Using User’s Attitude Angle in CGH
35Shunzo Yamagishi, Hidehiko Shishido, Yoshinari Kameda and Itaru KitaharaVisualization method of movement trajectory in outfielder's fly ball catching technique using baseball video
41Yui Yoshikawa, Hidehiko Shishido, Yoshinari Kameda and Itaru KitaharaEvaluation of a Video Generation Method Linking Dance and Scenes
124Aki Ichihara and Tokiichiro TakahashiA VR Stage Rehearsal Support System for Mastering "Vocal Perspective"

Go to list

IWAIT Session 2A : Best Paper Session III – Deep Learning and Applications
Chair: Prof. Hiroki Takahashi / Univ. Electro-Communication, Japan

#AuthorsTitle
14Eigo Hara, Keisuke Doman, Yoshito Mekada, Naoshi Nishida and Masatoshi KudoLiver Tumor Detection and Classification from Abdominal Ultrasound Images with CenterNet Using Contrastive Learning
24Fumiya Kimura, Hidehiko Shishido and Itaru Kitahara4D Portrait Generation based on Neural Radiance Field and Facial Expression Similarity
42Miho Takahashi, Kei Iino, Hiroshi Watanabe, Ichiro Morinaga, Shohei Enomoto, Xu Shi, Akira Sakamoto and Takeharu EdaCategory-based Memory Bank Design for Traffic Surveillance in Context R-CNN
48Wan-Chi Siu, H. Anthony Chan, Sin-Wai Chan, Wing-Ho Cheng, Cheuk-Yiu Chan, Chun-Chuen Hui, Ridwan Salahudeen and Bi-Cheng YangOn the Completion of Automatic Football Game Commentary System with Deep Learning
94Matthew Marchellus and In Kyu ParkGenre-Controlled Stochastic Dance Prediction with Spatial Feature Preservation
120Kosin Chamnongthai, Dipanita Chakraborty and Werapon ChiracharitObject-Camera Motion Classification Using Semantic Features and Neural Network on Sports Video

Go to list

IWAIT Session 2B : Best Paper Session IV – Video Coding and Processing
Chair: Yung-Lyul Lee / Sejong Univ., Korea

#AuthorsTitle
21Soonbin Lee, Jong-Beom Jeong and Eun-Seok RyuEfficient Pruning Graph Alignment for MPEG Immersive Video
23Masahiro Yagi, Sho Takahashi and Toru HagiwaraImprovement of Nighttime Visibility Estimation Based on Spatio-Temporal Correlation in Videos
57Gihwa Moon, Dohyeon Park and Jae-Gon KimEfficient Signaling of Extended GPM Modes in ECM
72Jihoon Do, Soowoong Kim, Hahyun Lee, Jinho Lee, Seong-Jun Bae, Gun Bang and Jung Won KangMost Probable Mode Derivation for Multi-View Texture map
92Bumyoon Kim, Jeeyoon Park and Byeungwoo JeonImproved Chroma Prediction in VVC

Go to list

IWAIT Special Session I – 3D Human and Metaverse
Chair: Prof. Ju Yong Chang / Kwangwoon Univ., Korea

#AuthorsTitle
95Nadhira Noor and In Kyu ParkSkeleton-based Fall Accident Detection for Elderly People
110Seong Hyun Kim, Do Hyun Jeon and Ju Yong ChangGlobal 3D Human Pose Estimation from Monocular Videos
114Tae Hyun Kim, Eunhye Lee, Jinsoo Yu and Yunjeong YangSemantic-Aware Video Inpainting for Unwanted Object Removal
119Joshua Santoso and Williem WilliemSemi-Supervised 3D Holistic Human Mesh Reconstruction from A Single Image

Go to list

IWAIT Special Session II – Deep Learning and Vision
Chair: Wonjun Kim / Konkuk Univ., Korea

#AuthorsTitle
111Wonjun KimAn Overview of Laplacian Pyramid-based Deep Neural Network and Its Applications
112Wonchul Son and Wonjun HwangParallel Teacher Assistant Knowledge Distillation for On-the-fly Convolutional Neural Network
113Tae Hyun Kim, Jinsoo Yu and Jihoon NamTest-Time Adaptation for Video Super Resolution via Self-Distillation
116Jung Eun Kwon, Dong Nyeong Lee, Tai Gon Kim and Sung In ChoA Deep Learning-based Welding Defect Detection for Shipbuilding
117Chang-Ryeol Jeon and Suk-Ju KangDriving Scene Segmentation Using Domain Adaptation

