Oral Session 1
Date & Time：13:30-15:30, August 24 Location：Meeting Room 3
（Report time is 9 minutes and question time is 3 minutes for each presentation)
| Time | Paper ID | Paper Title | Author Names |
|---|---|---|---|
| 13:30 - 13:42 | 5 | Accelerating Deep Convnets via Sparse Subspace Clustering | Dong Wang, Shengge Shi, Xiao Bai, and Xueni Zhang |
| 13:42 - 13:54 | 39 | Attention-aware Invertible Hashing Network | Shanshan Li, Qiang Cai, Zhuangzi Li, Haisheng Li, Naiguang Zhang, and Jian Cao |
| 13:54 - 14:06 | 89 | Noninvasive Epicardial and Endocardial Extracellular Potentials Imaging with Low-rank and Non-local Total Variation Regularization | Lide Mu, Huafeng Liu |
| 14:06 - 14:18 | 191 | Second-order Pooling Deep Hashing for Image Retrieval | Yongchao Yang, Jingdong Cheng, Chao Che, Jianxin Zhang, and Lin Shan |
| 14:18 - 14:30 | 193 | Spatial Probabilistic Distribution Map based 3D FCN for Visual Pathway Segmentation | Zhiqi Zhao, Danni Ai, Wenjie Li, Jingfan Fan, Hong Song, Yongtian Wang, Jian Yang |
| 14:30 - 14:42 | 276 | A Noise Robust Batch Mode Semi-supervised and Active Learning Framework for Image Classification | Chaoqun Hou, Chenhui Yang, Fujia Ren, and Rongjie Lin |
| 14:42 - 14:54 | 280 | FVCNN: Fusion View Convolutional Neural Networks for Non-rigid 3D Shape Classification and Retrieval | Yan Zhou, Fanzhi Zeng, Jiechang Qian, Yang Xiang, and Zhijian Feng |
| 14:54 - 15:06 | 303 | MMA: Motion Memory Attention Network for Video Object Detection | Huai Hu, Wenzhong Wang, Aihua Zheng, and Bin Luo |
| 15:06 - 15:18 | 321 | Towards Joint Multiply Semantics Hashing for Visual Search | Yunbo Wang and Zhenan Sun |
| 15:18 - 15:30 | 344 | Gradient Projection for Sparse Reconstruction Method for Dynamic Fluorescence Molecular Tomography | Jingxiao Fan, Hengna Zhao, Hongbo Guo, Yuqing Hou, Xiaowei He |
Oral Session 2
Date & Time：15:40 – 17:40, August 24 Location：Meeting Room 3
| Time | Paper ID | Paper Title | Author Names |
|---|---|---|---|
| 15:40 - 15:45 | 23 | No-reference Stereoscopic Video Quality Assessment Based on Spatial-temporal Statistics | Jiufa Zhang, Lixiong Liu, Jiachao Gong, and Hua Huang |
| 15:45 - 15:50 | 29 | Online Multi-Object Tracking using Single Object Tracker and Markov Clustering | Jiao Zhu, Shanshan Zhang, and Jian Yang |
| 15:50 - 15:55 | 36 | Combining Cross Entropy Loss with Manually Defined Hard Example for Semantic Image Segmentation | Zelu Deng, Jianbin Gao , and James C.Gee |
| 15:55 - 16:00 | 49 | Attribute-aware Pedestrian Image Editing | Xiaoyi Yin, Xinqian Gu, Hong Chang, Bingpeng Ma, and Xilin Chen |
| 16:00 - 16:05 | 55 | Towards Photo-Realistic Visible Watermark Removal with Conditional Generative Adversarial Networks | Xiang Li, Chan Lu, Danni Cheng, Wei-Hong Li, Mei Cao, Bo Liu, Jiechao Ma, and Wei-Shi Zheng |
| 16:05 - 16:10 | 64 | Low Resolution Person Re-identification by an Adaptive Dual-branch Network | Zhanxiang Feng, Wenxiao Zhang, Jianhuang Lai, and Xiaohua Xie |
| 16:10 - 16:15 | 68 | Personalized micro-video recommendation based on multi-modal features and user interest evolution | Yingying Jin, Juan Xu, and Xin He |
| 16:15 - 16:20 | 73 | JPEG Reversible Data Hiding with Matrix Embedding | Fangjun Huang and Jiayong Li |
| 16:20 - 16:25 | 80 | Detection and Localization of Video Object Removal by Spatio-Temporal LBP Coherence Analysis | Shanshan Bai, Haichao Yao, Rongrong Ni, and Yao Zhao |
| 16:25 - 16:30 | 85 | TQR-Net: Tighter Quadrangle-based Convolutional Neural Network for Dense Building Instance Localization in Remote Sensing Imagery | Kaiyu Jiang, Qingpeng Li |
| 16:30 - 16:35 | 121 | A Weakly Supervised Text Detection Based on Attention Mechanism | Lanfang Dong, Diancheng Zhou, and Hanchao Liu |
| 16:35 - 16:40 | 127 | Block Partitioning Decision Based on Content Complexity for Future Video Coding | Yanhong Zhang, Yao Zhao, Chunyu Lin, and Meiqin Liu |
| 16:40 - 16:45 | 135 | Modified LDE for Dimensionality Reduction of Hyperspectral Image | Lei He, Hongwei Yang, and Lina Zhao |
| 16:45 - 16:50 | 160 | Unsupervised Person Re-identification based on Clustering and Domain-invariant Network | Yangru Huang, Yi Jin, Peixi Peng, Congyan Lang, and Yidong Li |
| 16:50 - 16:55 | 186 | Tracker-Level Decision by Deep Reinforcement Learning for Robust Visual Tracking | Wenju Huang, Yuwei Wu, and Yunde Jia |
| 16:55 - 17:00 | 194 | Road Detection of Remote Sensing Image based on Convolutional Neural Network | Yuting Zhu, Jinwen Yan, Cong Wang, Yiqing Zhou |
| 17:00 - 17:05 | 212 | Scene Recognition with Comprehensive Regions Graph Modeling | Haitao Zeng and Gongwei Chen |
| 17:05 - 17:10 | 213 | Robust 3D Face Alignment with Efficient Fully Convolutional Neural Networks | Lei Jiang, Xiaojun Wu, and Josef Kittler |
| 17:10 - 17:15 | 306 | A Hybrid Convolutional Neural Network with Anisotropic Diffusion for Hyperspectral Image Classification | Feng Lu, Qichao Liu, Mohsen Molaei, Liang Xiao |
| 17:15 - 17:20 | 333 | A Comparative Study of CNN and FCN for Histopathology Whole Slide Image Analysis | Shujiao Sun, Bonan Jiang, Yushan Zheng, and Fengying Xie |
| 17:20 - 17:25 | 340 | Hybrid Simplifed Spherical Harmonics with Diffusion Equation for X-ray Luminescence Computed Tomography | Hengna Zhao, Jingxiao Fan, Hongbo Guo, Yuqing Hou, Xiaowei He |
| 17:25 - 17:30 | 368 | Realistic Modeling of Tree Ramifications from an Optimal Manifold Control Mesh | Zhengyu Huang, Zhiyi Zhang, Nan Geng, Long Yang, Dongjian He, and Shaojun Hu |
| 17:30 - 17:35 | 384 | Fitting Cuboids from the Unstructured 3D Point Cloud | Chengkun Cao and Guoping Wang |