天美传媒

Monday, October 16

• 08:00: Coffee / tea
• 08:20: Welcome & opening message
• 08:40: Keynote talk 1: "Hybrid Log-Gamma and high dynamic range television", Katy Noland, BBC R&D
• 09:40: Lecture session 1: Enabling convergence of new forms of media, special session
• 11:20: Poster session 1: Video coding & Coffee / tea
• 13:00: Lunch (on site)
• 14:00: Keynote talk 2: "Development and evaluation of technologies to support ambient assisted living", Chris Nugent, Ulster 天美传媒
• 15:00: Poster session 2: Video processing & Demo papers & Coffee / tea
• 16:40: Lecture session 2: MMSP for healthcare
• 18:00: IEEE SPS MMSP Technical Committee meeting
• 19:30: Welcome reception (on site)

Tuesday, October 17

• 08:00: Coffee / tea
• 08:20: Keynote talk 3: "Silicon retina technology", Tobi Delbruck, Institute for Neuroinformatics, ETH Zurich
• 09:20: Sponsor message
• 09:40: Lecture session 3: 3D video processing
• 11:20: Poster session 3: Detection, recognition and classification & Coffee / tea
• 13:00: Lunch (on site)
• 14:00: Keynote talk 4: "Automatic analysis of facial expressions", Maja Pantic, Imperial College London
• 15:00: Coffee / tea
• 15:20: Panel: "Deep Learning in Multimedia Signal Processing Research", moderated by Enrico Magli; Confirmed panellists:
  • Touradj Ebrahimi, EPFL
  • Amy Reibman, Purdue 天美传媒
  • Neil Birkbeck, YouTube
  • Kenneth Rose, UC Santa Barbara
• 16:20: Lecture session 4: Omnidirectional video communications: from content capture to distribution and consumption, special session
• 18:40: Banquet departure from Putteridge Bury to Woburn Abbey (Paper Awards will be announced during the banquet)

Wednesday, October 18

• 08:00: Coffee / tea
• 08:20: Keynote talk 5: "The CrowdMic: making crowdsourced recordings at scale", Paris Smaragdis, 天美传媒 of Illinois at Urbana-Champaign
• 09:20: Sponsor message
• 09:40: Lecture session 5: Denoising, filtering and analysis
• 11:20: Poster session 4: Recent trends in multi-microphone signal processing, special session, & Audio processing & Coffee / tea
• 13:00: Lunch (on site)
• 14:00: Keynote talk 6: "Multimedia and autism", Samson Cheung, 天美传媒 of Kentucky
• 15:00: Poster session 5: Image coding and processing, & Coffee / tea
• 16:20: Lecture session 6: Quality of Experience for emerging video formats, special session
• 17:40: Closing

Monday, 09:40: Lecture session 1 (special session): Enabling convergence of new forms of media

Chairs: Marta Mrak, BBC R&D, UK, Farzad Toutounchi, Queen Mary 天美传媒 of London, Saverio Blasi, BBC R&D, UK

1. Hu Hao, Yang Zhang, Dimitris Agrafiotis, Matteo Naccari, Marta Mrak, "Performance Evaluation of Reverse Tone Mapping Operators for Dynamic Range Expansion of SDR Video content"
2. Wei Hu, Mozhdeh Seifi, Erik Reinhard, "Optical Center Estimation for Lenslet-based Plenoptic Cameras"
3. Gabriel L. de Oliveira, Eduardo Peixoto, Ricardo L. de Queiroz, "Motion Estimation with Multiple Matching Criteria"
4. Andrei Purica, Benoit Boyadjis, Beatrice Pesquet-Popescu, Frederic Dufaux, "A study of norms in convex optimization super-resolution from compressed sources"
5. Farzad Toutounchi, Valia Guerra Ones, Ebroul Izquierdo, "An Efficient Video Super-Resolution Approach based on Sparse Representation"

