Preliminary Technical Program




   Important Dates


   Call for Papers

   Call for Workshop Proposals


   Keynote Speakers


   Accepted  Papers

   Camera-ready Submissions

   Paper Submissions

   Technical Program


   Visa Assistance 

   Venue & Accomodation

   General Information


Nov 9th, DAY 1
Type Authors Title Session Start End
Tutorials Shang-Hong Lai, Che-Tsung Lin, Chiou-Ting HsuDeep Domain Adaptation for Computer Vision19:0012:00
Junyeong KimDeep Learning for Vision and Language Reasoning214:0017:00
Taiji SuzukiDeep Learning Theory from Statistics to Optimization19:0012:00
Zhijian OuState-of-the-Art of End-to-End Speech Recognition214:0017:00

Nov 10th, DAY 2
Type Paper ID Authors Title Session Start End
Opening 8:30 9:00
KEYNOTE LEI ZHANG Gradient centralization and feature gradient decent for deep neural network optimization 9:00 10:00
MEDICAL 196Kun Yan, Zhizhe Liu, Shuai Zheng, Zhenyu Guo, Zhenfeng Zhu and Yao ZhaoCoarse-to-fine learning framework for semi-supervised multimodal MRI synthesis110:2010:40
44Zhan Zhang, Yun-Tian Wang, Bang Li, An Guo and Cheng-Lin LiuDeep Rejoining Model for Oracle Bone Fragment Images110:4011:00
140Guodong Sun, Zejin Wang, Guoqing Li and Hua HanRobust Frequency-Aware Instance Segmentation for Serial Tissue Sections111:0011:20
72Gun-Hee Lee, Han-Bin Ko and Seong-Whan LeeJoint Dermatological Lesion Classification and Confidence Modeling with Uncertainty Estimation111:2011:40
HUMAN SIGNALS 195Luhui Yue, Junxia Li and Qingshan LiuCausal Intervention Learning For Multi-Person Pose Estimation214:0014:20
20Pengfei Zhang, Xiang Li, Jianjun Qian, Zhong Jin and Jian YangHierarchical Attentive Upsampling on Input Signals for Remote Heart Rate Estimation214:2014:40
HUMAN IN THE LOOP 104Doo Yon Kim and Christian WallravenLabel quality in AffectNet: results of crowd-based re-annotation314:4015:00
102Ashish Menon, Piyush Singh, P. K. Vinod and C. V. JawaharInteractive Learning for Assisting Whole Slide Image Annotation315:0015:20
89Hoe Sung Ryu, Uijong Ju and Christian WallravenPredicting decision-making in the future: Human versus Machine315:2015:40
KEYNOTE ANDREAS DENGEL Combining Bird Eye View and Grass Root View for Earth Observation 16:00 17:00

Nov 11th, DAY 3
Type Paper ID Authors Title Session Start End
KEYNOTE JURE LESKOVEC Graph Neural Networks and Beyond 9:00 10:00
MATCHING 131Jin Zhang, Mingyang Zhao, Xin Jiang and Dong-Ming YanRobust Multi-view Registration of Point Sets with Laplacian Mixture Model110:2010:40
168Jegoon Ryu and Sei-Ichiro KamataA Fast and Accurate Point Pattern Matching Algorithm based on Multi-Hilbert Scans110:4011:00
17Zhixiong Pi, Changxin Gao and Nong SangSiamese Tracking with Bilinear Features111:0011:20
91Xinlei Qi, Yaqing Ding, Jin Xie and Jian YangPlanar Motion Estimation for Multi-camera System111:2011:40
DEPTH 48Jian Ren, Jin Xie and Zhong JinHierarchical Multi-Scale Architecture Search for Self-Supervised Monocular Depth Estimation214:0014:20
14Takahiro Suzuki, Tsubasa Hirakawa, Takayoshi Yamashita and Hironobu Fujiyoshi1D Self-Attention Network for Point Cloud Semantic Segmentation using Omnidirectional LiDAR214:2014:40
45Yiming Tu and Jin XieUnDeepLIO: Unsupervised Deep Lidar-Inertial Odometry214:4015:00
SECURITY 100Glen Brown, Jesus Martinez-Del-Rincon and Paul MillerLeast Privilege Learning315:2015:40
120Sreyasee Das Bhattacharjee and Junsong YuanMulti-modal Co-training for Fake News Identification using Attention-aware Fusion315:4016:00
84Pei-Kai Huang, Ming-Chieh Chin and Chiou-Ting HsuFace Anti-Spoofing via Robust Auxiliary Estimation and Discriminative Feature Learning316:0016:20
TEXT AND DOCUMENTS 23Yu-Ting Yang, Yan-Ming Zhang, Xiao-Long Yun, Fei Yin and Cheng-Lin LiuCASIA-onDo: A New Database for Online Handwritten Document Analysis416:2016:40
179Nam Tuan Ly, Trung Tan Ngo and Masaki NakagawaA Self-Attention based Model for Offline Handwritten Text Recognition416:4017:00

