|
|
|
| Nov 9th, DAY 1 |
| Type |
Authors |
Title |
Session |
Start |
End |
| Tutorials |
Junyeong Kim | Deep Learning for Vision and Language Reasoning | 1 | 09:00 | 12:00 |
| Zhijian Ou | State-of-the-Art of End-to-End Speech Recognition | 2 | 09:00 | 12:00 |
| Shang-Hong Lai, Che-Tsung Lin, Chiou-Ting Hsu | Deep Domain Adaptation for Computer Vision | 1 | 14:00 | 17:00 |
| Taiji Suzuki | Deep Learning Theory from Statistics to Optimization | 2 | 14:00 | 17:00 |
|
Nov 10th, DAY 2
|
| Type |
Paper ID |
Authors |
Title |
Session Chair |
Start |
End |
| Opening
| Christian Wallraven
| 8:30 |
9:00 |
| KEYNOTE |
- |
LEI ZHANG |
Gradient centralization and feature gradient decent for deep neural network optimization |
Cheng-Lin Liu |
9:00 |
10:00 |
| COFFEE |
| MEDICAL |
196 |
Kun Yan, Zhizhe Liu, Shuai Zheng, Zhenyu Guo, Zhenfeng Zhu and Yao Zhao |
Coarse-to-fine learning framework for semi-supervised multimodal MRI synthesis |
Han-Jeong Hwang |
10:20 |
10:40 |
| 44 |
Zhan Zhang, Yun-Tian Wang, Bang Li, An Guo and Cheng-Lin Liu |
Deep Rejoining Model for Oracle Bone Fragment Images |
10:40 |
11:00 |
| 140 |
Guodong Sun, Zejin Wang, Guoqing Li and Hua Han |
Robust Frequency-Aware Instance Segmentation for Serial Tissue Sections |
11:00 |
11:20 |
| 72 |
Gun-Hee Lee, Han-Bin Ko and Seong-Whan Lee |
Joint Dermatological Lesion Classification and Confidence Modeling with Uncertainty Estimation |
11:20 |
11:40 |
| LUNCH BREAK |
| HUMAN SIGNALS |
195 |
Luhui Yue, Junxia Li and Qingshan Liu |
Causal Intervention Learning For Multi-Person Pose Estimation |
Sungjoon Choi |
14:00 |
14:20 |
| 20 |
Pengfei Zhang, Xiang Li, Jianjun Qian, Zhong Jin and Jian Yang |
Hierarchical Attentive Upsampling on Input Signals for Remote Heart Rate Estimation |
14:20 |
14:40 |
| HUMAN IN THE LOOP |
104 |
Doo Yon Kim and Christian Wallraven |
Label quality in AffectNet: results of crowd-based re-annotation |
Jin Xie |
14:40 |
15:00 |
| 102 |
Ashish Menon, Piyush Singh, P. K. Vinod and C. V. Jawahar |
Interactive Learning for Assisting Whole Slide Image Annotation |
15:00 | 15:20 |
| 89 |
Hoe Sung Ryu, Uijong Ju and Christian Wallraven |
Predicting decision-making in the future: Human versus Machine |
15:20 | 15:40 |
| COFFEE |
| KEYNOTE |
|
ANDREAS DENGEL |
Combining Bird Eye View and Grass Root View for Earth Observation |
Christian Wallraven |
16:00 |
17:00 |
| SPOTLIGHTS + POSTERS |
17:00 |
18:30 |
|
Nov 11th, DAY 3
|
| Type |
Paper ID |
Authors |
Title |
Session Chair |
Start |
End |
| KEYNOTE |
- |
JURE LESKOVEC |
Graph Neural Networks and Beyond |
Seong-Whan Lee |
9:00 |
10:00 |
| BREAK |
10:00 |
10:20 |
| MATCHING |
131 |
Jin Zhang, Mingyang Zhao, Xin Jiang and Dong-Ming Yan |
Robust Multi-view Registration of Point Sets with Laplacian Mixture Model |
Christian Wallraven |
10:20 | 10:40 |
| 168 |
Jegoon Ryu and Sei-Ichiro Kamata |
A Fast and Accurate Point Pattern Matching Algorithm based on Multi-Hilbert Scans |
10:40 | 11:00 |
| 17 |
