Program at-a-glance

 


Sunday, December 9, 2018

13:00 - 14:00 Tutorial 1
Dr. Jiaying Liu
Dr. Wenhan Yang
Intelligent Image/Video Editing
(Building A, 3F Oxford Room)
Tutorial 2
Dr. Yuming Fang
Dr. Patrick Le Callet
Visual Quality Assessment: Theories, Methodology, and Applications
(Building A, 3F Harvard Room)
14:00 - 14:30 Coffee Break
14:30 - 15:30 Tutorial 1
Dr. Jiaying Liu
Dr. Wenhan Yang
Intelligent Image/Video Editing
(Building A, 3F Oxford Room)
Tutorial 2
Dr. Yuming Fang
Dr. Patrick Le Callet
Visual Quality Assessment: Theories, Methodology, and Applications
(Building A, 3F Harvard Room)

Monday, December 10, 2018

08:30 - 09:00 Opening Ceremony
(Building B, B1F Room A)
09:00 - 10.00 Keynote 1: Low-dimensional Models and Deep Networks for High-dimensional Data
Prof. Yi Ma
(Building B, B1F Room A)
10:00 - 10:30 Coffee Break
10:30 - 12:00 Poster session 1
(Building B, B1F Room A)
12:00 - 13:00 Lunch Break
13:00 - 15:30 Oral session 1
Multimedia Coding (I)
(Building A, 3F Oxford Room)
Oral session 2
Visual Recognition (I)
(Building A, 3F Harvard Room)
15:30 - 16:00 Coffee Break
16:00 - 17:30 Oral session 3
Multimedia Coding (II)
(Building A, 3F Oxford Room)
Oral session 4
Visual Recognition (II)
(Building A, 3F Harvard Room)
17:30 - 18:30 Break
18:30 - 21:30 Welcome Reception
(Building B, B1F Room A)

Tuesday, December 11, 2018

09:00 - 10:00 Keynote 2: A.I. in Practice
Dr. Shipeng Li
(Building B, B1F Room A)
10:00 - 10:30 Coffee Break
10:30 - 12:00 Panel
(Building B, B1F Room A)
12:00 - 13:00 Lunch Break
13:00 - 15:30 Oral session 5
Special Session
Thermal Infra-Red Image Processing
(Building A, 3F Oxford Room)
Oral session 6
Image Enhancement
(Building A, 3F Harvard Room)
15:30 - 16:00 Coffee Break
16:00 - 17:30 Oral session 7
Special Session
AI for Medical Image Analysis
(Building A, 3F Oxford Room)
Oral session 8
Machine Learning for Visual Information Processing
(Building A, 3F Harvard Room)
17:30 - 18:30 Break
18:30 - 21:30 Banquet
(Dadun Building 3F)

Wednesday December 12, 2018

09:00 - 10:00 Keynote 3: Graph Signal Processing for Machine Learning Applications: New Insights and Algorithms
Prof. Antonio Ortega
(Building B, B1F Room A)
10:00 - 10:30 Coffee Break
10:30 - 12:00 Poster session 2
(Building B, B1F Room A)
Demo session
(Building B, B1F Room A)
12:00 - 13:00 Lunch Break
13:00 - 15:30 Oral session 9
Special Session
Multimedia Content Analysis, Retrieval and Its Applications
(Building A, 3F Oxford Room)
Oral session 10
Image Processing
(Building A, 3F Harvard Room)
15:30 - 16:00 Coffee Break
16:00 - 17:30 Oral session 11
Special Session
Deep Metric Learning for Content-Based Multimedia Understanding
(Building A, 3F Oxford Room)
Oral session 12
Visual Modeling
(Building A, 3F Harvard Room)
17:30 - 18:30 Closing
(Building A, 3F Harvard Room)



Detailed Program

 



Sunday, December 9, 2018

13:00 - 14:00 Tutorial 1
(Building A, 3F Oxford Room)
Tutorial 2
(Building A, 3F Harvard Room)
Intelligent Image/Video Editing
Jiaying Liu, Peking University
Wenhan Yang, National University of Singapore
Visual Quality Assessment: Theories, Methodology, and Applications
Yuming Fang, Jiangxi University of Finance and Economics
Patrick Le Callet, Ecole polytechnique de l’Université de Nantes, France
14:00 - 14:30 Coffee Break (3F)
14:30 - 15:30 Tutorial 1
(Building A, 3F Oxford Room)
Tutorial 2
(Building A, 3F Harvard Room)
Intelligent Image/Video Editing
Jiaying Liu, Peking University
Wenhan Yang, National University of Singapore
Visual Quality Assessment: Theories, Methodology, and Applications
Yuming Fang, Jiangxi University of Finance and Economics
Patrick Le Callet, Ecole polytechnique de l’Université de Nantes, France