Monday, 11:20: Poster session 1: Video coding

Chair: Ce Zhu, 天美传媒 of Electronic Science & Technology of China

1. Mohsen Abdoli, Felix Henry, Patrice Brault, Pierre Duhamel, Frederic Dufaux, "Intra Prediction Using In-Loop Residual Coding for the post-HEVC Standard"
2. Dooseop Choi, Taeg-Hyun An, Taejeong Kim, "Hierarchical Motion Estimation Algorithm based on Maximum a Posteriori Probability"
3. Eric Cornwell, Li Li, Zhu Li, and Yangfan Sun, "An Efficient Compression Scheme for the Multi-Camera Light Field Image"
4. Kutan Feyiz, Fatih Kamisli, Emin Zerman, Giuseppe Valenzise, Alper Koz, Frederic Dufaux, "Statistical Analysis and Directional Coding of Layerbased HDR Image Coding Residue"
5. Paulo Gon莽alves, Guilherme Correa, Marcelo Porto, Bruno Zatt, Luciano Agostini, "Multiple Early-Termination Scheme for TZSearch Algorithm based on Data Mining and Decision Trees"
6. Hongwei Guo, Ce Zhu, Yanbo Gao, Shichang Song, "A Frame-Level Rate Control Scheme for Low Delay Video Coding in HEVC"
7. Michael Ropert, Julien Le Tanou, Maxime Bichon and M茅d茅ric Blestel, "R-D Spatio-Temporal Adaptive Quantization based on Temporal Distortion Backpropagation in HEVC"
8. Roger Porto, Luciano Agostini, Bruno Zatt, Marcelo Porto, Nuno Roma, Leonel Sousa, "Energy-Efficient Motion Estimation with Approximate Arithmetic"
9. Huyen T. T. Tran, Nam Pham Ngoc, Cuong T. Pham, Yong Ju Jung, Truong Cong Thang, "A Subjective 天美传媒 on QoE of 360 Video for VR Communication"
10. Shengwei Wang, Li Yu, Sen Xiang, Zixiang Xiong, "Fault-tolerance based Block-level Bit Allocation and Adaptive RDO for Depth Video Coding"

Monday, 15:00: Poster session 2: Video processing & Demo papers

Chair: Joao Ascenso, Instituto Superior T茅cnico, Portugal

1. Andrea Eichenseer, Michel Batz, and Andre Kaup, "Disparity Estimation for Fisheye Images with an Application to Intermediate View Synthesis"
2. Angeliki V. Katsenou, Thomas Ntasios, Mariana Afonso, Dimitris Agrafiotis and David R. Bull, "Understanding Video Texture - A Basis for Video Compression"
3. Yuyang Liu, Ce Zhu, Min Mao, Fangliang Song, Frederic Dufaux, Xiang Zhang, "Analytical Distortion Aware Video Coding for Computer Based Video Analysis"
4. Francesca De Simone, Pascal Frossard, Neil Birkbeck, Balu Adsumilli, "Deformable block-based motion estimation in omnidirectional image sequences"
5. Kexin Tang, Chenglin Li, Hongkai Xiong, Junni Zou, Pascal Frossard, "Reinforcement Learning-Based Opportunistic Routing for Live Video Streaming over Multi-Hop Wireless Networks"
6. Tao Liu, Yong Liu, Zheng Tang, Jenq-Neng Hwang, "Adaptive Ground Plane Estimation for Moving Camera-Based 3D Object Tracking"
7. Zhen Wang, Massimo Piccardi, "Dissimilarity-Based Action Recognition with the Pair Hidden Markov Support Vector Machine"

Demo: Utku Bulkan, Tasos Dagiuklas, "Predicting Quality Of Experience For Online Video Systems Using Machine Learning"

Demo: Hiroshi Sankoh and Sei Naito, "Interactive Free-viewpoint Video Viewers of Both 3D Full Model and 2D Billboard Model"

