Prof. Ichiro Ide

Keynote 1: 12:00-13:00 June 6, 2022

Prof. Ichiro Ide received his BEng, MEng, and PhD from The University of Tokyo in 1994, 1996, and 2000, respectively. He became an Assistant Professor at the National Institute of Informatics, Japan in 2000. Since 2004, he has been an Associate Professor, and since 2020, a Professor at Nagoya University. He was also a Visiting Associate Professor at National Institute of Informatics from 2004 to 2010, an Invited Professor at Institut de Recherche en Informartique et Systèmes Aléatoires (IRISA), France in 2005, 2006, and 2007, a Senior Visiting Researcher at ISLA, Instituut voor Informatica, Universiteit van Amsterdam from 2010 to 2011. His research interest ranges from the analysis and indexing to retargeting of multimedia contents, especially in large-scale broadcast video archives, mostly on news, cooking, and sports contents. He is a senior member of IEEE, IEICE and IPS Japan, and a member of JSAI, ITE, and ACM.

Challenges on Bridging the Gap between Vision and Language (V&L) information

The speaker has been working on multimedia contents analysis, mostly between Vision and Language (V&L) information for the past 25 years. Thanks to the recent advancement of visual information processing tools and the increase of available real-world data, it has become realistic to analyze the general relation between V&L information. This talk introduces two such attempts; 1) Controllable image captioning which quantifies the "Imageability" (psycholingustics concept) of words / sentences, and generates captions with different levels of imageability, and 2) Modeling the relation between human motion and mimetic words which allows to describe human gaits by mimetic words, and also generate human gaits from mimetic words. The speaker believes such work will lead to bridging the gap between V&L information.

Prof. Daniel A. Keim

Keynote 2: 12:00-13:00 June 7, 2022

DANIEL A. KEIM is full professor and head of the Information Visualization and Data Analysis Research Group in the Computer and Information Science Department of the University of Konstanz, Germany. He has been actively involved in data analysis and information visualization research for more than 25 years and developed a number of novel visual analysis techniques for large data sets. He has been program co-chair of the IEEE InfoVis and IEEE VAST as well as the ACM SIGKDD conference.
Dr. Keim got his Ph.D. and habilitation degrees in computer science from the University of Munich. Before joining the University of Konstanz, Dr. Keim was associate professor at the University of Halle, Germany and Senior Technology Consultant at AT&T Shannon Research Labs, NJ, USA.

Visual Analytics: The Role of Humans in Multimedia Data Analysis

Never before in history data is generated and collected at such high volumes as it is today. For the analysis of large multimedia data sets, there is trend to fully automate the data analysis process. In this talk, we argue that for the analysis to be effective, in many cases it is important to include the human in the data exploration process and combine the flexibility, creativity, and general knowledge of humans with the analytical capabilities of today's computers. Visual analytics seeks to integrate the human in the data analysis process, applying its abilities to the large data sets. Presenting data in an interactive, graphical form provides effective ways to understand and analyze the data, allowing novel discoveries and empowering individuals to take control of the analytical process.
In the visual analysis process, it is not obvious what can be done best by automated analysis and what should be done by interactive visual methods. In dealing with massive data, the use of automated methods is mandatory, but there is also a wide range of problems where the use of interactive visual methods is beneficial. The talk discusses the different roles of interactive visualization and automated analysis techniques and exemplifies them with several application examples, illustrating the exiting potential of current visual analysis techniques but also their limitations.