Monday, December 10, 2018

08:30 - 09:00 Opening Ceremony
(Building B, B1F Room A)
09:00 - 10.30 Keynote 1: Low-dimensional Models and Deep Networks for High-dimensional Data
Prof. Yi Ma

(Building B, B1F Room A)
10:00 - 10:30 Coffee Break (B1F)
10:30 - 12:00 Poster session 1
(Building B, B1F Room A)
12:00 - 13:00 Lunch Break (B1F)
13:00 - 15:30 Oral session 1: Multimedia Coding (I)
(Building A, 3F Oxford Room)
Rate-Distortion Theory for Simplified Affine Motion Compensation Used in Video Coding
Holger Meuel, Stephan Ferenz, Yiqun Liu, Jörn Ostermann
Institut für Informationsverarbeitung Leibniz Universität Hannover
Convolutional Neural Network-Based Residue Super-Resolution for Video Coding
Kang Liu, Dong Liu, Houqiang Li, Feng Wu
University of Science and Technology of China
Improving Picture Boundary Handling for Video Coding Beyond HEVC
Han Gao, Zhijie Zhao, Eckehard Steinbach, Jianle Chen
Technical University of Munich
Initial Perceived Quality Analysis for DASH Video Streaming
Jiarun Song1, Ruihuan Wang1, Fuzheng Yang1, Zhibin Ma2, Qiyong Zhao2
1Xidian Univiersity, 2Huawei Technologies Co., Ltd
Fast Plane-Based Free-viewpoint Synthesis for Real-time Live Streaming
Keisuke Nonaka, Ryosuke Watanabe, Jun Chen, Houari Sabirin, Sei Naito
KDDI Research, Inc.
Oral session 2: Visual Recognition (I)
(Building A, 3F Harvard Room)
Deep Network with Spatial and Channel Attention for Person Re-identification
Tiansheng Guo1, Dongfei Wang2, Zhuqing Jiang1, Aidong Men1, YunZhou2
1Beijing University of Posts and Telecommunications, 2Academy of Broadcasting Science
Spatiotemporal Attention on Sliced Parts for Video-based Person Re-identification
Xu Yang1, Bin Zhang1, Yuan Dong1, Fengye Xiong2, Hongliang Bai2
1Beijing University of Posts and Telecommunications, 2Beijing FaceAll Co
Comprehensive Samples Constrain for Person Search
Liangqi Li, Hua Yang and Lin Chen
Shanghai Jiao Tong University
Data Augmentation using GAN for Multi-Domain Network-based Human Tracking
Kexin Chen, Xue Zhou, Wei Xiang, Qidong Zhou
University of Electronic Science and Technology of China
Simple Iterative Clustering on Graphs for Robust Model Fitting
Hailing Luo1, Guobao Xiao2, Hanzi Wang1
1Xiamen University, 2Minjiang University
15:30 - 16:00 Coffee Break (3F)
16:00 - 17:30 Oral session 3: Multimedia Coding (II)
(Building A, 3F Oxford Room)
Optimized Spatial Recurrent Network for Intra Prediction in Video Coding
Yueyu Hu, Wenhan Yang, Sifeng Xia, Jiaying Liu
Peking University
Dense Residual Convolutional Neural Network based In-Loop Filter for HEVC
Yingbin Wang1, Han Zhu1, Yiming Li1, Zhenzhong Chen1, Shan Liu2
1Wuhan University, 2Tencent Media Lab
Estimation of Rate Control Parameters for Video Coding Using CNN
Maria Santamaria1, Ebroul Izquierdo1, Saverio Blasi2, Marta Mrak2
1Queen Mary University of London, 2British Broadcasting Corporation
Omnidirectional Video Streaming Using Visual Attention-Driven Dynamic Tiling for VR
Cagri Ozcinar1, Juli´an Cabreray2, and Aljosa Smolic1
1Trinity College Dublin, 2Universidad Polit´ecnica de Madrid
Virtual View Quality Enhancement Using Side View Information for Free Viewpoint Video
D. M. Motiur Rahaman, Manoranjan Paul, Nusrat Jahan Shoumy
Charles Sturt University
Oral session 4: Visual Recognition (II)
(Building A, 3F Harvard Room)
Convolutional Neural Networks with Generalized Attentional Pooling for Action Recognition
Yunfeng Wang1, Wengang Zhou1, Qilin Zhang2 and Houqiang Li1
1University of Science and Technology of China, 2HERE Technologies
Structurally Constrained Correlation Transfer for Zero-shot Learning
Yu Chen, Yuehan Xiong, Xing Gao, Hongkai Xiong
Shanghai Jiao Tong University
Advanced Orientation Robust Face Detection Algorithm Using Prominent Features and Hybrid Learning Techniques
Chien-Yu Chen, Jian-Jiun Ding, Hung-Wei Hsu, and Yih-Cherng Lee
National Taiwan University
CTSD: A Dataset for Traffic Sign Recognition in Complex Real-World Images
Yanting Zhang, Ziheng Wang, Yonggang Qi, Jun Liu, Jie Yang
Beijing University of Posts and Telecommunications
17:30 - 18:30 Break (3F)
18:30 - 21:30 Welcome Reception
(Building B, B1F Room A)