Monday, 16:40: Lecture session 2: MMSP for healthcare

Chair: Zixiang Xiong, Texas A&M 天美传媒

1. Debsubhra Chakraborty, Yasir Tahir, Zixu Yang, Tomasz Maszczyk, Justin Dauwels, Daniel Thalmann, Nadia Magnenat Thalmann, Bhing-Leet Tan, and Jimmy Lee, "Assessment and Prediction of Negative Symptoms of Schizophrenia from RGB+D Movement Signals"
2. Lucie L茅v锚que and Hantao Liu, Christine Cavaro-M茅nard, Yongqiang Cheng, Patrick Le Callet, "Video Quality Perception in Telesurgery"
3. Simone Spagnol, Stefano Baldan, Runar Unnthorsson, "Auditory depth map representations with a sensory substitution scheme based on synthetic fluid sounds"
4. Georg Wimmer, Andreas Uhl, Andreas Vecsei, "Evaluation of Domain Specific Data Augmentation Techniques for the Classification of Celiac Disease using Endoscopic Imagery"

Tuesday 09:40: Lecture session 3: 3D video processing

Chairs: Homer Chen, National Taiwan 天美传媒, Frederic Dufaux, Universit茅 Paris-Sud

1. Michele Buccoli, Bruno Di Giorgi, Massimiliano Zanoni, Fabio Antonacci, Augusto Sarti, "Using multi-dimensional correlation for matching and alignment of MoCap and Video signals"
2. Biao Ma, Amy R. Reibman, "Enhancing Viewability for First-person Videos based on a Human Perception Model"
3. Mattia Rossi and Pascal Frossard, "Graph-Based Light Field Super-Resolution"
4. Vladan Velisavljevic, Camilo Dorea, Jacob Chakareski, Ricardo de Queiroz, "Convexity Characterization of Virtual View Reconstruction Error in Multi-view Imaging"
5. Wenjie Zhu, Yiling Xu, Li Li, Zhu Li, "Lossless Point Cloud Geometry Compression via Binary Tree Partition and Intra Prediction"

Tuesday 11:20: Poster session 3: Detection, recognition and classification

Chair: Raouf Hamzaoui, De Montfort 天美传媒, UK

1. Prerna Arora, Reinhold Haeb-Umbach, "A 天美传媒 on Transfer Learning for Acoustic Event Detection in a Real Life Scenario"
2. Jos茅 Abecasis Teixeira, Catarina Brites, Fernando Pereira, Jo茫o Ascenso, "Epipolar based Light Field Key-Location Detector"
3. Tomas Bj枚rklund, Attilio Fiandrotti, Mauro Annarumma, Gianluca Francini, Enrico Magli, "Automatic License Plate Recognition with Convolutional Neural Networks Trained on Synthetic Data"
4. Gauri Deshpande, Venkata Subramanian Viraraghavan, Mayuri Duggirala, V Ramu Reddy, Sachin Patel, "Empirical evaluation of emotion classification accuracy for non-acted speech"
5. Sina Ghassemi, Attilio Fiandrotti, Enrico Magli, Gianluca Francini, "Fine-Grained Vehicle Classification using Deep Residual Networks with Multiscale Attention Windows"
6. Sang Yoon Han, Sang Hwa Lee, Nam Ik Cho, "Gaze Estimation Using 3-D Eyeball Model under HMD Circumstance"
7. Kanghang He, Cheng Yang, Vladimir Stankovic, and Lina Stankovic, "Graph-based clustering for identifying region of interest in eye tracker data analysis"
8. Xinyu Lin, Ce Zhu, Qian Zhang, Mengxue Wang, Yipeng Liu, "Learning Based 3D Keypoint Detection with Local and Global Attributes in Multi-Scale Space"
9. Tao Lu, Yingjie Guan, Deng Chen, Zixiang Xiong, Wei He, "Low-rank constrained collaborative representation for robust face recognition"
10. Daniel Rotman, Dror Porat, Gal Ashour, "Robust Video Scene Detection Using Multimodal Fusion of Optimally Grouped Features"
11. Allan F. da Silva, Lucas A. Thomaz, Sergio L. Netto, Eduardo A. B. da Silva, "Online Video-based Sequence Synchronization for Moving Camera Object Detection"
12. Gaoang Wang, Jenq-Neng Hwang, Craig Rose, Farron Wallace, "Uncertainty Sampling Based Active Learning with Diversity Constraint by Sparse Selection"
13. Xuemei Wu, Jing Li, Qiang Wu, Jiande Sun, "Appearance-Based Gaze Block Estimation via CNN Classification"

