Session 1: Deep Learning

Back to list of accepted papers

Information

Day 2 (Nov.18), talks: 09:00-11:00 (5th floor Hall 1), poster session: 11:00-13:30

• 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

• 09:00 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]
• 09:15 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>
• 09:30 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>
• 09:33 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>
• 09:36 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>
• 09:39 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>
• 09:42 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>
• 09:45 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>
• 09:48 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>
• 09:51 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>
• 09:54 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>
• 09:57 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>
• 10:12 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>
• 10:27 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>
• 10:30 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>
• 10:33 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>
• 10:36 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>
• 10:39 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>
• 10:42 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>
• 10:45 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>
• 10:48 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>