Accepted Papers

Papers

• Conference track papers are available at Proceedings of Machine Learning Research, Volume 101.
• Journal track papers will appear in a special issue of the Springer journal Machine Learning.

Format of presentations

• Each oral presentation consists of a 12-minute talk and a 2-minute discussion.
• Each spotlight presentation consists of a 2.5-minute talk.
• Each best paper presentation consists of a 15-minute talk and a 5-minute discussion.
• Each presentation (all of the above) are to be presented in the poster session on the same day. The size of a poster should be at largest A0 vertical (1189mm height × 841mm width) (A0 horizontal posters cannot be put up).

Program of presentations
See the program page for an overview of the schedule.
See the following pages for the detailed session schedules:

• Session 1: Deep Learning
  Day 2 (Nov.18), talks: 09:00-11:00 (5th floor Hall 1), poster session: 11:00-13:30
• Session 2: Multi-task Learning, NLP, Computer Vision, Applications
  Day 2 (Nov.18), talks: 09:00-11:00 (5th floor Hall 2), poster session: 11:00-13:30
• Best Papers in Special Session
  Day 2 (Nov.18), poster session: 11:00-13:30, talks: 15:50-16:10 & 17:20-17:40 (Nagoya Nohgakudo)
• Session 3: Supervised and General Machine Learning
  Day 3 (Nov.19), talks: 10:50-11:30 (5th floor Hall 1), poster session: 11:30-14:00
• Session 4: Unsupervised, Semi-supervised Learning, Reinforcement Learning
  Day 3 (Nov.19), talks: 10:50-11:30 (5th floor Hall 2), poster session: 11:30-14:00
• Session 5: Computer Vision
  Day 3 (Nov.19), poster session: 11:30-14:00, talks: 14:10-15:25 (5th floor Hall 1)
• Session 6: Supervised Learning
  Day 3 (Nov.19), poster session: 11:30-14:00, talks: 14:10-15:25 (5th floor Hall 2)
• Session 7: Reinforcement Learning
  Day 3 (Nov.19), poster session: 11:30-14:00, talks: 15:55-17:10 (5th floor Hall 1)
• Session 8: Unsupervised and Semi-supervised Learning
  Day 3 (Nov.19), poster session: 11:30-14:00, talks: 15:55-17:10 (5th floor Hall 2)

List of accepted papers

• Session 1 Oral Poster Mon01 Gradient Descent Optimizes Over-parameterized Deep ReLU Networks
  • DifanZou (University of California, Los Angeles); Yuan Cao (UCLA); Dongruo Zhou (UCLA); Quanquan Gu (University of California, Los Angeles) [Journal Track, Paper ID: 148]
• Session 1 Oral Poster Mon02 Efficient Diversified Mini-Batch Selection using Variable High-layer Features
  • Wanming Huang (UTS); Richard Yi Da Xu (University of Technology, Sydney); Ian Oppermann (The Treasury) [Conference Track, Paper ID: 132] <Download paper>
• Session 1 Spotlight Poster Mon03 ResNet and Batch-normalization Improve Data Separability
  • Yasutaka Furusho (Nara Institute of Science and Technology); Kazushi Ikeda (Nara Institute of Science and Technology) [Conference Track, Paper ID: 71] <Download paper>
• Session 1 Spotlight Poster Mon04 Focused Anchors Loss: cost-sensitive learning of discriminative features for imbalanced classification
  • Bahram Baloch (NUCES); Sateesh Kumar (NUCES); Sanjay Haresh (NUCES); Tahir Syed (National University of Computer and Emerging Sciences) [Conference Track, Paper ID: 324] <Download paper>
• Session 1 Spotlight Poster Mon05 Adaptive truncated residual regression for fine-grained regression problems
  • Hirotaka Hachiya (Center for Advanced Intelligence Project, RIKEN); Yamamoto Yu (Center for Advanced Intelligence Project, RIKEN); Kazuro HIrahara (Center for Advance Intelligence Project, RIKEN); Naonori Ueda (NTT) [Conference Track, Paper ID: 336] <Download paper>