Go to list

IWAIT Poster Session I – Online – Deep Learning and Image/Video Processing
Chair: Prof. Wonjun Hwang / Ajou Univ., Korea

#AuthorsTitle
3Tomoki Nakada and Kousuke ImamuraReducing the Number of Masks to Accelerate the Visualization Process of RISE
8Yu Yoshizato, Yexin Zhou, Yoichi Ohyanagi, Akiko Iwata, Koji Shibazaki and Naoki KamiyaInitial Study of Fiber Estimation in Paper Macroimages Based on Patch-Based Classification using Two-Stage EfficientNet
27Kohei Moriyama, Naoki Ono, Kohei Inoue and Kenji HaraVideo Super-resolution by Generative Adversarial Network with 3D Convolutional Neural Networks
51Takumi Kobayashi, Mengbo You and Kouichi KonnoA Study on Badminton Smash Return Prediction Simulation based on Neural Networks
79Hiraku Matsuda and Mutsuo SanoEvaluation of an Old-fashioned Style Picture Transformation System using Generative Adversarial Networks and Instance Segmentation
84Tatsuaki Uno and Toshiyuki YoshidaRealization of Depth From Defocus technique based on a CNN for real images
86Kanato Sakama, Wataru Kameyama and Shunichi SekiguchiPerformance Analysis of Generated Predictive Frames Using PredNet with Multiple Convolution Kernels
87Suguru Mastumura, Toshiyuki Yoshida, Shogo Tokai, Atsushi Otsuka and Masashi OnoDamage detection for wind turbine blades based on CNNs
102Tatsuya Chuman and Hitoshi KiyaA Jigsaw Puzzle Solver-based Attack on Block-wise Image Encryption for Privacy-preserving DNNs
131Yuta Sadamatsu, Seiichi Murakami, Li Guangxu and Tohru KamiyaDenoising of LDCT Image Using Deep CNN with Attention Module

Go to list

IWAIT Poster Session II – Online – Image Processing and Applications
Chair: Prof. Jae-Gon Kim, Korea Aerospace Univ., Korea

#AuthorsTitle
11Shoma Deguchi, Yuta Muraki, Naoyuki Awano and Ken-Ichi KoboriFast Seam Carving for Video with Consideration of Object Misalignment Suppression
36Yusuke Umeda and Akitoshi HanazawaPrediction of Uncertain Values in Depth Images by Segmentation and Gaussian Process Regression Leading to Its Generalization
37Miku Honda and Akitoshi HanazawaDiscrimination of Landslide Hazard Areas by Unsupervised Outlier Detection Using a Feature of Mountain Slope Inclination
45Hibiki Yamamoto, Diego Fujii, Yasuyo Kita, Ichiro Matsuda, Susumu Itoh, Kyohei Unno and Satoshi KomoritaLossless Compression of Point Cloud Attributes Based on Probability Modeling with Directional Predictors
49Shotaro Nakamura, Hidehiko Shishido and Yoshinari KamedaBraille block Detection at Shortest Distance by Mobile Devices
69Koki Hoshi, Toshiya Wakana, Yasuyo Kita, Ichiro Matsuda and Susumu ItohVehicle Entry/Exit Detection in Each Parking Slot from Outdoor Surveillance Camera Images
71Choi Minseok, Han Heeji, Jung Soon-Heung, Kwak Sangwoon, Choo Hyon-Gon and Choi HaechulFeature Clustering and Reordering Method for Neural Network Feature Compression
77Mengbo You and Kouichi KonnoA Study on Selecting the Optimal Number of Features for Clustering without Label Information
83Aoi Fukino, Hiroshi Ikeoka and Takayuki HamamotoAccuracy Inprovement of Depth Estimation with Tilted Optics and Color Filter Aperture
85Shota Muraishi, Mie Sato and Naoki HashimotoAn Examination of Weight Illusion by Adding Visual Effects on the Arm
101Ryosuke Namioka, Tsutomu Kinoshita, Xin Lu, Akio Kimura and Kouichi KonnoA Study on Automatic Face Parts Extraction for Evaluating Face Similarity of Haniwa Based on 3D Measured Point Clouds
109Gibran Benitez-Garcia, Luis Acevedo-Bringas, Natsuki Takayama and Hiroki TakahashiReal-time Spatiotemporal Hand Gesture Localization and Recognition for Interaction with Touchless Screens