Nov 12th, DAY 4
Type Paper ID Authors Title Session Start End
ALGORITHMS 103Yonghui Liang, Lu Zhang, Yuqing He, Na Xu and Mingqi LiuSARNN: A Spatiotemporal Prediction Model for Reducing Error Transmissions19:009:20
32Weiqi Zhao, Haobo Jiang and Jin XieFast Proximal Policy Optimization19:209:40
27Xiaoling Zhou and Ou WuDrop "Noise" Edge: An Approximation of the Bayesian GNNs19:4010:00
TRANSFORMERS 24Lufei Huang, Fengming Sun and Xia YuanCOMatchNet: Co-Attention Matching Network for Video Object Segmentation210:2010:40
106Tao Wang, Zhihui Lai and Heng KongTFNet: Transformer Fusion Network for Ultrasonic Image Segmentation210:4011:00
61Bolin Ni, Gaofeng Meng, Shiming Xiang and Chunhong PanNASformer: Neural Architecture Search for Vision Transformer211:0011:20
AWARDS & CLOSING 11:20 12:00
WORKSHOP Wor-1Byoung Chul Ko, Jong Ha LeeFuture Impact of AI in Real-World Applications313:0017:00

DAY 2 (Nov. 10th) Poster Schedule

13: Motoshi Abe and Takio Kurita. q-Softplus Function: Extensions of Activation Function and Loss Function by using q-Space.
18: Shungo Fujii, Naoki Okamoto, Toshiki Seo, Tsubasa Hirakawa, Takayoshi Yamashita and Hironobu Fujiyoshi. Super-class Mixup for Adjusting Training Data.
42: Jiacan Zheng, Zhihui Lai, Jianglin Lu and Jie Zhou. Low-Rank Correlation Analysis for Discriminative Subspace Learning.
43: Huanyu Li, Cuicao Zhang, Chunlei Li, Zhoufeng Liu, Yan Dong and Shuili Tang. Rapid and high-purity seed grading based on pruned deep convolutional neural network.
49: Wei Tian, Dongjun Xin and Chuzheng Wang. The Comparison of Multiple Attention Mechanisms Fused with Residual Neural Network for the Classification of Focal Liver Lesions.
73: Ji-Seon Bang and Seong-Whan Lee. Motor Imagery Classification based on CNN-GRU Network with Spatio-Temporal Feature Representation.
76: Young Eun Kim and Seong-Whan Lee. Domain Generalization with Pseudo-Domain Label for Face Anti-Spoofing.
80: Hyun Seung Lee and Christian Wallraven. Visualizing the embedding space to explain the effect of knowledge distillation.
81: Kaiheng Dang, Jianhuang Lai, Junhao Dong and Xie Xiaohua. Adversarial Training Inspired Self-attention Flow for Universal Image Style Transfer.
88: Haram Joo, Inhyeok Jeong and Sang Wan Lee. Estimating the level of inference using an order-mimic agent.
93: Tian Li, Kun Huang, Yuhan Zhang, Mingchao Li, Weiwei Zhang and Qiang Chen. Multi-stage domain adaptation for subretinal uid classication in cross-device OCT images.
94: Yuichi Kamata, Moyuru Yamada, Keizo Kato, Akira Nakagawa and Takayuki Okatani. Symbolizing Visual Features for Pre-training with Unlabeled Images.
125: He Sun, Mingkun Li and Chun-Guang Li. Hybrid Contrastive Learning with Cluster Ensemble for Unsupervised Person Re-identification.