• Session 1 Spotlight Poster Mon06 G-UAP: Generic Universal Adversarial Perturbation that Fools RPN-based Detectors
  • Xing Wu (SunYat-sen university); Lifeng Huang (SunYat-sen university); Chengying Gao (SunYat-sen university) [Conference Track, Paper ID: 419] <Download paper>
• Session 1 Spotlight Poster Mon07 Towards Governing Agent’s Efficacy:Action-Conditional β-VAE for Deep Transparent Reinforcement Learning
  • John Yang (Seoul National University); Gyuejeong Lee (Seoul National University); Simyung Chang (Seoul National University); Nojun Kwak (Seoul National University) [Conference Track, Paper ID: 53] <Download paper>
• Session 1 Spotlight Poster Mon08 Convolutional Neural Collaborative Filtering with Stacked Embeddings
  • Liu Han (Huazhong University of Science and Technology); Hailong Wu (Huazhong University of Science and Technology); Nan Hu (Huazhong University of Science and Technology); Binbin Qu (Huazhong University of Science and Technology) [Conference Track, Paper ID: 288] <Download paper>
• Session 1 Spotlight Poster Mon09 Investigating the effect of novel classes in semi-supervised learning
  • Yuxuan(Alex) Peng (University of Auckland); Yun Sing Koh (The University of Auckland, New Zealand); Patricia Riddle (University of Auckland, New Zealand); Bernhard Pfahringer (University of Waikato) [Conference Track, Paper ID: 271] <Download paper>
• Session 1 Spotlight Poster Mon10 From Implicit to Explicit Feedbacks: A deep neural network for modeling the sequential behaviors of online users
  • Anh Phan Tuan (Hanoi University of Science and Technology); Nhat Nguyen Trong (VCCorp Corporation); Duong Bui Trong (VCcorp Corporation); Linh Ngo Van (Hanoi University of Science and Technology); Khoat Than (Hanoi University of Science and Technology) [Conference Track, Paper ID: 416] <Download paper>
• Session 1 Spotlight Poster Mon11 Multivariate Time Series Prediction Based on Optimized Temporal Convolutional Networks with Stacked Auto-encoders
  • Yunxiao Wang (Nanjing University of Posts and Telecommunications); Zheng Liu (Nanjing University of Posts and Telecommunications); Di Hu (Nanjing University of Posts and Telecommunications); Mian Zhang (Nanjing University of Posts and Telecommunications) [Conference Track, Paper ID: 106] <Download paper>
• Session 1 Oral Poster Mon12 Regularizing Neural Networks via Stochastic Branch Layers
  • Wonpyo Park (POSTECH); Paul Hongsuck Seo (POSTECH); Bohyung Han (Seoul National University); Minsu Cho (POSTECH) [Conference Track, Paper ID: 277] <Download paper>
• Session 1 Oral Poster Mon13 Variational Conditional GAN for Fine-grained Controllable Image Generation
  • Mingqi Hu (Southeast University); Deyu Zhou (Southeast University); Yulan He (University of Warwick) [Conference Track, Paper ID: 75] <Download paper>
• Session 1 Spotlight Poster Mon14 An Anchor-Free Oriented Text Detector with Connectionist Text Proposal Network
  • Chenhui Huang (East China Normal University); Jinhua Xu (East China Normal University) [Conference Track, Paper ID: 273] <Download paper>
• Session 1 Spotlight Poster Mon15 Nuclei segmentation by using convolutional network with distance map and contour information
  • Xiaoming Liu (Wuhan University of Science and Technology); Zhengsheng Guo (Wuhan University of Science and Technology); Bo Li (Wuhan University of Science and Technology); Jun Cao (Wuhan University of Science and Technology) [Conference Track, Paper ID: 359] <Download paper>
• Session 1 Spotlight Poster Mon16 Multi-branch Siamese Network for High Performance Online Visual Tracking
