Technical Sessions ICONIP 2021
9 December 2021 – TS 1
TS 1-1 113 FSE: A powerful feature augmentation technique for classification task – Yaozhong Liu, Yan Yang and Md Zakir Hossain
150 UED: A Unified Encoder Decoder Network for Visual Dialog – Cheng Chen and Xiaodong Gu
192 Exploring Effective Speech Representation via ASR for High-Quality End-to-End Multispeaker TTS – Dawei Liu, Longbiao Wang, Sheng Li, Haoyu Li, Chenchen Ding, Ju Zhang and Jianwu Dang
358 A SSA-based Attention-BiLSTM model for COVID-19 prediction – Shuqi An, Shuyu Chen, Xiaohan Yuan, Lu Yuwen and Sha Mei
400 Explaining Neural Network Results By Sensitivity Analysis for Deception Detection – Xuecheng Zhang and Xuanying Zhu
589 Stress Recognition with EEG Signals Using Explainable Neural Networks and a Genetic Algorithm for Feature Selection – Eric Pan and Jessica Sharmin Rahman
TS 1-2 24 Metric Learning Based Vision Transformer For Product Matching – Lei Huang, Wei Shao, Fuzhou Wang, Weidun Xie and Ka-Chun Wong
: 30 Stochastic Recurrent Neural Network for Multistep Time Series Forecasting – Zexuan Yin and Paolo Barucca
55 Speaker Verification with Disentangled Self-Attention – Junjie Guo, Zhiyuan Ma, Haodong Zhao, Gongshen Liu and Xiaoyong Li
114 Multi Modal Normalization – Neeraj Kumar, Ankur Narang, Brejesh Lall and Srishti Goel
131 A Focally Discriminative Loss for Unsupervised Domain Adaptation – Dongting Sun, Mengzhu Wang, Xurui Ma, Tianming Zhang, Nan Yin, Wei Yu and Zhigang Luo
178 Automatic Drum Transcription with Label Augmentation using Convolutional Neural Networks – Tianyu Xu, Pei Dai, Baoyin He, Mei Zhang and Jinhui Zhu
TS 1-3 200 Adaptive Curriculum Learning for Semi-Supervised Segmentation of 3D CT-Scans – Obed Tettey Nartey, Guowu Yang, Dorothy Araba Yakoba Agyapong, Jinzhao Wu, Asare Kwadwo Sarpong and Lady Nadia Frempong
362 Genetic Algorithm and Distinctiveness Pruning in the Shallow Networks for VehicleX – Linwei Zhang and Yeu-Shin Fu
370 Stack Multiple Shallow Autoencoders into A Strong One: A New Reconstruction-based Method to Detect Anomaly – Hanqi Wang, Xing Hu, Liang Song, Guanhua Zhang, Yang Liu, Jing Liu and Linhua Jiang
375 Learning Discriminative Representation with Attention and Diversity for Large-scale Face Recognition – Zhong Zheng, Manli Zhang and Guixia Kang
448 Multi-task Perceptual Occlusion Face Detection with Semantic Attention Network – Lian Shen, Jia-Xiang Lin and Chang-Ying Wang
467 RAIDU-Net: Image Inpainting via Residual Attention Fusion and Gated Information Distillation – Xinyu Chen, Sheng Xu, Peifeng Li and Qiaoming Zhu
TS 1-4 476 Sentence Rewriting with Few-Shot Learning for Document-Level Event Coreference Resolution – Xinyu Chen, Sheng Xu, Peifeng Li and Qiaoming Zhu
  492 A Novel Metric Learning Framework for Semi-supervised Domain Adaptation – Rakesh Kumar Sanodiya, Chinmay Sharma, Sai Satwik, Aravind Challa, Sathwik Rao and Leehter Yao
495 Generating Adversarial Examples by Distributed Upsampling – Shunkai Zhou, Yueling Zhang and Jiangtao Wang
504 CPSAM: Channel and Position Squeeze Attention Module – Yuchen Gong, Zhihao Gu, Zhenghao Zhang and Lizhuang Ma
550 A Multi-Channel Graph Attention Network for Chinese NER – Yichun Zhao, Kui Meng and Gongshen Liu
578 GSNESR: A Global Social Network Embedding Approach for Social Recommendation – Bing-Biao Xiao and Jian-Wei Liu