Poster Session 1


10:30 – 12:00, Monday, December 10, 2018
(Building B, B1F Room A)

Automated Coronary Tree Segmentation for X-ray Angiography Sequences Using Fully-convolutional Neural Networks

Lei Zhao1, Deyu Li1, Jianhui Chen2, Tao Wan1
1Beihang University, 2No. 91 Central Hospital of PLA

A Stochastic Parallel Gradient Descent Algorithm for Person Re-identification

Keyang Cheng, Fei Tao
Jiangsu University

Text Detection in Manga by Deep Region Proposal, Classification, and Regression

Wei-Ta Chu, Chih-Chi Yu
National Chung Cheng University

Fast Korean Text Detection and Recognition in Traffic Guide Signs

Hyunjun Eun, Jonghee Kim, Jinsu Kim, and Changick Kim
Korea Advanced Institute of Science and Technology

Error-Compensated Luma Modification for Color Image Coding

Chang Cui, Shuyuan Zhu, Rui Liu, Guanghui Liu and Bing Zeng
University of Electronic Science and Technology of China

A CNN-Based In-Loop Filter with CU Classification for HEVC

Yuanying Dai, Dong Liu, Zheng-Jun Zha, Feng Wu
University of Science and Technology of China

Block-based Image Coding by Compression-Constrained Transform Domain Down-Scaling

Chang Cui1, Shuyuan Zhu1, Xiandong Meng2, Shuaicheng Liu1 and Bing Zeng1
1University of Electronic Science and Technology of China, 2Hong Kong University of Science and Technology

A spatiotemporal warping-based video synchronization method for video stitching

Xue Zhou, Zheng Zhou, Shuang Cao
University of Electronic Science and Technology of China

Direct Application of Convolutional Neural Network Features to Image Quality Assessment

Xianxu Hou1, Ke Sun1, Bozhi Liu1, Yuanhao Gong1, Jonathan Garibaldi2, Guoping Qiu1,2
1Shenzhen University, Shenzhen, 2University of Nottingham

Efficient Rate Control Method for Logo Insertion Video Coding in HEVC

Yunchang Li1, Qi Jing1, Yingfan Zhang1, Jun Sun1,2
1Peking University, 2Cooperative Medianet Innovation Center

Deep Dual-view Network with Smooth Loss for Spinal Metastases Classification

Haoyan Guan1, Guangyu Yao2, Yexun Zhang1, Yujun Gu1, Hui Zhao2, Ya Zhang1, Xiao Gu1
1Shanghai Jiaotong University, 2Shanghai Sixth People’s Hospital

Eye Movement Pattern Modeling and Visual Comfort Viewing S3D Images

Chi Zhang1, Jun Zhou1, Xiao Gu1, Shouchen Zhu1, Alan. C. Bovik2
1Shanghai Jiao Tong University, 2The University of Texas at Austin

High Efficient VR Video Coding Based on Auto Projection Selection Using Transferable Features

Lili Zhao, Meng Zhang, Wenyi Wang, Rumin Zhang, Liaoyuan Zeng, Jianwen Chen
University of Electronic Science and Technology of China

Stereoscopic Image Quality Assessment Based on both Distortion and Disparity

Yuzhen Niu, Yini Zhong, Xiao Ke, Yiqing Shi
Fuzhou University

A Statistical-based Rate Adaptation Approach for Short Video Service

Chao Zhou, Shucheng Zhong, Yufeng Geng, Bing Yu
Beijing Kuaishou Technology Co., Ltd

Combining Intra Block Copy and Neighboring Samples Using Convolutional Neural Network for Image Coding

Zhaobin Zhang1, Yue Li2, Li Li1, Li Zhu1, Shan Liu3
1University of Missouri Kansas City, 2University of Science and Technology of China, 3Tencent America Media Lab