  • Junfei Zhuang (Beijing University of Posts and Telecommunications & Beijing FaceAll Co); Yuan Dong ( Beijing University of Posts and Telecommunications); Hongliang Bai (Beijing Faceall Technology Co.,Ltd); wang gang (srcb) [Conference Track, Paper ID: 252] <Download paper>
• Session 1 Spotlight Poster Mon17 Forward-Backward Generative Adversarial Networks for Anomaly Detection
  • Youngnam Kim (Pohang University of Science and Technology); Seungjin Choi (BARO) [Conference Track, Paper ID: 403] <Download paper>
• Session 1 Spotlight Poster Mon18 Unpaired Data based Cross-domain Synthesis and Segmentation Using Attention Neural Network
  • Xiaoming Liu (Wuhan University of Science and Technology); Xiangkai Wei (Wuhan University of Science and Technology); Aihui Yu (Wuhan University of Science and Technology); Zhifang Pan (Wenzhou Medical University) [Conference Track, Paper ID: 364] <Download paper>
• Session 1 Spotlight Poster Mon19 Surface Reconstruction based on Self-Merging Octree with Deep Learning
  • Jian Lv (North University of China); Xie Han (North University of China); Jiajie Zheng (North University of China); Fengguang Xiong (North University of China); Min Pang (North University of China) [Conference Track, Paper ID: 342] <Download paper>
• Session 1 Spotlight Poster Mon20 Realistic Image Generation using Region-phrase Attention
  • Wanming Huang (UTS); Richard Yi Da Xu (University of Technology, Sydney); Ian Oppermann (The Treasury) [Conference Track, Paper ID: 128] <Download paper>
• Session 1 Spotlight Poster Mon21 An Encoding Adversarial Network for Anomaly Detection
  • Elies gherbi (irt-SystemX / Evry University); Blaize Hanczar (University of Evry); Jean-Christophe Janodet (University of Evry); Witold Klaudel (Renault) [Conference Track, Paper ID: 115] <Download paper>
• Session 2 Oral Poster Mon22 Communication-Efficient Distributed Multi-Task Learning with Matrix Sparsity Regularization
  • Qiang Zhou (NTU, Singapore); Yu Chen (Nanyang Technological University); Sinno Pan (NTU, Singapore) [Journal Track, Paper ID: 162]
• Session 2 Oral Poster Mon23 Few-Shot Learning with Adaptively Initialized Task Optimizer
  • Han-Jia Ye (Nanjing University); Xiang-Rong Sheng (National Key Laboratory of Novel Software Technology, Nanjing University); De-Chuan Zhan (Nanjing University) [Journal Track, Paper ID: 187]
• Session 2 Spotlight Poster Mon24 Learning to Sample Hard Instances for Graph Algorithms
  • Ryoma Sato (Kyoto University); Makoto Yamada (RIKEN AIP / Kyoto University); Hisashi Kashima (Kyoto University/RIKEN Center for AIP) [Conference Track, Paper ID: 244] <Download paper>
• Session 2 Spotlight Poster Mon25 A Model of Text-Enhanced Knowledge Graph Representation Learning with Mutual Attention
  • Yashen Wang (China Academy of Electronics and Information Technology of CETC) [Conference Track, Paper ID: 120] <Download paper>
• Session 2 Spotlight Poster Mon26 A New Multi-choice Reading Comprehension Dataset for Curriculum Learning
  • Yichan Liang (Sun Yat-sen University, China); Jianheng Li (Sun Yat-sen University, China); Jian Yin (Sun Yat-Sen University) [Conference Track, Paper ID: 295] <Download paper>
• Session 2 Spotlight Poster Mon27 An Attentive Memory Network Integrated with Aspect Dependency for Document-Level Multi-Aspect Sentiment Classification
  • Qingxuan Zhang (Beijing Institute of Technology); Chongyang Shi (Beijing Institute of Technology) [Conference Track, Paper ID: 223] <Download paper>
• Session 2 Spotlight Poster Mon28 Improving Statute Prediction via Mining Correlations between Statutes
