December 11

December 11, 2017 (Monday)

07:30 - 17:35HallwayRegistration
VIP Room, 10FDemo Session I: Video Related
Session Chair
Ramazan Savas Aygun, University of Alabama in Huntsville, USA
08:30 - 09:00Round Room II, 10FOpening Ceremony
Session Chair
Jeffrey J.P. Tsai, Asia University, Taiwan
09:00 - 09:50Round Room II, 10FKeynote I
Cinematic Virtual Reality: Immersive Video for Head-Mounted Displays
Bernd Girod, Stanford University, USA
Session Chair
Jeffrey J.P. Tsai, Asia University, Taiwan
09:50 - 10:10Coffee Break
10:10 - 12:10Round Room II, 10FSession 1: Diverse Topics
Session Chair
Frode Sandnes, Oslo and Akershus University College of Applied Sciences, Norway
12:10 - 13:00Olympus Room II, 11FLunch
13:00 - 14:15Round Room II, 10FSession 7-A: Retrieval, Recommendation, and Summarization
Session Chair
Yi Yu, National Institute of Informatics, Japan
Round Room I, 10FSession 7-B: Tracking & Matching
Session Chair
Jarno Vanne, Tampere University of Technology, Finland
14:15 - 15:35Round Room II, 10FSession 2: 360° Video & Image
Session Chair
Shervin Shirmohammadi, University of Ottawa, Canada
15:35 - 15:55Coffee Break
15:55 - 17:55Round Room II, 10FSession 3: Learning
Session Chair
Wei-Ta Chu, National Chung Cheng University, Taiwan
17:55 - 18:55Round Room I, 10FPoster Session I
Session Chair
Han C.W. Hsiao, Asia University, Taiwan
18:55 - 19:15Break
19:15 - 21:30The Grand Ballroom II, 13FReception
Session Co-Chairs
Wolfgang Huerst, Universiteit Utrecht, The Netherlands
Jianquan Liu, NEC, Japan

 

Session 1: Diverse Topics (20 min/paper)

Session Chair
Frode Sandnes, Oslo and Akershus University College of Applied Sciences, Norway

Boundary-Preserving Depth Upsampling without Texture Copying artifacts and Holes (6)
Jiji Cai, Liang Chang, Hongbin Wang, Cheolkon Jung, Joongkyu Kim

Multi-generation-robust Coding with JPEG XS (13)
Thomas Richter, Joachim Keinert, Antonin Descampe, Gael Rouvroy, Alexandre Willeme

Occlusion Robust Light Field Depth Estimation Using Segmentation Guided Bilateral Filtering (39)
Qiuxia Hou, Cheolkon Jung

Price-Based Fair Bandwidth Allocation for Networked Multimedia (86)
Hamed Hamzeh, Mahdi Hemmati, Shervin Shirmohammadi

Performance Evaluation of Walking Imagery Training Based on Virtual Environment in Brain-computer Interfaces (111)
Xiaolu Liu, Shuang Liang, Wenlong Hang, Baiying Lei, Qiong Wang, Jing Qin, Kup-Sze Choi

Image based localization based on feature scale consistency in BOF vector (142)
Mahdi Salarian

 

Session 2: 360° Video & Image (20 min/paper)

Session Chair
Shervin Shirmohammadi, University of Ottawa, Canada

A New Adaptation Approach for Viewport-adaptive 360-degree Video Streaming (62)
Duc V. Nguyen, Huyen T. T. Tran, Anh T. Pham, Truong Cong Thang

Estimation of optimal encoding ladders for tiled 360-degree VR video in adaptive streaming systems (81)
Cagri Ozcinar, Ana De Abreu, Sebastian Knorr, Aljosa Smolic

Perceptual Analysis of Perspective Projection for Viewport Rendering in 360° Images (121)
Falah Jabar, Joao Ascenso, Paula Queluz

A Cloud-Based Multi-Threaded Implementation of View Synthesis System (122)
Parvaneh Pouladzadeh, Razib Iqbal, Shervin Shirmohammadi, Omid Fatemi

 

Session 3: Learning (20 min/paper)

Session Chair
Wei-Ta Chu, National Chung Cheng University, Taiwan

Convolutional DLSTM for Crowd Scene Understanding (14)
Naifan Zhuang, Jun Ye, Kien A. Hua

Recurrent Visual Relationship Recognition with Triplet Unit (29)
Kento Masui, Akiyoshi Ochiai, Shintaro Yoshizawa, Hideki Nakayama

A Pre-Saliency Map Based Blind Image Quality Assessment via Convolutional Neural Networks (33)
Zhengxue CHENG, Masaru TAKEUCHI, Jiro KATTO

Human Action Classification Using Temporal Slicing for Deep Convolutional Neural Networks (93)
Nathan Henderson, Ramazan Aygun

Rate-Accuracy Optimization of Deep Convolutional Neural Network Models (127)
Alessandro Filini, Joao Ascenso, Riccardo Leonardi

Automatic Classification of Microstructures in Thermal Barrier Coating Images (132)
Wei-Bang Chen, Yongjin Lu, James Li, Ben Zimmerman

 

Session 7-A: Retrieval, Recommendation, and Summarization (15 min/paper)