Zhixiong Pi, Changxin Gao and Nong Sang |
Siamese Tracking with Bilinear Features |
11:00 | 11:20 |
| 91 |
Xinlei Qi, Yaqing Ding, Jin Xie and Jian Yang |
Planar Motion Estimation for Multi-camera System |
11:20 | 11:40 |
| LUNCH BREAK |
11:40 |
14:00 |
| DEPTH |
48 |
Jian Ren, Jin Xie and Zhong Jin |
Hierarchical Multi-Scale Architecture Search for Self-Supervised Monocular Depth Estimation |
Qingshan Liu |
14:00 | 14:20 |
| 14 |
Takahiro Suzuki, Tsubasa Hirakawa, Takayoshi Yamashita and Hironobu Fujiyoshi |
1D Self-Attention Network for Point Cloud Semantic Segmentation using Omnidirectional LiDAR |
14:20 | 14:40 |
| 45 |
Yiming Tu and Jin Xie |
UnDeepLIO: Unsupervised Deep Lidar-Inertial Odometry |
14:40 | 15:00 |
| BREAK |
15:00 |
15:20 |
| SECURITY |
100 |
Glen Brown, Jesus Martinez-Del-Rincon and Paul Miller |
Least Privilege Learning |
Byoung Chul Ko |
15:20 | 15:40 |
| 120 |
Sreyasee Das Bhattacharjee and Junsong Yuan |
Multi-modal Co-training for Fake News Identification using Attention-aware Fusion |
15:40 | 16:00 |
| 84 |
Pei-Kai Huang, Ming-Chieh Chin and Chiou-Ting Hsu |
Face Anti-Spoofing via Robust Auxiliary Estimation and Discriminative Feature Learning |
16:00 | 16:20 |
| TEXT AND DOCUMENTS |
23 |
Yu-Ting Yang, Yan-Ming Zhang, Xiao-Long Yun, Fei Yin and Cheng-Lin Liu |
CASIA-onDo: A New Database for Online Handwritten Document Analysis |
Tae-Eui Kam |
16:20 | 16:40 |
| 179 |
Nam Tuan Ly, Trung Tan Ngo and Masaki Nakagawa |
A Self-Attention based Model for Offline Handwritten Text Recognition |
16:40 | 17:00 |
| SPOTLIGHTS + POSTERS |
17:00 |
18:30 |
|
Nov 12th, DAY 4
|
| Type |
Paper ID |
Authors |
Title |
Session Chair |
Start |
End |
| ALGORITHMS |
103 |
Yonghui Liang, Lu Zhang, Yuqing He, Na Xu and Mingqi Liu |
SARNN: A Spatiotemporal Prediction Model for Reducing Error Transmissions |
Takio Kurita |
9:00 | 9:20 |
| 32 |
Weiqi Zhao, Haobo Jiang and Jin Xie |
Fast Proximal Policy Optimization |
9:20 | 9:40 |
| 27 |
Xiaoling Zhou and Ou Wu |
Drop "Noise" Edge: An Approximation of the Bayesian GNNs |
9:40 | 10:00 |
| COFFEE |
10:00 |
10:20 |
| TRANSFORMERS |
24 |
Lufei Huang, Fengming Sun and Xia Yuan |
COMatchNet: Co-Attention Matching Network for Video Object Segmentation |
Christian Wallraven |
10:20 | 10:40 |
| 106 |
Tao Wang, Zhihui Lai and Heng Kong |
TFNet: Transformer Fusion Network for Ultrasonic Image Segmentation |
10:40 | 11:00 |
| 61 |
Bolin Ni, Gaofeng Meng, Shiming Xiang and Chunhong Pan |
NASformer: Neural Architecture Search for Vision Transformer |
11:00 | 11:20 |
| AWARDS & CLOSING |
Christian Wallraven |
11:20 |
12:00 |
| LUNCH BREAK |
| WORKSHOP |
- |
- |
Future Impact of AI in Real-World Applications |
Jong-Ha Lee, Byoung Chul Ko |
13:00 | 17:00 |
Poster List
|
Nov 10th, DAY 2 Poster Schedule
|
| Paper ID |
Authors |
Title |
| 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? |
|
Nov 11th, DAY 3 Poster Schedule
|
| Paper ID |
Authors |
Title |
| 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 |
|