  • Yi Feng (Nanjing University); Chuanyi Li (Nanjing University); Jidong Ge (Nanjing University); Bin Luo (Nanjing University) [Conference Track, Paper ID: 284] <Download paper>
• Session 2 Spotlight Poster Mon29 Cell-aware Stacked LSTMs for Modeling Sentences
  • Jihun Choi (Seoul National University); Taeuk Kim (Seoul National University); Sang-goo Lee (Seoul National University) [Conference Track, Paper ID: 415] <Download paper>
• Session 2 Spotlight Poster Mon30 Text Length Adaptation in Sentiment Classification
  • Reinald Kim Amplayo (University of Edinburgh); Seonjae Lim (Yonsei University); Seungwon Hwang (Yonsei University, Korea) [Conference Track, Paper ID: 275] <Download paper>
• Session 2 Spotlight Poster Mon31 Forward and Backward Knowledge Transfer for Sentiment Classification
  • Hao Wang (Southwest Jiaotong University); Bing Liu (UIC); Shuai Wang (University of Illinois at Chicago, USA); Nianzu Ma (UIC); Yan Yang (Southwest Jiaotong University) [Conference Track, Paper ID: 231] <Download paper>
• Session 2 Spotlight Poster Mon32 Effective Sentence Scoring Method Using BERT for Speech Recognition
  • Joongbo Shin (Seoul National University); Yoonhyung Lee (Seoul National University); Kyomin Jung (Seoul National University) [Conference Track, Paper ID: 392] <Download paper>
• Session 2 Oral Poster Mon33 Differentially Private Community Detection in Attributed Social Networks
  • Tianxi Ji (Case Western Reserve University); Changqing Luo (Virginia Commonwealth University); Yifan Guo (Case Western Reserve University); Jinlong Ji (Case Western Reserve University); Weixian Liao (Towson University); Pan Li (Case Western Reserve University) [Conference Track, Paper ID: 30] <Download paper>
• Session 2 Oral Poster Mon34 Fusing Recalibrated Features and Depthwise Separable Convolution for the Mangrove Bird Sound Classification
  • Chongqin Lei (CHONGQING UNIVERSITY); Gong Weiguo (Chongqing University); Zixu Wang (CHONGQING UNIVERSITY) [Conference Track, Paper ID: 347] <Download paper>
• Session 2 Spotlight Poster Mon35 SPCDet: Enhancing Object Detection with Combined Feature Fusing
  • haixin wang (Beijing Institute of Technology); lintao wu (Intel Labs China); qiongzhi wu (Beijing Institute of Technology) [Conference Track, Paper ID: 122] <Download paper>
• Session 2 Spotlight Poster Mon36 An Articulated Structure-Aware Network for 3D Human Pose Estimation
  • Zhenhua Tang (College of Computer Science and Software Engineering, Shenzhen University); Xiaoyan Zhang (College of Computer Science and Software Engineering, Shenzhen University); Junhui Hou (City University of Hong Kong, Hong Kong) [Conference Track, Paper ID: 59] <Download paper>
• Session 2 Spotlight Poster Mon37 Multi-Scale Visual Semantics Aggregation with Self-Attention for End-to-End Image-Text Matching
  • Zhuobin Zheng ( Tsinghua University); Youcheng Ben (Tsinghua University); Chun Yuan (Tsinghua University) [Conference Track, Paper ID: 348] <Download paper>
• Session 2 Spotlight Poster Mon38 Cascaded and Dual: Discrimination Oriented Network for Brain Tumor Classification
  • Wenxuan Zhang (Nanjing University of Science and Technology); Dong Zhang (Nanjing University of Science and Technology); Xinguang Xiang (NJUST) [Conference Track, Paper ID: 206] <Download paper>
• Session 2 Spotlight Poster Mon39 Software Component Prediction for Bug Reports
  • Wei Zhang (Adobe); Chris Challis (adobe) [Conference Track, Paper ID: 317] <Download paper>
• Session 2 Spotlight Poster Mon40 SDC-causing Error Detection Based on Lightweight Vulnerability Prediction