Effective Similarity Measurement for Video-based Person Re-identification

Yiheng Liu, Chao Xie, Wengang Zhou, Houqiang Li
University of Science and Technology of China

Stretching Schemes for Coding Frames of Panoramic Videos in Craster Parabolic Projection

Saiping Zhang1, Li Li2, Mengpin Qiu1, Fuzheng Yang1 and Shuai Wan1
1Xidian University, 2Northwestern Polytechnical University

Generative Adversarial Network-Based Frame Extrapolation for Video Coding

Jianping Lin, Dong Liu, Houqiang Li, Feng Wu
University of Science and Technology of China

PANORAMA-Based Multi-Scale and Multi-Channel CNN for 3D Model Retrieval

Weizhi Nie, Kun Wang, Yao Lu, Anan Liu, Yuting Su
Tianjin University

Multi-exposure Fusion With JPEG Compression Guidance

Xingdi Zhang, Shuaicheng Liu*, Shuyuan Zhu, Bing Zeng
University of Electronic Science and Technology of China

Adaptive Motion Vector Prediction for Omnidirectional Video

Ramin Ghaznavi-Youvalari, Alireza Aminlou
Nokia Technologies

Hierarchical Discriminant Feature Learning for Heterogeneous Face Recognition

Xiaolin Xu, Yidong Li, Yi Jin, Congyan Lang, Songhe Feng, Tao Wang
Beijing Jiaotong University

Selective Convolutional Features based Generalized-mean Pooling for Fine-grained Image Retrieval

Zhuoqun Wang1, Zhu Li2, Jun Sun1, Yiling Xu1
1Shanghai Jiao Tong University, 2University of Missouri

Compressively Sensed Multi-View Image Reconstruction Using Joint Optimization Modeling

Jiale Zhu, Jin Wang, Qing Zhu
Beijing University of Technology

BAN, A Barcode Accurate Detection Network

Yuan Tiany, Zhaohui Chey, Guangtao Zhaiy, and Zhiyong Gao
Shanghai Jiao Tong University

Fast HEVC Transrating using Random Forests

Mateus Grellert1,2, Tiago Oliveira2, Carlos Rafael Duarte2, Luis A. da Silva Cruz2
1University of Coimbra, 2Catholic University of Pelotas

Point Clouds Attribute Compression Using Data-Adaptive Intra prediction

Qi Zhang, Yiting Shao, Ge Li
Peking University Shenzhen Graduate School

Dual-Layer Lossless Coding for Infrared Video

Hui-Shan Hsiao, Jui-Chiu Chiang, Wen-Hsien Shih, Wen-Nung Lie
National Chung Cheng University

Surprisingly Easy Network Compression and Data Extension for Object Instance Detection

Rui Wang1, Jingwen Xu1, Tony X Han2
1Beihang University, 2Jingchi.ai

Compressed Sensing via a Deep Convolutional Auto-encoder

Hao Wu1, Ziyang Zheng2, Yong Li1, Wenrui Dai1, Hongkai Xiong1
1Shanghai Jiao Tong University, 2University of Texas Health Science Center at Houston

SIQD: Surveillance Image Quality Database and Performance Evaluation for Objective Algorithms

Wenhan Zhu1, Guangtao Zhai1, Chen Yao2, and Xiaokang Yang1
1Shanghai Jiao Tong University, 2The Third Research Institute of Ministry of public security

Real-Time Object Tracking with Motion Information

Chaoqun Wang1, Xiaoyan Sun2, Xuejin Chen1, Wenjun Zeng2
1University of Science and Technology of China, 2Microsoft Research

Multi-Scale Deep Compressive Sensing Network

Thuong Nguyen Canh and Byeungwoo Jeon
Sungkyunkwan University



Tuesday, December 11, 2018

09:00 - 10:00 Keynote 2: A.I. in Practice
Dr. Shipeng Li

(Building B, B1F Room A)
10:00 - 10:30 Coffee Break (B1F)
10:30 - 12:00 Panel
(Building B, B1F Room A)
12:00 - 13:00 Lunch (B1F)
13:00 - 15:30 Oral session 5
Special Session: Thermal Infra-Red Image Processing