128: Yujia Zhai, Fulin Tang and Yihong Wu. 3OFRR-SLAM: Visual SLAM with 3D-assisting Optical Flow and Refined-RANSAC.
144: Lifang Wu, Heng Zhang, Ge Shi and Sinuo Deng. Weakly Supervised Interaction Discovery Network for Image Sentiment Analysis.
147: Jian Pang, Weifeng Liu, Baodi Liu, Kai Zhang, Dapeng Tao and Xiaoping Lu. Interference Distillation for Underwater Fish Recognition.
150: Jinhyo Shin and Wonzoo Chung. Motor Imagery Classification based on local log Riemannian distance matrices selected by confusion area score.
178: Zhoufeng Liu, Chengli Gao, Chunlei Li, Ning Huang and Zijing Guo. Unsupervised Fabric Defect Detection Based on DCGAN with Component-encoder.
190: Sreyasee Das Bhattacharjee and Junsong Yuan. Proactive Student Persistence Prediction in MOOCs via Multi-Domain Adversarial Learning.
191: Jinhong Yu and Kun Sun. A Multi-feature Embedding Method for Robust Image Matching.
55: Ayan Banerjee, Shivakumara Palaiahnakote, Soumyajit Pal, Umapada Pal and Cheng-Lin Liu. DCT-DFT-FFT based Method for Text Detection in Underwater Images.
10: Sangwon Kim, In-Su Jang and Byoungchul Ko. Image Registration Between Real Image and Virtual Image Based on Self-Supervised Keypoint Learning.
28: Xuran Xu, Tong Zhang, Chunyan Xu and Zhen Cui. Circulant Tensor Graph Convolutional Network for Text Classification.
50: Abhishek Srivastava, Sukalpa Chanda and Umapada Pal. Exploiting Multi-Scale Fusion, Spatial Attention and Patch Interaction Techniques for Text-Independent Writer Identification.
51: Tamal Chowdhury, Sukalpa Chanda, Saumik Bhattacharya, Soma Biswas and Umapada Pal. Contact-Less Heart Rate Detection in Low Light Videos.
65: Kento Terauchi and Keiji Yanai. Pose Sequence Generation with a GCN and an Initial Pose Generator.
95: Miseon Shim, Seung-Hwan Lee and Han-Jeong Hwang. Development of a resting-state electroencephalography (EEG)-based computer-aided diagnosis (CAD) system for first-episodic drug-naïve female major depressive disorder.
111: Daehyun Cho and Christian Wallraven. Paperswithtopic: Topic Identification from PaperTitle Only.
118: Juho Lee, Jin Woo Choi and Sungho Jo. Subject-Independent Motor Imagery EEG Classification Based on Graph Convolutional Network.
157: Yuhang Chen, Bolin Ni and Gaofeng Meng. Joint Semantic Segmentation and Edge Detection for Waterline Extraction.
170: Pilhyeon Lee, Sunhee Hwang, Seogkyu Jeon and Hyeran Byun. Subject Adaptive EEG-based Visual Recognition.
172: Wonjun Ko, Eunjin Jeon and Heung-Il Suk. Spectro-Spatio-Temporal EEG Representation Learning for Imagined Speech Recognition.
175: Jinyoung Choi, Sehyeon Jang and Sung Chan Jun. Is notable EEG feature extracted over time-dependent cognitive load variation during intelligence tests?.