  • Cheng Liu (Nanjing University of Aeronautics and Astronautics); Jingjing Gu (Nanjing University of Aeronautics and Astronautics); Zujia Yan (Nanjing University of Aeronautics and Astronautics); Fuzhen Zhuang (Institute of Computing Technology, Chinese Academy of Sciences); Yunyun Wang (Nanjing University of Posts and Telecommunications) [Conference Track, Paper ID: 386] <Download paper>
• Session 2 Spotlight Poster Mon41 Improving Relation Classification by Entity Pair Graph
  • Yi Zhao (Beijing Jiaotong University); Huaiyu Wan (Beijing Jiaotong University); Jianwei Gao (Beijing Jiaotong University); Youfang Lin (Beijing Jiaotong University) [Conference Track, Paper ID: 406] <Download paper>
• Session 2 Spotlight Poster Mon42 Multi-modal Representation Learning for Successive POI Recommendation
  • Lishan Li (Tsinghua University); Ying Liu (Tsinghua University); Jianping Wu (Tsinghua University); Lin He (Tsinghua University); Gang Ren (Tsinghua University) [Conference Track, Paper ID: 224] <Download paper>
• Special Session Best student paper Poster Mon43 Model-Based Reinforcement Learning Exploiting State-Action Equivalence
  • Mahsa Asadi (Inria); Mohammad Sadegh Talebi (Inria); Hippolyte Bourel (ENS Rennes); Odalric Maillard (Inria) [Conference Track, Paper ID: 116] <Download paper>
• Special Session Best paper Poster Mon44 A Generalization Bound for Online Variational Inference
  • Badr-Eddine Chérief-Abdellatif (CREST); Pierre Alquier (RIKEN); Mohammad Emtiyaz Khan (RIKEN) [Conference Track, Paper ID: 276] <Download paper>
• Session 3 Spotlight Poster Tue01 Learning Weighted Top-k Support Vector Machine
  • Tsuyoshi Kato (Gunma University); Yoshihiro Hirohashi (DENSO CORPORATION) [Conference Track, Paper ID: 304] <Download paper>
• Session 3 Spotlight Poster Tue02 Multiple Empirical Kernel Learning with Discriminant Locality Preservation
  • Bolu Wang (East China University of Science and Technology); Dongdong Li (East China University of Science and Technology); Zhe Wang ( East China University of Science and Technology ) [Conference Track, Paper ID: 67] <Download paper>
• Session 3 Spotlight Poster Tue03 Optimal PAC-Bayesian Posteriors for Stochastic Classifiers and their use for Choice of SVM Regularization Parameter
  • Puja Sahu (Indian Institute of Technology Bombay); Nandyala Hemachandra (Indian Institute of Technology Bombay) [Conference Track, Paper ID: 125] <Download paper>
• Session 3 Spotlight Poster Tue04 Zero-shot Domain Adaptation Based on Attribute Information
  • Masato Ishii (The University of Tokyo/RIKEN/NEC); Takashi Takenouchi (Future University Hakodate/RIKEN Center for Advanced Intelligence Project); Masashi Sugiyama (RIKEN/The University of Tokyo) [Conference Track, Paper ID: 237] <Download paper>
• Session 3 Spotlight Poster Tue05 Kernel Learning for Data-Driven Spectral Analysis of Koopman Operators
  • Naoya Takeishi (RIKEN) [Conference Track, Paper ID: 352] <Download paper>
• Session 3 Spotlight Poster Tue06 Stochastic Gradient Trees
  • Henry Gouk (University of Edinburgh); Bernhard Pfahringer (University of Waikato); Eibe Frank (University of Waikato) [Conference Track, Paper ID: 395] <Download paper>
• Session 3 Spotlight Poster Tue07 Minimax Online Prediction of Varying Bernoulli Process under Variational Approximation
  • Kenta Konagayoshi (Kyushu University); Kazuho Watanabe (Toyohashi University of Technology) [Conference Track, Paper ID: 81] <Download paper>
• Session 3 Spotlight Poster Tue08 Learning to Aggregate: Tackling the Aggregation/Disaggregation Problem for OWA
  • Vitalik Melnikov (Paderborn University); Eyke Hüllermeier (University of Paderborn) [Conference Track, Paper ID: 397] <Download paper>