Session Chair
Yi Yu, National Institute of Informatics, Japan

Enhancing Effectiveness of Descriptors for Searching and Recognition in Motion Capture Data (18)
Jan Sedmidubsky, Petr Elias, Pavel Zezula

Blog Article Summarization with Image-Text Alignment Techniques (19)
Wei-Ta Chu, Ming-Chih Kao

Minimum-Risk Structured Learning of Video Summarization (61)
Fairouz Hussein, Massimo Piccardi

Feature Selection for FM-based Context-Aware Recommendation Systems (124)
Xueyu Mao, Saayan Mitra, Viswanathan Swaminathan

Personalized Video Recommendations for Shared Accounts (137)
Shuo Yang, Somdeb Sarkhel, Saayan Mitra, Viswanathan Swaminathan

 

Session 7-B: Tracking & Matching (15 min/paper)

Session Chair
Jarno Vanne, Tampere University of Technology, Finland

Moment-Based Correspondence Matching Robust to Image Variation (35)
Inyong Yun, Seokhoon Boo, Joongkyu Kim, Cheolkon Jung

Very Small Moving Objects detection in Videos by Means of Fuzzy Logic and Reliability Coefficients: application to migrating birds counting (49)
Henri NICOLAS , Valentina GUERIN DETOURVILLE

A Gaze Tracking Based, Multi Modal Human Computer Interaction Concept for Efficient Input (89)
Leon Stapper, Sebastian Pospiech, Florian Bussmann, Arthur Graf, Marius Mamsch, Robert Mertens

Robust and Fast Object Tracking for Challenging 360-degree Videos (118)
Ahmad Delforouzi, Marcin Grzegorzek

Temporal Matching Kernel with Embedded Stability-Sensitive Filter (133)
Fan Yang, Sébastien Poullot, Shin’Ichi Satoh

 

Demo Session I: Video Related

Session Chair
Ramazan Savas Aygun, University of Alabama in Huntsville, USA

HEVC/H.265 4K30p Intra Encoder (15)
Arttu Ylä-Outinen, Ari Lemmetti, Marko Viitanen, Jarno Vanne, Timo D. Hämäläinen: Kvazaar

Endometriosis Annotation in Endoscopic Videos (21)
Andreas Leibetseder, Bernd Münzer, Klaus Schoeffmann, Jörg Keckstein

EndoXplore: A Web-based Video Explorer for Endoscopic Videos (68)
Bernd Muenzer, Klaus Schoeffmann, Laszlo Boeszoermenyi

The One Man Show (140)
Sai Samarth R Phaye, Love Mehta, Mukesh Saini

 

Poster Session I (Papers of Sessions 1, 2, 3, 7-A, 7-B, 7-C have to present as a poster as well.)

Session Chair
Han C.W. Hsiao, Asia University, Taiwan

A Color Prediction System for Interactive Drawing Based Image Retrieval on Mobile Devices (59)
A Gaze Tracking Based, Multi Modal Human Computer Interaction Concept for Efficient Input (49)
A New Adaptation Approach for Viewport-adaptive 360-degree Video Streaming (62)
A New Multimedia Documents Clustering Approach based on Feature Patterns Similarity (112)
A Pre-Saliency Map Based Blind Image Quality Assessment via Convolutional Neural Networks (33)
Adaptive Sparse Learning for Neurodegenerative Disease Classification (85)
Automatic Classification of Microstructures in Thermal Barrier Coating Images (132)
Blog Article Summarization with Image-Text Alignment Techniques (19)
Boundary-Preserving Depth Upsampling without Texture Copying artifacts and Holes (6)
Convolutional DLSTM for Crowd Scene Understanding (14)
Enhancing Effectiveness of Descriptors for Searching and Recognition in Motion Capture Data (18)
Estimation of optimal encoding ladders for tiled 360-degree VR video in adaptive streaming systems (81)
Feature Selection for FM-based Context-Aware Recommendation Systems (124)
Human Action Classification Using Temporal Slicing for Deep Convolutional Neural Networks (93)
Image based localization based on feature scale consistency in BOF vector (142)
Minimum-Risk Structured Learning of Video Summarization (61)
Moment-Based Correspondence Matching Robust to Image Variation (35)
Multi-generation-robust Coding with JPEG XS (13)
Occlusion Robust Light Field Depth Estimation Using Segmentation Guided Bilateral Filtering (39)
Perceptual Analysis of Perspective Projection for Viewport Rendering in 360° Images (121)
Performance Evaluation of Walking Imagery Training Based on Virtual Environment in Brain-computer Interfaces (111)
Personalized Video Recommendations for Shared Accounts (137)
Price-Based Fair Bandwidth Allocation for Networked Multimedia (86)
Recurrent Visual Relationship Recognition with Triplet Unit (29)
Robust and Fast Object Tracking for Challenging 360-degree Videos (118)
Temporal Matching Kernel with Embedded Stability-Sensitive Filter (133)
User Segment Identification based on Similarity in Content Consumption (136)
VenueNet: Fine-Grained Venue Discovery by Deep Correlation Learning (74)
Very Small Moving Objects detection in Videos by Means of Fuzzy Logic and Reliability Coefficients: application to migrating birds counting (49)