TS 1-5 591 Classification Models for Medical Data with Interpretative Rules – Xinyue Xu, Xiang Ding, Zhenyue Qin and Yang Liu
  602 Contrastive Goal Grouping for Policy Generalization in Goal-Conditioned Reinforcement Learning – Qiming Zou and Einoshin Suzuki
612 Global Fusion Capsule Network with Pairwise-Relation Attention Graph Routing – Xinyi Li, Song Wu and Guoqiang Xiao
669 MA-GAN: A Method Based on Generative Adversarial Network for

Calligraphy Morphing – Jiaxin Zhao, Yang Zhang, Xiaohu Ma, Dongdong Yang, Yao Shen and Hualiang Jiang

701 One-Stage Open Set Object Detection with Prototype Learning – Yongyu Xiong, Peipei Yang and Cheng-Lin Liu
726 Aesthetic-aware Recommender System for Online Fashion Products – Bei Zhou, Basem Suleiman and Waheeb Yaqub
TS 1-6 60 Deep Supervised Hashing By Classification For Image Retrieval – Xiao Luo, Yuhang Guo, Zeyu Ma, Huasong Zhong, Tao Li, Wei Ju, Chong Chen and Minghua Deng
61 Towards Human-level Performance in Solving Double Dummy Bridge Problem – Szymon Kowalik and Jacek Mandziuk
102 Coarse-to-Fine Visual Place Recognition – Junkun Qi, Rui Wang, Chuan Wang and Xiaochun Cao
116 BFConv: Improving Convolutional Neural Networks with Butterfly Convolution – Dengjie Yang, Xuehui Yu, Yi Sun, Fuzhen Zhuang  Qing He and Shiwei Ye
136 Integrating Rich Utterance Features for Emotion Recognition in Multi-party Conversations – Yang Sun, Nan Yu and Guohong Fu
159 Vehicle Image Generation Going Well with the Surroundings – Jeesoo Kim, Jangho Kim, Jaeyoung Yoo, Daesik Kim and Nojun Kwak
TS 1-7 161 Scale Invariant Domain Generalization Image Recapture Detection – Jinian Luo, Jie Guo, Weidong Qiu, Zheng Huang and Hong Hui
217 Tile2vec with Predicting Noise for The Land Cover Classification – Marshal Arijona Sinaga, Fadel Muhammad Ali and Aniati Murni Arymurthy
222 A Joint Representation Learning Approach for Social Media Tag Recommendation – Xiangyu Li and Weizheng Chen
251 Identity-based Data Augmentation via Progressive Sampling for One-Shot Person Re-identification – Runxuan Si, Shaowu Yang, Jing Zhao, Haoang Chi and Yuhua Tang
252 Feature Fusion Learning Based on LSTM and CNN Networks for Trend Analysis of Limit Order Books – Xuerui Lv and Li Zhang
300 WikiFlash: Generating Flashcards from Wikipedia Articles – Yuang Cheng, Yue Ding, Sebastien Foucher, Damian Pascual, Oliver Richter, Martin Volk and Roger Wattenhofer
TS 1-8 307 Video Face Recognition with Audio-Visual Aggregation Network – Qinbo Li, Qing Wan, Sang-Heon Lee and Yoonsuck Choe
336 WaveFuse: A Unified Unsupervised Framework for Image Fusion with Discrete Wavelet Transform – Shaolei Liu, Manning Wang and Zhijian Song
383 Manipulation-invariant Fingerprints for Cross-dataset Deepfake Detection – Zuoyan Li, Wenyuan Yang, Ruixin Liu and Yuesheng Zhu
384 Low-resource Neural Machine Translation based on Improved Reptile Meta-Learning Method – Nier Wu, Hongxu Hou, Wei Zheng and Shuo Sun
391 Efficient, Low-Cost, Real-Time Video Super-Resolution Network – Guanqun Liu, Xin Wang, Daren Zha, Lei Wang and Lin Zhao
395 On the Unreasonable Effectiveness of Centroids in Image Retrieval – Mikolaj Wieczorek, Barbara Rychalska and Jacek Dabrowski

 

9 December 2021 – TS 2
TS 2-1 666 BCI Speller on Smartphone Device with Diminutive-sized Visual Stimuli – Nuray Serkali, Adai Shomanov, Madina Kudaibergenova and Min-Ho Lee