• Session 3 Spotlight Poster Tue09 Learning to Augment with Feature Side-information
  • Amina Mollaysa (university of geneva); Alexandros Kalousis (AU Geneva); Eric Bruno (Expedia); Maurits Diephuis (University of Geneva) [Conference Track, Paper ID: 111] <Download paper>
• Session 3 Spotlight Poster Tue10 Self-Paced Multi-Label Learning with Diversity
  • Seyed Amjad Seyedi (University of Kurdistan); S.Siamak Ghodsi (University of Kurdistan); Fardin Akhlaghian Tab (University of Kurdistan); Mahdi Jalili (RMIT University); Parham Moradi (University of Kurdistan) [Conference Track, Paper ID: 316] <Download paper>
• Session 3 Spotlight Poster Tue11 FEARS: a FEature And Representation Selection approach for time series classification
  • Alexis Bondu (Orange); Dominique Gay (Université de La Réunion); Vincent Lemaire (Orange); Marc Boulle (Orange Labs); Eole Cervenka (Orange) [Conference Track, Paper ID: 213] <Download paper>
• Session 3 Spotlight Poster Tue12 Prediction of Crowd Flow in City Complex with Missing Data
  • Shiyang Qiu (University of Science and Technology of China); Peng Xu (University of Science and Technology of China); Wei Zheng (Kehang Technology and Information); Wang Junjie (University of Science and Technology of China); Guo Yu (China People's Police University); Mingyao Hou (Kehang Technology and Information); Hengchang Liu (USTC) [Conference Track, Paper ID: 298] <Download paper>
• Session 4 Spotlight Poster Tue13 Self-Weighted Multi-View Clustering with Deep Matrix Factorization
  • Beilei Cui (Dalian University of Technology); Hong Yu (Dalian University of Technology); Tiantian Zhang (Dalian University of Technology); Siwen Li (Dalian University of Technology) [Conference Track, Paper ID: 263] <Download paper>
• Session 4 Spotlight Poster Tue14 Latent Multi-view Semi-Supervised Classification
  • Xiaofan Bo (University of Electronic Science and Technology); Zhao Kang (University of Electronic Science and Technology of China); Zhitong Zhao (University of Electronic Science and Technology); yuanzhang su (University of Electronic Science and Technology); Wenyu Chen (University of Electronic Science and Technology of China) [Conference Track, Paper ID: 202] <Download paper>
• Session 4 Spotlight Poster Tue15 Self-Supervised Deep Multi-View Subspace Clustering
  • Xiukun Sun (Beijing Jiaotong University); Miaomiao Cheng (Beijing Jiaotong University); Chen Min (Beijing Jiaotong University); Liping Jing (Beijing Jiaotong University) [Conference Track, Paper ID: 374] <Download paper>
• Session 4 Spotlight Poster Tue16 Geometry-Aware Maximum Likelihood Estimation of Intrinsic Dimension
  • Marina Gomtsyan (Skolkovo Institute of Science and Technology); Nikita Mokrov (Skolkovo Institute of Science and Technology); Maxim Panov (Skolkovo Institute of Science and Technology); Yury Yanovich (Skolkovo Institute of Science and Technology) [Conference Track, Paper ID: 399] <Download paper>
• Session 4 Spotlight Poster Tue17 Exemplar Based Mixture Models with Censored Data
  • Masahiro Kohjima (NTT Corporation); Tatsushi Matsubayashi (NTT Corporation); Hiroyuki Toda (NTT) [Conference Track, Paper ID: 257] <Download paper>
• Session 4 Spotlight Poster Tue18 Efficient Learning of Restricted Boltzmann Machines Using Covariance Estimates
  • Vidyadhar Upadhya (Indian Institute of Science, Bangalore); P. S.Sastry (Indian Institute of Science) [Conference Track, Paper ID: 325] <Download paper>
• Session 4 Spotlight Poster Tue19 Gradient-based Training of Slow Feature Analysis by Differentiable Approximate Whitening