(Building A, 3F Oxford Room)
Parametric Study of Deep Perceptual Model on Visible to Thermal Face Recognition
Wei-Ta Chu, Jo-Ning Wu
National Chung Cheng University
Voting-based Hand-Waving Gesture Spotting from a Low-Resolution Far-Infrared Image Sequence
Yasutomo Kawanishi1, Chisato Toriyama1, Tomokazu Takahashi2, Daisuke Deguchi1, Ichiro Ide1, Hiroshi Murase1, Tomoyoshi Aizawa3, Masato Kawade1
1Nagoya University, 2Gifu Shotoku Gakuen University, 3OMRON Corporation
Posture Detection for Elderly using Infrared Array Sensor and Fine Tuning
Hyoga Fujita, Shingo Otsuka
Kanagawa Institute of Technology
Vehicle Detection In Thermal Images Using Deep Neural Network
Chin-Wei Chang1, Kathiravan Srinivasan2, Yung-Yao Chen3, Wen-Huang Cheng4, Kai-Lung Hua1
1National Taiwan University of Science and Technology, 2Vellore Institute of Technology, 3National Taipei University of Technology, 4National Chiao-Tung University, Hsinchu, Taiwan
Perception-based High Dynamic Range Infrared Video Coding
Yan-Jhu Chen, Wen-Hsien Shih, Jui-Chiu Chiang, Wen-Nung Lie
National Chung Cheng University
Oral session 6
Image Enhancement

(Building A, 3F Harvard Room)
SC-IQA: Shift compensation based image quality assessment for DIBR-synthesized views
Shishun Tian, Lu Zhang, Luce Morin, Olivier D´eforges
National Institute of Applied Sciences of Rennes
Light Field Image Sparse Coding via CNN-Based EPI Super-Resolution
Jinbo Zhao, Ping An, Xinpeng Huang, Liang Shan, Ran Ma
Shanghai University
Channel Attention and Multi-level Features Fusion for Single Image Super-Resolution
Yue Lu1, Yun Zhou2, Zhuqing Jiang1, Xiaoqiang Guo2, Zixuan Yang1
1Beijing University of Posts and Telecommunications, 2Academy of Broadcasting Science
Multiple Residual Learning Network for Single Image Super-Resolution
Renhe Liu, Sumei Li, Chunping Hou, Guoqing Lei
Tianjin University
BoostNet: A Structured Deep Recursive Network to Boost Image Deblocking
Chen Zhao1, Jian Zhang2, Ronggang Wang3, Wen Gao4
Peking University Shenzhen Graduate School
15:30 - 16:00 Coffee Break (3F)
16:00 - 17:30 Oral session 7
Special Session: AI for Medical Image Analysis

(Building A, 3F Harvard Room)
Stacked Fully Convolutional Networks for Pulmonary Vessel Segmentation
Yuxin Wang2, Jianjun Chen1, Chunxiao Liu1, Zhendong Mao1
1Chinese Academy of Sciences, 2University of Science and Technology of China
Automatic tissue segmentation by deep learning: from colorectal polyps in colonoscopy to abdominal organs in CT exam
Cheng-Hsien Huang1, Wei-Ting Xiao1, Li-Jen Chang2, Wei-Ta Tsai3, Wei-Min Liu1
1National Chung Cheng University, 2Chia-Yi Christian Hospital, 3Buddhist Dalin Tzu Chi Hospital
A Review of Breast Cancer Detection in Medical
Yao Lu, Jia-Yu Li, Yu-Ting Su, An-An Liu
Tianjin University
Potential of Attention Mechanism for Classification of Optical Coherence Tomography Images
Zhihua Shang, Zilong Fu, Chuanbin Liu, Hongtao Xie, Yongdong Zhang
University of Science and Technology of China
Oral session 8
Machine Learning for Visual Information Processing

(Building A, 3F Harvard Room)
A Wavelet-based Learning for Face Hallucination with Loop Architecture
Cong Geng, Li Chen, Xiaoyun Zhang, Peng Zhou, Zhiyong Gao
Shanghai Jiao Tong University
Multi-Label Deep Sparse Hashing
Venice Erin Liong1, Jiwen Lu2, Yap-Peng Tan1
1Nanyang Technological University, 2Tsinghua University
Multi-scale Spatiotemporal Information Fusion Network for Video Action Recognition
Yutong Cai1, Weiyao Lin1, John See2, Ming-Ming Cheng3, Guangcan Liu4, Hongkai Xiong1
1Shanghai Jiao Tong University, 2Multimedia University, 3Nankai University, 4Nanjing University of Information Science and Technology
Efficient Weighted Kernel Sharing Convolutional Neural Networks
Helong Zhou1, Yie-Tarng Chen1, Jie Zhang2,3, Wen-Hsien Fang1
1National Taiwan University of Science and Technology, 2Chinese Academy of Sciences, 3Seetatech Techonology Co., Ltd
17:30 - 18:30 Break (3F)
18:30 - 21:30 Banquet
(Dadun Building 3F)

