1. Home
  2. Proceedings
  3. ISM
  4. ISM 2024
Default Cover Image

2024 International Symposium on Multimedia (ISM)

Dec. 11 2024 to Dec. 13 2024

Tokyo, Japan

ISBN: 979-8-3315-1111-1

Table of Contents

Title Page iFreely available from IEEE.pp. 1-1
Title Page iiiFreely available from IEEE.pp. 3-3
Copyright PageFreely available from IEEE.pp. 4-4
Table of ContentsFreely available from IEEE.pp. 5-12
Message from the General ChairsFreely available from IEEE.pp. 13-13
Message from the Program ChairsFreely available from IEEE.pp. 14-15
S2MGen: A synthetic skin mask generator for improving segmentationFull-text access may be available. Sign in or learn about subscription options.pp. 1-8
by Subhadra Gopalakrishnan, Trisha Mittal, Jaclyn Pytlarz, Yuheng Zhao
Generating and Evaluating Cursive Chinese Calligraphy by Semi-Classifying Style: A Case Study Using a Diffusion ModelFull-text access may be available. Sign in or learn about subscription options.pp. 9-16
by Yi-Chieh Wu, Yu-Jung Hsu
StegoFusion-Net: Fusion of Convolutional Neural Networks for Spatial Image SteganalysisFull-text access may be available. Sign in or learn about subscription options.pp. 17-23
by Yassine Belkhouche, AlaaIdin Dwaik
Disparity Correction Method of the Monocular Omnidirectional Stereo CameraFull-text access may be available. Sign in or learn about subscription options.pp. 24-25
by Hisayoshi Kaneda, Ryota Kawamata, Kazuyoshi Yamazaki, Kazuya Shimizu
Unveiling the Potential of SSL-Generated Audio Embeddings for Cross-Lingual Speaker RecognitionFull-text access may be available. Sign in or learn about subscription options.pp. 26-32
by Wen-Hung Liao, Po-Han Chen, Yi-Chieh Wu
Two-stage instrument timbre transfer method using RAVEFull-text access may be available. Sign in or learn about subscription options.pp. 33-40
by Di Hu, Katunobu Ito
Speaker Pseudonymization for Japanese Speech Using Duration EmbeddingsFull-text access may be available. Sign in or learn about subscription options.pp. 41-48
by Aoi Ito, Katunobu Itou
Modeling User Quality of Experience in Adaptive Point Cloud Video StreamingFull-text access may be available. Sign in or learn about subscription options.pp. 49-54
by Duc V. Nguyen, Nguyen Long Quang, Tran Thuy Hien, Nguyen Ngoc Huyen, Truong Thu Huong, Pham Ngoc Nam
Appeal prediction for AI up-scaled ImagesFull-text access may be available. Sign in or learn about subscription options.pp. 55-62
by Steve Goring, Rasmus Merten, Alexander Raake
Modelling Concurrent RTP Flows for End-to-end Predictions of QoS in Real Time CommunicationsFull-text access may be available. Sign in or learn about subscription options.pp. 63-70
by Tailai Song, Paolo Garza, Michela Meo, Maurizio Matteo Munafò
SoccerNet-Echoes: A Soccer Game Audio Commentary DatasetFull-text access may be available. Sign in or learn about subscription options.pp. 71-78
by Sushant Gautam, Mehdi Houshmand Sarkhoosh, Jan Held, Cise Midoglu, Anthony Cioppa, Silvio Giancola, Vajira Thambawita, Michael A. Riegler, Pal Halvorsen, Mubarak Shah
Ensuring Color Consistency in RGB-D Multi-Camera SetupFull-text access may be available. Sign in or learn about subscription options.pp. 79-84
by Peter O. Fasogbon
Low Complexity Learning-based Lossless Event-based CompressionFull-text access may be available. Sign in or learn about subscription options.pp. 85-92
by Ahmadreza Sezavar, Catarina Brites, João Ascenso
PlayerTV: Advanced Player Tracking and Identification for Automatic Soccer Highlight ClipsFull-text access may be available. Sign in or learn about subscription options.pp. 93-97
by Hakon Solberg, Mehdi H. Sarkhoosh, Sushant Gautam, Saeed S. Sabet, Pal Halvorsen, Cise Midoglu
Flexible And Faithful Data Insights GenerationFull-text access may be available. Sign in or learn about subscription options.pp. 98-105
by Wei Zhang, Victor Soares Bursztyn
Holistic Visualization of Contextual Knowledge in Hotel Customer Reviews Using Self-AttentionFull-text access may be available. Sign in or learn about subscription options.pp. 106-109
by Shuntaro Masuda, Toshihiko Yamasaki
Investigation of Feature Distribution and Network Weight Updates in the Machine Unlearning ProcessFull-text access may be available. Sign in or learn about subscription options.pp. 110-113
by Wen-Hung Liao, Yang-Jing Lin
Platform for Endangered Language EducationFull-text access may be available. Sign in or learn about subscription options.pp. 114-115
by Greeshma Sree Parimi, Gurkirat Singh Guliani, Min Chen
Homophonic Music Composition Using a GAN and LSTM Pipeline for Melody and Harmony GenerationFull-text access may be available. Sign in or learn about subscription options.pp. 116-119