  • Merlin Schueler (RUB); Hlynur Davíð Hlynsson (RUB); Laurenz Wiskott (RUB) [Conference Track, Paper ID: 139] <Download paper>
• Session 4 Spotlight Poster Tue20 Random Projection in Neural Episodic Control
  • Daichi Nishio (Kanazawa University); Satoshi Yamane (Kanazawa University) [Conference Track, Paper ID: 20] <Download paper>
• Session 4 Spotlight Poster Tue21 Active Change-Point Detection
  • Shogo Hayashi (Kyoto University); Yoshinobu Kawahara (Kyushu University / RIKEN); Hisashi Kashima (Kyoto University/RIKEN Center for AIP) [Conference Track, Paper ID: 382] <Download paper>
• Session 4 Spotlight Poster Tue22 Trust Region Sequential Variational Inference
  • Geon-Hyeong Kim (KAIST); Youngsoo Jang (KAIST); Jongmin Lee (KAIST); Wonseok Jeon (MILA, McGill University); Hongseok Yang (KAIST); Kee-Eung Kim (KAIST) [Conference Track, Paper ID: 385] <Download paper>
• Session 4 Spotlight Poster Tue23 Functional Isolation Forest
  • Guillaume Staerman (Télécom Paris); Pavlo Mozharovskyi (Télécom Paristech); Stéphan Clémençon (Télécom ParisTech); Florence d’Alche-Buc (Télécom ParisTech) [Conference Track, Paper ID: 191] <Download paper>
• Session 5 Oral Poster Tue24 Multi-width Activation and Multiple Receptive Field Networks for Dynamic Scene Deblurring
  • Cui Jinkai (Chongqing University); Li Weihong (Chongqing University); Wei Guo (Chongqing university); Gong Weiguo (Chongqing University) [Conference Track, Paper ID: 331] <Download paper>
• Session 5 Oral Poster Tue25 LADet: A Light-weight and Adaptive Network for Multi-scale Object Detection
  • Jiaming Zhou (Beihang University); Yuqiao Tian (Beihang University); Weicheng Li (Beihang University); Rui Wang (Beihang University); Zhongzhi Luan (Beihang University); Depei Qian (Beihang University) [Conference Track, Paper ID: 344] <Download paper>
• Session 5 Oral Poster Tue26 Separate Loss for Basic and Compound Facial Expression Recognition in the Wild
  • Yingjian Li (Harbin Institute of Technology (Shenzhen), Shenzhen); Yao Lu ( Harbin Institute of Technology (Shenzhen), Shenzhen); Jinxing Li (The Chinese University of Hong Kong (Shenzhen)); Guangming Lu ( Harbin Institute of Technology (Shenzhen), Shenzhen) [Conference Track, Paper ID: 343] <Download paper>
• Session 5 Oral Poster Tue27 SPoD-Net: Fast Recovery of Microscopic Images Using Learned ISTA
  • Satoshi Hara (Osaka University); Weichih Chen (National Taiwan University); Takashi Washio (The Institute of Scienti c and Industrial Research, Osaka University); Tetsuichi Wazawa (Osaka University); Takeharu Nagai (Osaka University) [Conference Track, Paper ID: 283] <Download paper>
• Session 5 Oral Poster Tue28 Capsule Networks Need an Improved Routing Algorithm
  • Inyoung Paik (Deep Bio Inc.); Injung Kim (Handong Global University); Tae-Yeong Kwak (Deep Bio Inc.) [Conference Track, Paper ID: 240] <Download paper>
• Session 6 Oral Poster Tue29 Multi-Label Optimal Margin Distribution Machine
  • Zhi-Hao Tan (Nanjing University); Peng Tan (Nanjing University); Yuan Jiang (Nanjing University); Zhi-Hua Zhou (Nanjing university) [Journal Track, Paper ID: 175]
• Session 6 Oral Poster Tue30 Multi-Label Learning with Regularization Enriched Label-Specific Features
  • Ze-Sen Chen (Southeast University); Min-Ling Zhang (Southeast University) [Conference Track, Paper ID: 222] <Download paper>
• Session 6 Oral Poster Tue31 Handling Concept Drift via Model Reuse
  • Peng Zhao (Nanjing University); Le-Wen Cai (Nanjing University); Zhi-Hua Zhou (Nanjing university) [Journal Track, Paper ID: 161]
• Session 6 Oral Poster Tue32 Deep Learning with a Rethinking Structure for Multi-label Classification