Wednesday December 12, 2018

09:00 - 10:00 Keynote 3: Graph Signal Processing for Machine Learning Applications: New Insights and Algorithms
Prof. Antonio Ortega

(Building B, B1F Room A)
10:00 - 10:30 Coffee Break (B1F)
10:30 - 12:00 Poster session 2
(Building B, B1F Room A)
Demo session
(Building B, B1F Room A)
12:00 - 13:00 Lunch Break (B1F)
13:00 - 15:30 Oral session 9
Special Session: Multimedia Content Analysis, Retrieval and Its Applications

(Building A, 3F Oxford Room)
Visual Analysis of Human Motion: A Survey on Recent Advances and Applications
Qifei Wang11, Yunbo Rao2
1University of California, Berkeley, 2University of Electronic Science and Technology of China
Near-Duplicate Image Retrieval Based on Multiple Features
Xueqing Zhang
Nanjing University of Science and Technology
Improving Generative Adversarial Networks with Adaptive Control Learning
Xiaohan Ma1, Rize Jin2, Kyung-Ah Sohn1, Joon-Young Paik2, Jing Sun1, Tae-Sun Chung1
1Ajou University, 2Tianjin Polytechnic University
Synthesizing 3D Acoustic-Articulatory Mapping Trajectories: Predicting Articulatory Movements by Long-Term Recurrent Convolutional Neural Network
Lingyun Yu, Jun Yu, Qiang Ling
University of Science and Technology of China
Weighted Two-Phase Linear Reconstruction Measure-based Classification
Jianping Gou, Jun Song. Heping Song, Liangjun Wang
Jiangsu University
Oral session 10
Image Processing

(Building A, 3F Harvard Room)
Analysis of Smoothed LHE Methods for Processing Images with Optical Illusions
Prasoon Ambalathankandy, Takeshi Shimada, Shinya Takamaeda, Masato Motomura, Tetsuya Asai, Masayuki Ikebe
Hokkaido University
Low-Rank and Locally Linear Embedding Approach to Image Inpainting
Ryohei Sasaki1, Katsumi Konishi2, Tomohiro Takahashi3, Toshihiro Furukawa1
1Tokyo University of Science, 2Hosei University, 3Tokai University
Sub-window Box Filter
Yuanhao Gong, Bozhi Liu, Xianxu Hou, Guoping Qiu
Shenzhen University
A Fully Automatic Approach for Fisheye Camera Calibration
Yen-Chou Tai, Yi-Yu Hsieh, and Jen-Hui Chuang
National Chiao Tung University
15:30 - 16:00 Coffee Break (3F)
16:00 - 17:30 Oral session 11
Special Session: Deep Metric Learning for Content-Based Multimedia Understanding

(Building A, 3F Oxford Room)
FORECAST-CLSTM: A New Convolutional LSTM Network for Cloudage Nowcasting
Chao Tan1, Xin Feng1, Jianwu Long1, Li Geng2
1Chongqing University of Technology, 2New York City College of Technology of City University of New York
Joint Deep Learning for RGB-D Action Recognition
Xiaolei Qin, Yongxin Ge, Liuwei Zhan, Guangrui Li, Sheng Huang, Hongxing Wang, Feiyu Chen
Chongqing University
Video-based Parent-Child Relationship Prediction
Ying Sun, Jiachen Li, Yiwen Wei, and Haibin Yan
Beijing University of Posts and Telecommunications
A Light Deep Learning Based Method for Bank Serial Number Recognition
Ardian Umam, Jen-Hui Chuang, Dong-Lin Li
National Chiao Tung University
Multi-scale Deep Representation Learning for Face Detection
Jifei Han, Jiwen Lu, Jianjiang Feng, Jie Zhou
State Key Lab of Intelligent Technologies and Systems, Beijing National Research Center for Information Science and Technology, Tsinghua University
Oral session 12
Visual Modeling

(Building A, 3F Harvard Room)
Robust Anomaly Detection via Fusion of Appearance and Motion Features
Zhu Chen, Weihai Li, Chi Fei, Bin Liu, Nenghai Yu
Chinese Academy of Sciences, University of Science and Technology of China
Driving Maneuvers Prediction Based on Cognition-driven and Data-driven Method
Dong Zhou, Huimin Ma, Yuhan Dong
Tsinghua University
Weakly Supervised Semantic Segmentation Using Color Adjacency Loss
Youngeun Kim, Taekyung Kim, Seunghyeon Kim, and Changick Kim
Korea Advanced Institute of Science and Technology
ZipNet: ZFNet-level Accuracy with 48x Fewer Parameters
Arren Matthew C. Antioquia1,2, Daniel Stanley Tan1, Arnulfo Azcarraga2, Wen-Huang Cheng3, Kai-Lung Hua1
1National Taiwan University of Science and Technology, 2De La Salle University, 3National Chiao Tung University
17:30 - 18:30 Closing
(Building A, 3F Harvard Room)