by Clément Saint-Marc, Katunobu Itou
Instrumentality Classification Evaluation System for Natural Sounds*Full-text access may be available. Sign in or learn about subscription options.pp. 120-123
by Yuhuan Wang, Katunobu Itou
Generating Bass Phrases from Guitar Chord Backing with NMFFull-text access may be available. Sign in or learn about subscription options.pp. 124-125
by Tomoo Kouzai, Junya Koguchi, Tetsuro Kitahara
Watch your back! Dynamic thumbnails for a 360-degree video player to enhance viewing experience on 2D displaysFull-text access may be available. Sign in or learn about subscription options.pp. 126-132
by Jakub Kovác̆, Wolfgang Hürst
Influence of Display Devices and Field of View on Subjective Quality of Experience Evaluation of 8K 360° VideosFull-text access may be available. Sign in or learn about subscription options.pp. 133-136
by Daichi Arai, Yuichi Kondo, Yasuko Sugito, Yuichi Kusakabe
VEMOCLAP: A video emotion classification web applicationFull-text access may be available. Sign in or learn about subscription options.pp. 137-140
by Serkan Sulun, Paula Viana, Matthew E. P. Davies
A Power-Law Transformation Approach for Template-Based Cross-Component PredictionFull-text access may be available. Sign in or learn about subscription options.pp. 141-142
by Zhikai Liu, Kun Zhang, Xin-Yi Cui, Wei Sun, Fan Liang
Investigating the Impact of High Frame Rate on Video Quality: A SAMVIQ ApproachFull-text access may be available. Sign in or learn about subscription options.pp. 143-144
by Dominik Keller, Paul Rudi Frank, Steve Göring, Alexander Raake
A Server-driven View-aware Point Cloud Video Streaming FrameworkFull-text access may be available. Sign in or learn about subscription options.pp. 145-148
by Tran Gia Minh, Truong Thu Huong, Duc V. Nguyen
Evaluation of strategies for efficient rate-distortion NeRF streamingFull-text access may be available. Sign in or learn about subscription options.pp. 149-153
by Pedro Martin, António Rodrigues, João Ascenso, Maria Paula Queluz
Perceptual Quality Driven Point Cloud Compression for 6DoF 3D Point Cloud StreamingFull-text access may be available. Sign in or learn about subscription options.pp. 154-157
by Yumeka Chujo, Yusuke Tagashira, Yukiko Harada, Kenji Kanai, Jiro Katto
On Multi-CDN Delivery Costs Optimization ProblemFull-text access may be available. Sign in or learn about subscription options.pp. 158-161
by Yuriy A. Reznik, Guillem Cabrera
Sliding Window Check: Repairing Object IdentitiesFull-text access may be available. Sign in or learn about subscription options.pp. 162-169
by Geerthan Srikantharajah, Naimul Khan
Data Augmentation with Diffusion Model for Hand DetectionFull-text access may be available. Sign in or learn about subscription options.pp. 170-173
by Genta Matsukawa, Atsuo Yoshitaka
AI Maintenance Techniques by Detecting Performance Degradation in Domain Shift Using Model EnsemblesFull-text access may be available. Sign in or learn about subscription options.pp. 174-175
by Keita Yamane, Akira Kitayama, Keigo Hasegawa, Yusuke Obonai, Hiroto Sasao
Cross-Modal 3D Model RetrievalFull-text access may be available. Sign in or learn about subscription options.pp. 176-180
by Raphael Waltenspul, Florian Spiess, Heiko Schuldt
Prevention of Unexpected Object Generation in Diffusion Model-Based InpaintingFull-text access may be available. Sign in or learn about subscription options.pp. 181-184
by Takumi Komori, Takahiro Hayashi
LMM-Regularized CLIP Embeddings for Image ClassificationFull-text access may be available. Sign in or learn about subscription options.pp. 185-188
by Maria Tzelepi, Vasileios Mezaris
Evaluation Framework for Novel View SynthesisFull-text access may be available. Sign in or learn about subscription options.pp. 189-192
by Kolja Kieslich, Louay Bassbouss, Stephan Steglich, Stefan Arbanowski
A Simulation for the Evaluation of the Mean Opinion Score (MOS) for EVS-WB and AMR-WB Audio Codecs for 5G Mobile NetworksFull-text access may be available. Sign in or learn about subscription options.pp. 193-196
by Jussif Abularach Arnez, Cássio Antonio Tavares Alves, Wederson Medeiros Silva, Isaac Barros Gomes, Carla Lapa Nogueira, Maria Gabriela Lima Damasceno
FrameCorr: Adaptive, Autoencoder-based Neural Compression for Video Reconstruction in Resource and Timing Constrained Network SettingsFull-text access may be available. Sign in or learn about subscription options.pp. 197-200
by John Li, Deepak Nair, Klara Nahrstedt, Indranil Gupta, Shehab Sarar Ahmed
Ultra-low-latency 8K120p-video-transmission System Parallelizing SMPTE ST 2110Full-text access may be available. Sign in or learn about subscription options.pp. 201-202