Go to list

IWAIT Poster Session III – Online – Multimedia Applications
Chair: Prof. Nobuhiko Mukai / Tokyo City Univ., Jap

#AuthorsTitle
25Masaki Nakai and Hidekazu TsujiaiInstrument played by nodding
39Tomoki Kosaka, Yuta Muraki, Naoyuki Awano and Ken-Ichi KoboriA Method for Reducing Drawing Load by Omitting the Draw Process Based on Impression Deterioration
52Atsuki Hirakawa, Kei Kanari, Mie Sato and Hiroshi HasegawaAn Examination on Operation Methods of AR Multi-Viewpoint Viewing System for Ohayashi
66Jiahao Weng and Haoran XieInteractive Layout Drawing Interface with Shadow Guidance
76Shogo Saito, Sho Ooi and Mutsuo SanoA Study of Relationship between 2D Character Illustration and Animation Character Voice
78Takuto Tsukiyama, Sho Ooi and Mutsuo SanoStudy on Character Style Transformation for an Animator Support System
80Tatsuya Yamashita, Shogo Tokai, Toshiyuki Yoshida, Atsushi Otsuka and Masashi Ono3D alignment of local surface images of wind turbine blades with shape estimation using multiple 2D barcodes
88Tomohiro Fujiwara, Kei Kanari and Mie SatoAn Examination on Eye-Gaze Input Using a Bubble Cursor in AR
93Mizuki Fukasawa, Sai Sun, Shinsuke Shimojo and Takuya AkashiA System for Measuring the Frequency of Micro-Periodic Motion Against Varying Backgrounds Using Periodicity
104Misato Imai, Hidehiko Shishido, Itaru Kitahara and Yoshinari KamedaA Visual Feedback Method of Motion Information on Alpine Skiing Experience in Head Mounted Display

Go to list

DAY 2, JAN 10

IWAIT Session 3A : Oral-Online I – 3D Processing and Recognition
Chair: Dr. Gun Bang / ETRI, Korea

#AuthorsTitle
17Tetsu Okamoto, Akio Kimura, Hiroyuki Shimono, Koji Harashina and Kiyohito Yamamoto3D Reconstruction of Rice Plant Community Using Spectral Images with a Goal of Making Rice Breeding Efficient
29Daichi Mochizuki, Yoshitsugu Manabe and Noriko YataA Study of Recognition of Ingredients for Cooking Guide System
30Eijiro Shibusawa, Hiromichi Sotodate and Norishige FukushimaDouble-Direction Fisheye Plane Sweep Stereo for Road Surface 3D Reconstruction
32Amgalan Altansukh, Mengbo You, Enkhbayar Altantsetseg, Oyundolgor Khorloo and Kouichi KonnoA Study on Automatic Flake Surface Segmentation of Stone Tools by Calculating Shape Features
73Kan Miyazaki, Isao Nishihara and Takayuki NakataInvestigation of the effectiveness by Redirected Walking with tilt presentation to the sole
89You-Jia Wu and Jian-Jiun DingConfidence-Selective Moving Trace Approximation Using Ellipse and Line Models for Hand Gesture Recognition
108Ponlawat Chophuk, Prawit Boonmee, Seksan Jiarasuwan, Suwannee Jearasuwan and Pattrawut BookprakongTheft Detection by Patterns of Walking Behavior using Motion-based Artificial Intelligence

Go to list

IWAIT Session 3B : Oral-Online II – Image Processing
Chair: Prof. Gyemin Lee / Seoultech, Korea

#AuthorsTitle
16Hirofumi Hayasaka and Akio KimuraA training data augmentation approach using GAN for learning of tactile paving images
38Haruya Takahashi, Toru Higaki, Raytchev Bisser and Kazufumi KanedaReproduction of Color Vision Deficiency Considering Spectrum
40Ayaka So and Akitoshi HanazawaMarker Identification by Object Recognition Algorithm Using Machine Learning
44Kunihiko Takano, Tetsushi Oiwa, Kaketu Fukushima, Kazuyuki Takasaki, Ryoji Wakabayashi, Tomohiro Endo, Koki Sato, Kikuo Asai, Itta Kajimura and Haruchika OnoOn the characteristics of the projected holographic images onto the mist screen employed blue-violet laser
61Sankarasrinivasan S, Jing-Ming Guo and Lv HungDeep Residual and Classified Neural Networks for Inverse Halftoning
83Aoi Fukino, Hiroshi Ikeoka and Takayuki HamamotoAccuracy Inprovement of Depth Estimation with Tilted Optics and Color Filter Aperture
107Jian-Jiun Ding and Chun-Lin LiaoImage Denoising Based on the Noise Prediction Model Using Smooth Patch and Sparse Domain Priors