Poster Session 2


10:30 – 12:00, Wednesday, December 12, 2018
(Building B, B1F Room A)

Multi-task Learning for Deep Semantic Hashing

Lei Ma, Hongliang Li, Qingbo Wu, Chao Shang and Kingngi Ngan
University of Electronic Science and Technology of China

FFDet: a Fully Convolutional Network for Coral Reef Fish Detection by Layer Fusion

Cuncun Shi1,2, Caiyan Jia1, Zhineng Chen2
1Beijing Jiaotong University, 2Chinese Academy of Sciences

Attribute-and-Identity Correspondence Network for Clothes Search

Jiahui Yuan, Jie Yang, Zhonghua Luo, Wei Wen
Samsung Research Institute China - Beijing

Hybrid one-shot depth measuring for stereo-view structured light systems

Sen Xiang1, Huiping Deng1, Jin Wu1, Lei Zhu1, Li Yu2
1Wuhan University of Science & Technology, 2Huazhong University of Science & Technology

Two-Stream Federated Learning: Reduce the Communication Costs

Xin Yao, Chaofeng Huang, Lifeng Sun
Tsinghua University

Deep Feature Extraction and Multi-feature Fusion for Similar Hand Gesture Recognition

Cunhuang Xie, Li Yu, Shengwei Wang
Huazhong University of Science and Technology

Motion Trajectory based Spatial-Temporal Degradation Measurement for Video Quality Assessment

Jinjian Wu, Yongxu Liu, and Guangming Shi
Xidian University

Parallel Rate Distortion Optimized Quantization for 4K Real-time GPU-based HEVC Encoder

Hiroaki Igarashi, Fumiyo Takano, Takashi Takenaka, Hiroaki Inoue, Tatsuji Moriyoshi
NEC Corporation

Multi-task CNN Model for Action Detection

Xin Chen, Yahong Han
Tianjin University

Coupled Primary and Secondary Transform for Next Generation Video Coding

Xin Zhao1, Li Li2, Zhu Li2, Xiang Li1, Shan Liu1
1Tencent America, 2University of Missouri-Kansas City

Region-based Template Matching for Decoder-Side Motion Vector Derivation

Gayathri Venugopal, Detlev Marpe, Thomas Wiegand
Fraunhofer Heinrich Hertz Institute, HHI

Two-Pass Rate Control for Constant Quality in High Efficiency Video Coding

Guiyan Cao, Xiang Pan, Yan Zhou, Yiming Li, Zhenzhong Chen
Wuhan University

Cascaded Multi-scale and Multi-dimension Convolutional Neural Network for Stereo Matching

Haihua Lu, Hai Xu, Li Zhang, Yanbo Ma, Yong Zhao
Shenzhen Graduate School, Peking University

A Novel Foveated-JND Profile Based on an Adaptive Foveated Weighting Model

Hongkui Wang1, Li Yu1, Shengwei Wang1, Guangjing Xia2, Haibing Yin3
1Huazhong University of Science and Technology, 2China Jiliang University, 3Hangzhou Dianzi University

A New Update Strategy for Blocks with Low Correlation in 3-D Recursive Search

Wontae Kim1, Sehun Kim1, Jin-Sung Kim2, and Hyuk-Jae Lee1
1Seoul National University, 2Sun Moon University

Towards Low-Complexity Scalable Coding for Ultra-High Resolution Video And Beyond

Emmanuel Thomas, Alexandre Gabriel, Omar Niamut, Sylvie Dijkstra-Soudarissan
TNO

Roads Detection of Aerial Image with FCN-CRF Model

Yunbo Rao1, Wei Liu1, Jiansu Pu1, Jianhua Deng1, Qifei Wang2
1University of Electronic Science and Technology of China, 2University of California, Berkeley

A new framework for optimal facial landmark localization on light-field images

Chiara Galdi1, Lara Younes2, Christine Guillemot2, Jean-Luc Dugelay1
1EURECOM, 2INRIA

A Sub-Partitioning Method for Point Cloud Inter-prediction Coding

Cristiano F. Santos3,1, Fernando Lopes1,5, Antonio Pinheiro1,4, Luis A. da Silva Cruz1,2
1Instituto de Telecomunicações – Coimbra, 2University of Coimbra, 3Federal University of Pelotas, 4University of Beira Interior, 5Polytechnic Institute of Coimbra

Probability-Based Intra Encoder Optimization in High Efficiency Video Coding

Hongan Wei, Minghai Wang, Yiwen Xu, Yisang Liu, Tiesong Zhao
Fuzhou University

Confusion Weighted Loss for Ambiguous Classification

Yu Lei1, Yuan Dong1, Fengye Xiong2, Hongliang Bai2, Hao Yuan1
1Beijing University of Posts and Telecommunications, 2Beijing FaceAll Co.