by Yasuhiro Mochida, Takuro Yamaguchi, Hirokazu Takahashi, Koichi Takasugi
Low-latency Software-based Uncompressed Video TransmissionFull-text access may be available. Sign in or learn about subscription options.pp. 203-204
by Takuro Yamaguchi, Yasuhiro Mochida, Hirokazu Takahashi
Visual Speech Recognition with Surrounding and Emotional InformationFull-text access may be available. Sign in or learn about subscription options.pp. 205-212
by Pengcheng Zeng, Atsuo Yoshitaka
Synchronized Object Sharing for Augmented Reality Virtual ConferencingFull-text access may be available. Sign in or learn about subscription options.pp. 213-218
by John Murray, Michael Zink
Fusion-Based Human Pose Estimation Using RGB and IR Images with Transformer-Based DecodingFull-text access may be available. Sign in or learn about subscription options.pp. 219-220
by Viviana Crescitelli, Takashi Oshima
Occlusion-Aware Real-Time Tiny Facial Alignment Model for Makeup Virtual Try-OnFull-text access may be available. Sign in or learn about subscription options.pp. 221-224
by Kin Ching Lydia Chau, Zhi Yu, Ruowei Jiang
A Study on Mental Stress Test using Cybersickness caused by Virtual Reality ContentsFull-text access may be available. Sign in or learn about subscription options.pp. 225-226
by Nan Bu, Kakeru Nakano
Exploring Augmented Table Setup and Lighting Customization in a Simulated Restaurant to Improve the User ExperienceFull-text access may be available. Sign in or learn about subscription options.pp. 227-231
by Jana Motowilowa, Maurizio Vergari, Tanja Kojić, Maximilian Warsinke, Sebastian Möller, Jan-Niklas Voigt-Antons
Human-in-the-loop knowledge base upkeep for retrieval augmented generation applicationsFull-text access may be available. Sign in or learn about subscription options.pp. 232-233
by Pedro Baptista de Castro, Hiroko Sukeda, Soichi Takashige
LiveSkeleton: High-Quality Real-Time Human Tracking and Pose EstimationFull-text access may be available. Sign in or learn about subscription options.pp. 234-235
by Hannes Fassold
A technical Concept for enhancing the Student Experience in Hybrid Lecture ScenariosFull-text access may be available. Sign in or learn about subscription options.pp. 236-241
by Florian Schimanke, Robert Mertens, Felix Prankel
SpotiView: Partial Face Display Method for Smooth Communication While Protecting PrivacyFull-text access may be available. Sign in or learn about subscription options.pp. 242-249
by Ryota Kishimoto, Shuhei Tsuchida, Tsutomu Terada, Masahiko Tsukamoto
Characterizing students behavior in multi-user multi-computer testing environmentsFull-text access may be available. Sign in or learn about subscription options.pp. 250-254
by Rajini Chittimalla, Sujung Choi, Madhu Sai Vineel Reka, Yassine Belkhouche
Evaluating Interactive Concept Maps Produced from E-PortfoliosFull-text access may be available. Sign in or learn about subscription options.pp. 255-260
by Alexander Gantikow, Andreas Isking, Wolfgang Müller, Paul Libbrecht, Sandra Rebholz
Gender Stereotypes in the Creation of Educational Cases with ChatGPTFull-text access may be available. Sign in or learn about subscription options.pp. 261-266
by Gabriel Valerio-Ureña, Giomara Sevilla-Campoverde, Soledad Ortúzar, Christian Lazcano
Multi-View Gesture Recognition in Conflict SituationsFull-text access may be available. Sign in or learn about subscription options.pp. 267-268
by Karam Tomotaki-Dawoud, Birgit Nierula, Farelle Toumaleu Siewe, Thomas Koch, Daniel Johannes Meyer, Andreas Bock, Marianne Heinze, Daniela Knuth, Denis Martin, Julia Schander, Anna Hilsmann, Peter Eisert, Sebastian Bosse
PanoramaViewer – A Framework for Educational Collaborative Virtual Field TripsFull-text access may be available. Sign in or learn about subscription options.pp. 269-274
by Mario Wolf, Sebastian Hartwig, Gregor Steinhöfel, Heinrich Söbke, Eckhard Kraft
Real-time Multi-modal Highlight Prediction for Simultaneous Viewing of Multiple Live StreamsFull-text access may be available. Sign in or learn about subscription options.pp. 275-278
by Yusuke Maeda, Takahiro Hayashi
Slide Analysis Method for Editing Lecture Materials based on Hierarchical Structures of Subject TerminologiesFull-text access may be available. Sign in or learn about subscription options.pp. 279-284
by Itsuki Sano, Yuanyuan Wang, Yukiko Kawai, Kazutoshi Sumiya
The ≪Huh?≫ Button: Improving Understanding in Educational Videos with Large Language ModelsFull-text access may be available. Sign in or learn about subscription options.pp. 285-289
by Boris Ruf, Marcin Detyniecki
Author IndexFreely available from IEEE.pp. 291-293
Showing 66 out of 66