Go to list

IWAIT Session 3C : Oral-Online III – Image Processing and Applications
Chair: Prof. Yoshito Mekada / Chukyo Univ., Japan

#AuthorsTitle
2Dingjie Peng and Wataru KameyamaA Transformer-based Semantic Segmentation Model for Street Fashion Images
4Alyssa Takazume, Yoshitsugu Manabe and Noriko YataA investigation of Japanese sign language recognition using human skeleton data
20Yuta Watanabe, Yoshitsugu Manabe and Noriko YataA Study of Face Authentication Methods Using Thermal Images
22Tomoya Wakasugi, Toru Higaki, Bisser Raytchev, Kazufumi Kaneda and Masashi BabaAcquiring Spectral Scattering Properties of Seawater from an RGB Image
58Taiju Watanabe, Takahiro Shindo and Hiroshi WatanabeNovel CNN Approach for Video Prediction Based on FitVid
100Ching-Ting Chou, Jian-Jiun Ding and Meng-Lin ChangUltrasonic Bladder Image Analysis for Intravesical Prostatic Protrusion Measurement Using Noise-Robust Gradient Information and Adaptive Contour Connection
118Phokin Promvijittrakarn and Theekapun CharoenpongA Method of Soccer-Team Identification by Histogram Feature Vector and Support Vector Machine

Go to list

IWAIT Session 4A : Oral-Online IV – Deep Learning and Applications
Chair: Prof. Chin Kuan Ho / Asia Pacific Univ. Technol. Innovation, Malaysia

#AuthorsTitle
7Yun Liu, Remina Yano, Hiroshi Watanabe, Ikai Tomohiro, Takeshi Chujoh, Zheming Fan and Takuya SuzukiA Prior-Guided Face Image Super-Resolution Network Based on Attention Mechanism
15Sota Watanabe and Makoto HasegawaVisualization of Cutibacterium acnes with Visible Light Using Deep Learning
28Sartaj Ahmed Salman, Hiroki Takahashi and Ali ZakirCascaded Deep Graphical Convolutional Neural Network for 2D Hand Pose Estimation
31Kenta Takano, Xin Lu, Chunhong Yuan and Akio KimuraFreshness prediction for seafood using deep neural network
34Masaaki Miyazaki and Akitoshi HanazawaReinforcement Learning for Finding Multiple Evacuation Paths in the Danger of Heavy Rain Disasters
43Kazuma Yoshimura and Naoki HashimotoA Study on Radiometric Compensation for Moving Non-rigid Surfaces Using Motion Prediction

Go to list

IWAIT Session 4B : Oral – Image/Video Processing
Chairs: Prof. Yoko Yamakata / Univ. Tokyo, Japan

#AuthorsTitle
5Jeonghwan Yoon and Nam Ik ChoDeformable Offset Gating Network with Variational Autoencoder for Compression Artifacts Reduction
46Ikuto Ohki, Hidehiko Shishido and Yoshinari KamedaA Study of Next Step Prediction Method using Smartphone IMU
74Gun Bang, Jihoon Do, Jinho Lee, Jun Won Kang, Seong-Jun Bea, Hahyun Lee and Soowoong KimNeural Implicit Visual Representation Compression of 3D Scenes
90Jonghoon Yim, Vinh Duong, Thuc Huu and Byeungwoo JeonSynthesizing Light Field Views based on Superpixels in Epipolar Plane Image Domain
115Gwan Ik Park, Kyu Dong Sim, Min Su Kyeon, Sang Hwa Lee, Jeong Hyun Baek and Jong-Il ParkDetection of Leaf Diseases Using Color and Shape Models
123Eunseong Lee, Jongseok Lee, Young-Ho Seo and Donggyu SimApplicability of Embedment of Watermarking on End-to-end Image Compression

Go to list

IWAIT Session 4C – Oral – Video Coding and Image Processing
Chair: Prof. Zen-Chung Shih / Nat. Yang Ming Chiao Tung Univ., Taiwan