Tuesday 16:20: Lecture session 4 (special session): Omnidirectional video communications: from content capture to distribution and consumption

Chairs: Francesca De Simone, EPFL, Switzerland

1. Ramin Ghaznavi-Youvalari, Alireza Zare, Huameng Fang, Alireza Aminlou, Qingpeng Xie, Miska M. Hannuksela, Moncef Gabbouj, "Comparison of HEVC Coding Schemes For Tile-based Viewport-adaptive Streaming of Omnidirectional Video"
2. Guilherme Luz, Jo茫o Ascenso, Catarina Brites, Fernando Pereira, "Saliency-driven Omnidirectional Imaging Adaptive Coding: Modeling and Assessment"
3. Thomas Maugey, Olivier Le Meur, Zhi Liu, "Saliency-based Navigation in Omnidirectional Image"
4. Silvia Rossi, Laura Toni, "Navigation-Aware Adaptive Streaming Strategies for Omnidirectional Video"
5. Bharath Vishwanath, Tejaswi Nanjundaswamy, Kenneth Rose, "Rotational Motion Model for Temporal Prediction in 360 Video Coding"

Wednesday 09:40: Lecture session 5: Denoising, filtering and analysis

Chair: Zhu Li, 天美传媒 of Missouri

1. Martin Alain, Aljosa Smolic, "Light Field Denoising by Sparse 5D Transform Domain Collaborative Filtering"
2. Darshan Batavia, Aditya Tatu, "Estimating Graph Topology from Sparse Graph Signals with an Application to Image Denoising"
3. Pierre David, Mikael Le Pendu, Christine Guillemot, "White Lenslet Image Guided Demosaicing for Plenoptic Cameras"
4. Gazi Illahi, Matti Siekkinen, Enrico Masala, "Foveated Video Streaming for Cloud Gaming"
5. Dominic Rufenacht, David Taubman, "Leveraging Decoded HEVC Motion for Fast, High Quality Optical Flow Estimation"

Wednesday 11:20: Poster session 4 (special session): Recent trends in multi-microphone signal processing

Audio processing

Chairs: Athanasios Mouchtaris,  Nikolaos Stefanakis, FORTH-ICS, Greece, Paris Smaragdis, 天美传媒 of Illinois at Urbana-Champaign

1. Bochra Bouchhima, Monia Turki Hadj Alaoune, Rim Amara, "Perceptual sparse modeling of wideband speech signals"
2. Keisuke Imoto, Nobutaka Ono, "Acoustic Scene Classification using Asynchronous Multichannel Observations with Different Lengths"
3. Juan M. Mart谋n-Donas, Angel M. Gomez, Ivan Lopez-Espejo, Antonio M. Peinado, "Dual-channel DNN-based Speech Enhancement for Smartphones"
4. Irene Mart谋n-Morato, Maximo Cobos, Francesc J. Ferri, "Analysis of Data Fusion Techniques for Multi-Microphone Audio Event Detection in Adverse Environments"
5. Marco A. Mart谋nez Ram谋rez, Joshua D. Reiss, "Stem Audio Mixing as a Content-Based Transformation of Audio Features"
6. Goncalo Mordido, Joao Magalhaes, Sofia Cavaco, "Automatic Organisation,Segmenation,and Filtering of User-Generated Audio Content"
7. Alexandru Nelus, Sebastian Gergen, Rainer Martin, "Analysis of Temporal Aggregation and Dimensionality Reduction on Feature Sets for Speaker Identification in Wireless Acoustic Sensor Networks"
8. Joerg Schmalenstroeer, Jahn Heymann, Lukas Drude, Christoph Boeddecker, Reinhold Haeb-Umbach, "Multi-Stage Coherence Drift Based Sampling Rate Synchronization for Acoustic Beamforming"
9. Nikolaos Stefanakis, Athanasios Mouchtaris, "Maximum Component Elimination in Mixing of User Generated Audio Recordings"
10. Alfredo Zermini, Qingju Liu, Yong Xu, Mark D. Plumbley, Dave Betts, Wenwu Wang, "Binaural and Log-Power Spectra Features with Deep Neural Networks for Speech-Noise Separation"

