Papers

IW-FCV2023 Online Proceeding

Proceeding Book : Download Link

Oral Papers

Oral Session 1 [Zoom Link]

Hierarchical Image Classification with Conceptual Hierarchies Generated via Lexical [Link]
Action Recognition for Each Person with Feature Extraction by Large-scale Object Detector[Link]
Structural Point Cloud Data Recovery to Learning 3D Feature Representation[Link]
Point Cloud Based Deep Molecular Pose Estimation for Structure-Based Virtual Screening[Link]
Efficient Multi-Receptive Pooling for Object Detection on Drone[Link]

Oral Session 2[Zoom Link]

Robust Scene Text Detection under Occlusion via Multi-Scale Adaptive Deep Network_Minh-Trieu Tran[Link]
Detection and Tracking of Flying Small Bats under Complex Backgrounds[Link]
Facial Depth and Normal Estimation using Single Dual-Pixel Camera[Link]
Generative Bias for Robust Visual Question Answering[Link]
DDConv Dilated Depthwise Convolution with YOLOv5 for Drone Imagery[Link]

Oral Session 3 [Zoom Link]

DASO Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning[Link]
Improvement of Robustness to Noise for Medical Image Segmentation by using Self-Supervised Learning Approach[Link]
Bidirectional Domain Mixup for Domain Adaptive Semantic Segmentation[Link]
LabOR Labeling Only if Required for Domain Adaptive Semantic Segmentation[Link]
Attribute Auxiliary Clustering for Person Re-identification[Link]

Oral Session 4 [Zoom Link]

UDA-COPE Unsupervised Domain Adaptation for Category-level Object Pose Estimation[Link]
Dynamic Circular Convolution for Image[Link]
Task-specific Scene Structure Representations[Link]
Learning Depth from Focus in the Wild[Link]
Human Face Detector with Gender Identification by Split-based Inception Block and Regulated Attention Module[Link]

Oral Session 5 [Zoom Link]

Three-dimensional structure extraction and evaluation of microvessels in cardiac tissue imaged via confocal microscopy[Link]
Multi-Attributed Face Synthesis for One-Shot Deep Face Recognition[Link]
Parallax-based Imitation Learning with Human Intervention for Uncertain Insertion Tasks[Link]
A Style-Based Caricature Generator[Link]
Detecting Mounting Behaviors of Dairy Cows by Pre-Training with Pseudo Images[Link]
Classification of Lung and Colon Cancer Using Deep Learning Method[Link]

Oral Session 6 [Zoom Link]

Reproduction of Artwork on Display using Hyperspectral Imaging and Monitor Calibration[Link]
Game Engine Compatible 3D Clothes Modeling from a Single Image[Link]
Event-Based Reflectance Separation[Link]
A Set of Control Points Conditioned Pedestrian Trajectory Prediction[Link]

Poster Papers

Poster Session 1

Format-Compatible 3D Metahuman Modeling from a Single Image_Sojin Yun[Link]
YOLO5PKLot A Parking Lot Detection Network Based on Improved YOLOv5 for Smart Parking Management System_Duy-Linh Nguyen[Link]
Texture Synthesis Based on Aesthetic Texture Perception Using CNN Style and Content Features_[Link]
Emotion Recognition by using optimised deep features_Irfan Haider[Link]
Monitoring students’ classroom attention on digital platform_Hiromasa Nakatani[Link]
Patent Image Retrieval Using Cross-entropy-based Metric Learning_Kotaro Higuchi[Link]
Pre-training of Pneumonia Classifier for Chest CT images using Fractal Database_Yuken Yoshioka[Link]
Advanced Video Inpainting method using Residual Query Connection_Youngjun La[Link]
Utilization of Temporal Detection Consistency for Improving the Multi-Object Tracking_Abhyudaya Singh Tak[Link]
A Study on Tracking Moving Objects Pig counting with YOLOv5 and StrongSORT_Seunggwan Lee[Link]
BRDF Measurement with TDCRA_Atsushi Kimura[Link]
Multi-scale Recurrent Residual U-Net for Anomaly Segmentation in Industrial Images_Haoyu Chen[Link]
LHFAN Scene Text Recognition Method Based on Multi-level Feature Fusion and Enhancement of Semantic Knowledge_Ruturaj Mahadshetti[Link]
Preliminary Study on Fish Tracking in Indoor Aquaculture through Deep Learning_Nguyen Ngoe Huynh[Link]
Front Cover Image Database of Japanese Manga and Typeface Estimation of their Title_Shota Ishiyama[Link]
Robotics Education under Pandemic Lockdown Situation._Danilo Cáceres-Hernández[Link]
Lane Detection using Canny Edge Detection Algorithm for Real-time Racing Game_Iftikhar Ahmad[Link]
Influence Analysis of Each Facial Region on Facial Expressions Recognition_Minsol Park[Link]

Poster Session 2

Diffuse Large B-cell Lymphoma Survival Prediction using Encoding Clinical Features_Phuc Pham[Link]
Robust Data Augmentation for Accurate Human Pose Estimator_SyPhue Pham[Link]
Multi-task model for glioma segmentation and isocitrate dehydrogenase status prediction using segmentation boundary_Xiaoyu Shi[Link]
Impression Estimation of Suit Patterns Based on Style Features Using Multi-scale CNN_Eiki Tsumura[Link]
A multi-layered structure of Pretrained Convolutional Neural Network for weed classification_Gwanghyun Yu[Link]
Two-stream Network for Moving Object Detection_Wisan Dhammatorn[Link]
Multimodal Transformer for Automatic Depression Estimation System_Khanh Nguyen[Link]
Motion synthesis for automatic animation of sign language_Jongho Jeong[Link]
Cattle Action Recognition with Multi-Viewpoint Cameras based on Deep Learning_Muhammad Fahad Nasir[Link]
Convolutional Neural Networks with Particle Swarm Optimization A Reliable Method for SARS-CoV-2 Detection in X-Ray Images_Atif Ali[Link]
Multi-region based radial GCN algorithm for real-time action recognition_Hanbyul Jang[Link]
Advanced Machine Learning Techniques To Identify Emotions In Texts_Zulqarnain Fareed[Link]
Object Pose Estimation Based on Template-matching Using Attention Module and Residual Block_Gaeun Noh[Link]
COVID -19 Detection based on CT Scan Images using Deep Learning Methods_Tuan Le Dinh[Link]
Change Detection Over Multispectral Images A Case Study On RUSHIKONDA_Fyzulla Shaik[Link]
Gaussian Process based Illumination Planning for Photometric Stereo_Yuji Oyamada[Link]
Classifying Breast Cancer Using Deep Convolutional Neural Network Method_Musfequa Rahman[Link]
Rough Target Region Extraction with Background Learning_Ryo Nakamura[Link]