Weakly Supervised Semantic Segmentation by Multiple Group Cosegmentation

Kunming Luo, Fanman Meng, Qingbo Wu, Hongliang Li
University of Electronic Science and Technology of China

Probability-Based Intra Encoder Optimization in High Efficiency Video Coding

Hongan Wei, Minghai Wang, Yiwen Xu, Yisang Liu, Tiesong Zhao
Fuzhou University

Eye-tracking-Based Quality Assessment for Image Interpolation

Jinling Chen, Yiwen Xu, Ludi Wu, Yisang Liu, Tiesong Zhao
Fuzhou University

Graph Regularized and Label-matched Dictionary Learning for Video-based Person Re-identification

Lingchuan Sun1, Yun Zhou2, Jianlei Liu1, Zhuqing Jiang1, Zixuan Yang1
1Beijing University of Posts and Telecommunications, 2Academy of Broadcasting Science

Interactive Style Transfer: Towards Styling User-Specified Object

John Jethro Virtusio1,2, Arces Talavera1,2, Daniel Stanley Tan1, Kai-Lung Hua11, Arnulfo Azcarraga2
1National Taiwan University of Science and Technology, 2De La Salle University

Adaptive Weighted Bi-Prediction based on Template Similarity in Video Coding

Jue Mao1, Yin Zhao2, Weiwei Xu2, Lu Yu1
1Zhejiang University, 2Huawei Technologies Co Ltd

End-to-End Facial Image Compression with Integrated Semantic Distortion Metric

Tianyu He, Zhibo Chen
University of Science and Technology of China

Effect of Using Object Shape Prior on Visual Object Counting

Minki Jeong, Changick Kim
Korea Advanced Institute of Science and Technology

Tracklet Siamese Network with Constrained Clustering for Multiple Object Tracking

Jinlong Peng1, Fan Qiu1, John See2, Qi Guo3, Shaoshuai Huang3, Ling-Yu Duan4, Weiyao Lin1
1Shanghai Jiao Tong University, 2Multimedia University, 3SAIC Motor Corporation Limited, 4Peking University

Multiscale Progressive Image Compression Network Guided by Learnable Just Noticeable Distortion

Xin Jin, Runchun Ye, Zhibo Chen
University of Science and Technology of China

SubdSH: Subdivision-based Spherical Harmonics Field for Real-time Shading-based Refinement under Challenging Unknown Illumination

Teng Deng, Jianmin Zheng, Jianfei Cai and Tat-Jen Cham
Nanyang Technological University



Demo Session


10:30 – 12:00, Wednesday, December 12, 2018
(Building B, B1F Room A)

A Dance Movements Recognition System Based on Movement Kinematics

Chih Chieh Fang, Wei-Chen Yen, Yen-Cheng Chang, Shih-Wei Sun
Taipei National University of Art

SET: A Speech Enhancement Toolkit developed by Bio-ASP Lab

Yu Tsao
Academia Sinica

Rate-mixed HEVC Tile based 360 Video Streaming System

Ying Luo1, Xu Liu1, Chen Zhu1, Rong Xie1,2, Li Song1,2
1Shanghai Jiao Tong University, 2Cooperative Medianet Innovation Center

An improved Real-Time Video Communication System

Zhaoliang Ma1, Shengwei Yu1, Yongcheng Huang1, Rong Xie1,2, Li Song1,2
1Shanghai Jiao Tong University, 2Cooperative Medianet Innovation Center

Real-time Obstacle Detection on Embedded System

Shih-Hsuan Hung, Kuo-Wei Chen, Chien-Hua Chen, Hsuan-Ting Chou, and Chih-Yuan Yao
National Taiwan University of Science and Technology

Divide-and-conquer Jigsaw Puzzle Solving

Huang-Chia Shih and Chien-Liang Lu
Yuan Ze University

A Cloud-based Intelligent Skin and Scalp Analysis System

Wen-Shiung Huang1, Bing-Kai Hong1, Wen-Huang Cheng2, Shih-Wei Sun3, Kai-Lung Hua1
1National Taiwan University of Science and Technology, 2National Chiao Tung University, 3Taipei National University of the Arts