700 Examining Transfer Learning with Neural Network and Bidirectional Neural Network on Thermal Imaging for Deception Recognition – Zishan Qin, Xuanying Zhu and Tom Gedeon
741 Multi-scale Fusion Attention Network for Polyp Segmentation – Dongjin Huang, Kaili Han, Yongjie Xi and Wenqi Che
754 A Fusion Framework to Enhance sEMG-based  Gesture Recognition Using TD and FD Features – Yao Luo, Tao Luo, Qianchen Xia, Huijiong Yan, Liang Xie, Ye Yan and Erwei Yin
983 Label Aggregation for Crowdsourced Triplet Similarity Comparisons – Jiyi Li, Lucas Ryo Endo and Hisashi Kashima
97 Relation-Aware Attribute Network for Fine-Grained Clothing Recognition – Mingjian Yang, Yixin Li, Zhuo Su and Fan Zhou
TS 2-2 733 DAFD: Domain Adaptation Framework for Fake News Detection – Yinqiu Huang, Min Gao, Jia Wang and Kai Shu
739 Document Image Classification Method based on Graph Convolutional Network – Yangyang Xiong, Zhongjian Dai, Yan Liu and Xiaotian Ding
783 Continual Learning of 3D Point Cloud Generators – Michal Sadowski, Karol J. Piczak, Przemyslaw Spurek and Tomasz Trzcinski
791 Attention-Based 3D ResNet for Detection of Alzheimer’s Disease Process – Mingjin Liu, Jialiang Tang, Wenxin Yu and Ning Jiang
801 Generation of a Large-Scale Line Image Dataset with Ground Truth Texts from Page-Level Autograph Documents – Ayumu Nagai
817 DAP-BERT: Differentiable Architecture Pruning of BERT – Chung-Yiu Yau, Haoli Bai, Irwin King and Michael R. Lyu
TS 2-3 843 Trash Detection On Water Channels – Mohbat Tharani, Abdul Wahab Amin, Fezan Rasool, Muhammad Maaz, Murtaza Taj and Abubakar Muhammad
908 Tri-Transformer Hawkes Process: Three Heads are better than one -Zhi – Yan Song, Jian-Wei Liu, Lu-Ning Zhang and Ya-Nan Han
925 PhenoDeep: A deep Learning-based approach for detecting reproductive organs from the digitized herbarium specimen images – Abdelaziz Triki, Bassem Bouaziz, Jitendra Gaikwad and Walid Mahdi
927 Document-level Event Factuality Identification using Negation and Speculation Scope – Heng Zhang, Zhong Qian, Xiaoxu Zhu and Peifeng Li
938 Dynamic Network Embedding by Time-Relaxed Temporal Random Walk – Yifan Song, Darong Lai, Zhihong Chong and Zeyuan Pan
940 Dual-band Maritime Ship Classification based on Multi-layer Convolutional Features and Bayesian Decision – Zhaoqing Wu, Yancheng Cai, Xiaohua Qiu, Min Li, Yujie He, Yu Song and Weidong Du
TS 2-4 941 Context-Based Anomaly Detection via Spatial Attributed Graphs in Human Monitoring – Kang Zhang, Muhammad Fikko Fadjrimiratno and Einoshin Suzuki
969 Domain-Adaptation Person Re-Identification via Style Translation and Clustering – Peiyi Wei, Canlong Zhang, Zhixin Li, Yanping Tang and Zhiwen Wang
984 Multimodal Named Entity Recognition Via Co-attention-based Method with Dynamic Visual Concept Expansion – Xiaoyu Zhao and Buzhou Tang
1008 Ego Networks – Andrei Marin, Traian Rebedea and Ionel Hosu
1010 Cross-modal based Person Re-Identification via Channel Exchange and adversarial Learning – Xiaohui Xu, Song Wu, Shan Liu and Guoqiang Xiao
1061 SPBERT: An Efficient Pre-training BERT on SPARQL Queries for Question Answering over Knowledge Graphs – Hieu Tran, Long Phan, James Anibal, Binh T. Nguyen and Truong-Son Nguyen