#AuthorsTitle
50Hamed Razavi Khosroshahi, Jaime Sancho, Gonzalo Rosa, Ruben Salvador, Eduardo Juarez, Gauthier Lafruit and Mehrdad TerataniAssessment of Multi-Plenoptic 2.0 Camera Depth Maps for DIBR
65Kazuya Ishikawa, Sou Oishi and Norishige FukushimaPrincipal Component Analysis for Accelerating Color Bilateral Filtering
68Eun-bin An, A-Young Kim, Soon-heung Jung, Hyon-Gon Choo, Jeong-Il Seo and Kwang-deok SeoECM-based Sub-optimal VCM Coding Architecture for Image Object Detection
70Dohyeon Park, Gihwa Moon and Jae-Gon KimTraining Methods Considering Block Partitioning for Neural Networks-Based Intra Prediction
97SuYeon Lim and Yung-Lyul LeeLong-tap Interpolation Filters in VVC
122Minhun Lee, Seungjin Park, Younhee Kim, Se Yoon Jeong and Donggyu SimA novel feature map compression method based on transformation for Video Coding for Machines

Go to list

IWAIT Poster Session IV – Multimedia Systems and Applications
Chair: Prof. Kwang-deok Seo / Yonsei Univ., Korea

#AuthorsTitle
9Rui Matsuo, Kensuke Yotsumoto, Hiroko Kawanobe, Megumi Nakashima and Makoto HasegawaProposal for Predicting the Facial Brightening Effect of Cosmeceuticals Using Deep Learning
12Nobuhiko Mukai, Takuya Natsume, Masamichi Oishi and Marie OshimaMicelle Behavior Analysis Using Dissipative Particle Dynamics Method
47Taku TsukamotoDevelopment of 4K 240fps professional hand-held video camera using four CMOS image sensors
54Kaito Okazaki and Makoto HasegawaStudy of Meniscus Height Measurement for Dry Eye Detection Using Smartphone Camera and Ring Light
55Haruki Nogami, Sou Oishi, Tomohiro Sasaki, Yoshihiro Maeda and Norishige FukushimaPerformance Evaluation of Halide Auto-Scheduler with Directional Cubic Convolution Interpolation
60Makoto J. Hirayama3D Modeling and 3D Printing of Human Jaws for Speech Production Research and Education
64Tomoya Hirabayashi and Tokiichiro TakahashiSwitchable Dual Dial: A Japanese Text Input Method for VR Contents based on Flick Input by Using Two VR Controller
82Chihiro Okamura, Atsushi Osa and Kazuyuki MiuraMeasurement of micro-vibration frequency along optical axis by spatial frequency analysis of video images
91Muho Cheon, Hyunki Jeong and Byeungwoo JeonObject-Tracking Gimbal for Projection Mapping
99Yuta Bando, Takayuki Nakata and Isao NishiharaGrasping Method and Voice Coil Motor Design Considering 3D Directional Presentation of Virtual Force Sensation

Go to list

IWAIT Poster Session V – Image/Video Processing
Chair: Prof. Jae-Gon Kim / Korea Aerospace Univ., Korea

#AuthorsTitle
6Kazuya Ueki, Yuma Suzuki, Takayuki Hori and Hideaki OkamotoMultiple Facial Attribute Model
56Sou Oishi, Haruki Nogami, Kazuya Ishikawa and Norishige FukushimaPerformance Evaluation of Image Convolution with WebAssembly
63Yukine Taya and Tokiichiro TakahashiDynamic Projection Mapping onto Non-rigid Objects using Markers and Skeletal Information
75Jeehwan Lee, Bumyoon Kim and Byeungwoo JeonImproved Cross Component Linear Model for Chroma Channel Coding in VVC
96Yujin Lee, Jeeyoon Park and Byeungwoo JeonAdaptive Multiple Reference Lines Candidate List Reordering
98Jeeyoon Park, Jeehwan Lee and Byeungwoo JeonSimplified Rate-Distortion Optimized Quantization for Transform Skip Mode in VVC Screen Content Coding
103Daiki Tanaka, Akiyoshi Hizukuri, Ryohei Nakayama, Kaori Kusuda, Ken Masamune and Yoshihiro MuragakiComputerized Classification Method for Molecular Subtypes of Low-Grade Glioma in Brain MRI Images Using 3D-Attention Branch Networks with Additive Angular Margin Penalty
106Kazunori Oka, Daisuke Fujita, Koichi Arimura, Koji Iihara and Syoji KobashiDiscrimination of ICH and IVH in Initial CT Images Using Hierarchical Region Extraction Мethod
121JoonHo Lee and Gyemin LeeA Source-Free Unsupervised Domain Adaptation Method Based on Feature Consistency