DAY 3 (Nov. 11th) Poster Schedule

6: Kai Li, Yongsheng Zhang, Weiming Yang, Lei Zhang and Zhenchao Zhang. Intelligent recognition of point source target image control points with simulation datasets.
7: Keiichi Yamada and Susumu Matsumi. One-Shot Image Learning Using Test-Time Augmentation.
12: Jiang Zhentao, Chen Qiang, Jiang Bo, Leng Cong and Cheng Jian. Weakly Supervised Salient Object Detection with Box Annotation.
25: Fengming Sun, Lufei Huang, Xia Yuan and Chunxia Zhao. Foreground-Background Collaboration Network for Salient Object Detection.
38: Fan Gao, Ying Hu and Yan Yan. Deep Siamese Network with Co-Channel and Cr-Spatial Attention For Object Tracking.
41: Serin Park and Christian Wallraven. Comparing Facial Expression Recognition in Humans and Machines: Using CAM, GradCAM, and Extremal Perturbation.
53: Yikai Bian, Jin Xie and Jianjun Qian. Unsupervised Domain Adaptive Point Cloud Semantic Segmentation.
59: Tingting Wang, Yang Xu, Zebin Wu and Zhihui Wei. Spatial-Spectral Joint Correction Network for Hyperspectral and Multispectral Image Fusion.
63: Jui Chang, Yu-Ting Pang and Chiou-Ting Hsu. Towards the Target: Self-Regularized Progressive Learning for Unsupervised Domain Adaptation on Semantic Segmentation.
108: Jin Liu and Yazhou Liu. Spatial Pyramid-based Wavelet Embedding Deep Convolutional Neural Network for Semantic Segmentation.
112: Qifeng Luo, Ting-Bing Xu and Zhenzhong Wei. CFFNet: Cross-scale Feature Fusion Network for Real-time Semantic Segmentation.
132: Farzeen Munir, Shoaib Azam, Unse Fatima and Moongu Jeon. ARTSeg: Employing Attention for Thermal images Semantic Segmentation.
143: Qiuyan Tang,Jialin Ye,Fukang Chen and Xia Yuan. Attention Guided Multi-level Feedback Network for Camouflage Object Detection.
145: Sha Xie, Yuhan Zhang, Mingchao Li, Zexuan Ji, Songtao Yuan and Qiang Chen. Gaussian Distribution Prior Based Multi-view Self-supervised Learning for Serous Retinal Detachment Segmentation.
151: Sangpil Kim and Jihyun Bae. Hand Type Estimation for Hand Action Recognition.
152: Yulan Deng, Lunke Fei, Genping Zhao, Wei Jia, Jie Wen and Chunwei Tian. Joint Multi-feature Learning for Facial Age Estimation.
163: Haetsal Lee, Junghyun Cho, Ig-Jae Kim and Unsang Park. Distance-GCN for Action Recognition.
167: Hiroya Kawai, Takashi Kozu, Koichi Ito, Hwann-Tzong Chen and Takafumi Aoki. Is CNN Really Looking at Your Face?.
184: Tsung Hsuan Wu, Chun Lung Yang, Li Ling Chiu, Ting Wei Wang, Gueter Josmy Faure and Shang Hong Lai. CONFIDENCE-AWARE ANOMALY DETECTION IN HUMAN ACTIONS.
188: Yufei Sun, Yong Li and Zhen Cui. NFW: Towards National and Individual Fairness in Face Recognition.
11: Chuangquan Lin, Zhihui Lai and Jianglin Lu. Fast Deep Asymmetric Hashing for Image Retrieval.
22: Jiaman Tang, Jinwen Wu, Fei Yin and Linlin Huang. Offline Handwritten Mathematical Expression Recognition via Graph Reasoning Network.
60: Dong-Gyu Lee and Dong-Ok Won. Spatio-temporal Weight of Active Region for Human Activity Recognition.
87: Bing Liu, Zheng Wang and Jufu Feng. PalmNet: A Robust Palmprint Minutiae Extraction Network.
99: Xu Liang, Zhaoqun Li, Dandan Fan, Jinyang Yang, Guangming Lu and David Zhang. SaME: Sharpness-Aware Matching Ensemble for Robust Palmprint Recognition.
117: Oskar Natan and Jun Miura. Semantic Segmentation and Depth Estimation with RGB and DVS Sensor Fusion for Multi-view Driving Perception.
148: Truong Thanh-Nghia, Hung Tuan Nguyen, Cuong Tuan Nguyen and Masaki Nakagawa. Learning Symbol Relation Tree for Online Handwritten Mathematical Expression Recognition.
Today's Visits
Total Visits
Address: International Center for Converging Technology, Room 202, Korea University, 145 Anam-ro, Sengbuk-gu, Seoul, 02841, Korea
Tel: +82-2-3290-5920, Business License Number: 302-82-07147

E-mail comments to
Last update: 27, Jan. 2021