TS 2-5 630 Hybrid DE-MLP-based Modeling Technique for Prediction of Alloying Element Proportions and Process Parameters – Ravindra Savangouder, Jagdish Patra and Suresh Palanisamy
94 Hierarchical Features Integration and Attention Iteration Network for Juvenile Refractive Power Prediction – Yang Zhang, Risa Higashita, Guodong Long, Rong Li, Daisuke Santo and Jiang Liu
410 Continual Learning with Laplace Operator based Node-Importance Dynamic Architecture Neural Network – Zhiyuan Li, Ming Meng, Yifan He and Yihao Liao
581 Single-Image Smoker Detection by Human-Object Interaction with Post-Refinement – Hua-Bao Ling and Dong Huang
968 Condition-Invariant Physical Adversarial Attacks via Pixel-wise Adversarial Learning – Chenchen Zhao and Hao Li
1017 Measuring Shift-invariance of Convolutional Neural Network with a Probability-incorporated Metric – Hikaru Higuchi, Satoshi Suzuki and Hayaru Shouno
TS 2-6 406 Few-shot Classification with Multi-task Self-supervised Learning – Fan Shi, Rui Wang, Sanyi Zhang and Xiaochun Cao
408 Self-Supervised Compressed Video Action Recognition via Temporal-Consistent Sampling – Pan Chen, Shaohui Lin, Yongxiang Zhang, Jiachen Xu, Xin Tan and Lizhuang Ma
431 Stack-VAE network for Zero-Shot Learning – Jinghao Xie, Jigang Wu, Tianyou Liang and Min Meng
434 TRUFM: a Transformer-guided Framework for Fine-grained Urban Flow Inference – Xinchi Zhou, Dongzhan Zhou and Lingbo Liu
436 Saliency Detection Framework Based on Deep Enhanced Attention Network – Xing Sheng, Zhuoran Zheng, Qiong Wu, Chunmeng Kang, Yunliang Zhuang, Lei Lyu and Chen Lyu
447 SynthTriplet GAN: Synthetic Query Expansion for Multimodal Retrieval – Ivona Tautkute and Tomasz Trzcinski
TS 2-7 449 SS-CCN: Scale Self-guided Crowd Counting Network – Jinfang Zheng, Jinyang Xie, Chen Lyu and Lei Lyu
  456 QS-Hyper: A Quality-Sensitive Hyper Network for the No-Reference Image Quality Assessment – Xuewen Zhang, Yunye Zhang, Wenxin Yu, Liang Nie, Ning Jiang and Jun Gong
457 An Efficient Manifold Density Estimator for All Recommendation Systems – Jacek Dabrowski, Barbara Rychalska, Michal Daniluk, Dominika Basaj, Konrad Goluchowski, Piotr Babel, Andrzej Michalowski and Adam Jakubowski
460 Cleora: A Simple, Strong and Scalable Graph Embedding Scheme – Barbara Rychalska, Piotr Babel, Konrad Goluchowski, Andrzej Michalowski, Jacek Dabrowski and Przemyslaw Biecek
463 STA3DCNN: Spatial-temporal Attention 3D Convolutional Neural Network for Citywide Crowd Flow Prediction – Gaozhong Tang, Zhiheng Zhou and Bo Li
465 Learning Pre-Grasp Pushing Manipulation of Wide and Flat Objects using Binary Masks – Jiaxi Wu, Shanlin Zhong and Yinlin Li
TS 2-8 469 Multi-DIP: A General Framework For Unsupervised Multi-degraded Image Restoration – Qiansong Wang, Xiao Hu, Haiying Wang, Aidong Men and Zhuqing Jiang
471 Multi-Attention Network for Arbitrary Style Transfer – Sihui Hua and Dongdong Zhang
475 Image Brightness Adjustment with Unpaired Training – Chaojian Liu, Hong Chen and Aidong Men
515 Self-Supervised Image-to-Text and Text-to-Image Synthesis – Anindya Sundar Das and Sriparna Saha
520 TextCut: A Multi-region Replacement Data Augmentation Approach for Text Imbalance Classification – Wanrong Jiang, Ya Chen, Hao Fu and Guiquan Liu
522 A Multi-task Model for Sentiment aided Cyberbullying Detection in Code-Mixed Indian Languages – Krishanu Maity and Sriparna Saha