  • Yao-Yuan Yang (National Taiwan University); Yi-An Lin (National Taiwan University ); Hong-Min Chu (National Taiwan University); Hsuan-Tien Lin (National Taiwan University) [Conference Track, Paper ID: 79] <Download paper>
• Session 6 Oral Poster Tue33 Variational Inference from Ranked Samples with Features
  • Yuan Guo (Northeastern University); Jennifer Dy (Northeastern); Deniz Erdogmus (Northeastern University); Jayashree Kalpathy-Cramer (MGH/Harvard Medical School); Susan Ostmo (Oregon Health & Science University); J. Peter Campbell (Oregon Health & Science University); Michael F. Chiang (Oregon Health & Science University); Stratis Ioannidis (Northeastern University) [Conference Track, Paper ID: 267] <Download paper>
• Session 7 Oral Poster Tue34 X-Armed Bandits: Optimizing Quantiles, CVaR and Other Risks
  • Leonard Torossian (INRA-IMT); Aurélien Garivier (ENS Lyon); Victor Picheny (Prowler) [Conference Track, Paper ID: 124] <Download paper>
• Session 7 Oral Poster Tue35 A Continuous Actor-Critic Reinforcement Learning Approach to Flocking with Fixed-Wing UAVs
  • Chang Wang (NUDT); Chao Yan (NUDT); XiaojiaXiang (NUDT); HanZhou (NUDT) [Conference Track, Paper ID: 62] <Download paper>
• Session 7 Oral Poster Tue36 Real-time tree search with pessimistic scenarios: Winning the NeurIPS 2018 Pommerman Competition
  • Takayuki Osogami (IBM Research - Tokyo); Toshihiro Takahashi (IBM) [Conference Track, Paper ID: 265] <Download paper>
• Session 7 Oral Poster Tue37 Unified Policy Optimization for Robust Reinforcement Learning
  • Zichuan Lin (Tsinghua University); Li Zhao (Microsoft Research); Jiang Bian (Microsoft Research); Tao Qin (Microsoft Research Asia); Guangwen Yang (Tsinghua University) [Conference Track, Paper ID: 215] <Download paper>
• Session 7 Oral Poster Tue38 Skill-based Curiosity for Intrinsically Motivated Reinforcement Learning
  • Nicolas Bougie (National Institute of Informatics); Ryutaro Ichise (National Institute of informatics) [Journal Track, Paper ID: 150]
• Session 8 Oral Poster Tue39 Joint Consensus and Diversity for Multi-view Semi-supervised Classification
  • Wenzhang Zhuge (National Universify of Defense Technology); Chenping Hou (National University of Defense Technology); Shaoliang Peng (Hunan University); Dongyun Yi () [Journal Track, Paper ID: 28]
• Session 8 Oral Poster Tue40 Principled analytic classifier for positive-unlabeled learning via weighted integral probability metric
  • Yongchan Kwon (Seoul National University); Wonyoung Kim (Seoul National University); Masashi Sugiyama (RIKEN/The University of Tokyo); Myunghee Cho Paik (Seoul National University) [Journal Track, Paper ID: 152]
• Session 8 Oral Poster Tue41 Canonical Soft Time Warping
  • Keisuke Kawano (Toyota Central R&D Labs., Inc); Satoshi Koide (Toyota Central R&D Labs., Inc.); Takuro Kutsuna (Toyota Central R&D Labs. Inc.) [Conference Track, Paper ID: 260] <Download paper>
• Session 8 Oral Poster Tue42 Rank minimization on tensor ring: An efficient approach for tensor decomposition and completion
  • Longhao Yuan (Saitama Institute of Technology/RIKEN AIP); Chao Li (RIKEN); jianting cao (Saitama Institute of Technology); Qibin Zhao (RIKEN AIP) [Journal Track, Paper ID: 164]
• Session 8 Oral Poster Tue43 Hyperbolic Ordinal Embedding
  • Atsushi Suzuki (The University of Tokyo); Jing Wang (The University of Tokyo); Feng Tian (Bournemouth University); Atsushi Nitanda (The University of Tokyo / RIKEN); Kenji Yamanishi (The University of Tokyo) [Conference Track, Paper ID: 391] <Download paper>