Wednesday 15:00: Poster session 5: Image coding and processing

Chair: Touradj Ebrahimi, EPFL, Switzerland

1. Amir Adler, David Boublil, Michael Zibulevsky, "Block-based Compressed Sensing of Images via Deep Learning"
2. Sebastien BEUGNON, William PUECH, Jean-Pierre PEDEBOY, "An efficient lossless (2, n) Secret Image Sharing based on Blakley’s Scheme"
3. Volker Bruns, Miguel 脕. Mart铆nez-del-Amor, Heiko Sparenberg, "Evaluation of GPU/CPU Co-Processing Models for JPEG 2000 Packetization"
4. Da-Fang Chang, Sih-Sian Wu, Hsin-Yu Hou, Liang-Gee Chen, "Accurate and Fast Segment-based Cost Aggregation Algorithm for Stereo Matching"
5. Saber Farag, Vladan Velisavljevic, Amar Aggoun, "A Hybrid Approach for Image Super-Resolution of Light Field Images"
6. Shan Feng, Zhu Li, Yiling Xu, Jun Sun, "Compact Scalable Hash from Deep Learning Features Aggregation for Content De-duplication"
7. Andr茅 F. R. Guarda, Jos茅 M. Bioucas-Dias, Nuno M. M. Rodrigues, Fernando Pereira, "Improving Point Cloud to Surface Reconstruction with Generalized Tikhonov Regularization"
8. J谩n Koloda, Michel B盲tz, Andr茅 Kaup, "Iterative Denoising-Based Mesh-to-Grid Reconstruction with Hyperparametric Adaptation"
9. Yuan Liu, John W. Woods, "New and Efficient Interframe Extensions of EZBC and JPEG 2000"
10. Carlo Noel Ochotorena, Yukihiko Yamashita, "Multi-scale Structure-preserving Image Filtering"
11. V. Shreyas, Vinod Pankajakshan, "A Deep Learning Architecture for Brain Tumor Segmentation in MRI Images"
12. Marcio P. Pereira, Gustavo Alves, Carla L. Pagliari, Murilo B. de Carvalho, Eduardo A. B. da Silva, "Geometric Space-View Redundancy Descriptor for Light Fields: Predicting the Compression Potential of the JPEG Pleno Light Field Datasets"
13. Dazhi Zhan, Xiangrong Zeng, Weili Li, Yu Liu, Zhihui Xiong, "Blur Kernel Estimation Using Normal Sinh-Arcsinh Model Based on Simple Lens System"

Wednesday 16:20: Lecture session 6 (special session): Quality of Experience for emerging video formats

Chairs: Giuseppe Valenzise, Universit茅 Paris-Sud

1. Evangelos Alexiou, Evgeniy Upenik and Touradj Ebrahimi, "Towards Subjective Quality Assessment of Point Cloud Imaging in Augmented Reality"
2. Vedad Hulusic, Giuseppe Valenzise, Jean-Charles Gicquel, Jerome Fournier, Frederic Dufaux, "Quality of Experience in UHD-1 Phase 2 television: the contribution of UHD+HFR technology"
3. Alireza Javaheri, Catarina Brites, Fernando Pereira, Joao Ascenso, "Subjective and Objective Quality Evaluation of Compressed Point Clouds"
4. Suiyi Ling, Patrick Le Callet, Gene Cheung, "Quality assessment for synthesized view based on variable-length context tree"