Prof. Sai-Kit Yeung

Keynote 3: 12:00-13:00 June 9, 2022

Dr. Sai-Kit Yeung is an Associate Professor at the Division of Integrative Systems and Design (ISD) and the Department of Computer Science and Engineering (CSE) at the Hong Kong University of Science and Technology (HKUST). His research interests include 3D vision and graphics, content generation, fabrication, and novel computational techniques and integrative systems for marine-related problems.
Dr. Yeung has published extensively in premiere computer vision and graphics venues including numerous full oral papers in CVPR, ICCV, and AAAI. His work has received best paper honorable mention awards at ICCP 2015 and 3DV 2016. He has served as a Senior Program Committee member in IJCAI and AAAI, and as a Course Chair for SIGGRAPH Asia 2019. In addition, he regularly serves as a Technical Papers Committee member for SIGGPAPH & SIGGRAPH Asia and is currently an Associate Editor of the ACM Transactions on Graphics (TOG).

Computer Vision and Graphics for Real-World Challenges

With the recent advancements in sensing technology and pervasive computing devices, the fields of computer vision and graphics are witnessing renewed importance in addressing real-world problems. In this talk, I will be discussing my research relating to 3D reconstruction, scene understanding, content generation, and fabrication. My talk will also overview ways this core research can be used in multidisciplinary projects involving city planning, seafloor surveying, and fishery design. I will conclude my talk by discussing potential collaborative projects between computer vision, graphics, and other disciplines to address challenging issues related to human empowerment and the building of sustainable environments.

Programme overview

Programme detail

Patching Your Clothes: Semantic-aware Learning for Cloth-Changed Person Re-Identification

Shared Latent Space of Font Shapes and Their Noisy Impressions

Depthwise-separable Residual Capsule for Robust Keyword Spotting

Adversarial Attacks on Deepfake Detectors: A Practical Analysis

Multi-Modal Semantic Inconsistency Detection in Social Media News Posts

HyText – a Scene-Text Extraction Method for Video Retrieval

Personalized Fashion Recommendation using Pairwise Attention

SUnet++:Joint Demosaicing and Denoising of Extreme Low-light Raw Image

Graph Neural Networks Based Multi-Granularity Feature Representation Learning for Fine-Grained Visual Categorization

Effects and Combination of Tailored Browser-Based and Mobile Cognitive Software Training

Exploring Implicit and Explicit Relations with the Dual Relation-Aware Network for Image Captioning

AS-Net: Class-aware Assistance and Suppression Network for Few-shot Learning

Lightweight Wavelet-Based Network for JPEG Artifacts Removal

Long-range Feature Dependencies Capturing for Low-resolution Image Classification

Fast CU Depth Decision Algorithm for AVS3

Progressive GAN-based Transfer Network for Low-Light Image Enhancement

Compressive Sensing-based Image Encryption and Authentication in Edge-clouds

Leveraging Selective Prediction for Reliable Image Geolocation

PicArrange – Visually Sort, Search, and Explore Private Images on a Mac Computer

ILMICA – Interactive Learning Model of Image Collage Assessment: A Transfer Learning Approach for Aesthetic Principles

DIG: A Data-driven Impact-based Grouping Method for Video Rebuffering Optimization

Generative Landmarks Guided Eyeglasses Removal 3D Face Reconstruction

Indie Games Popularity Prediction by Considering Multimodal Features

ECAS-ML: Edge Computing Assisted Adaptation Scheme with ML for HAS

Adaptive Speech Intelligibility Enhancement for Far-and-Near-end Noise Environments Based on Self-Attention StarGAN

MoViDNN: A Mobile Platform for Evaluating Video Quality Enhancement with Deep Neural Networks

DataCAP: A Satellite Datacube and Crowdsourced Street-level Images for the Monitoring of the Common Agricultural Policy

Making Few-shot Object Detection Simpler and Less Frustrating

CDeRSNet: Towards High Performance Object Detection in Vietnamese Document Images

A Virtual Reality Reminiscence Interface for Personal Lifelog

EEG Emotion Recognition Based On Dynamically Organized Graph Neural Network

Fast Detection of Multi-Direction Remote Sensing Ship Object Based on Scale Space Pyramid

XQM: Search-Oriented vs.~Classifier-Oriented Relevance Feedback on Mobile Phones

Social event

Phu Quoc Discovery
Day: 9 June, 2022