Conference program
Click to download a PDF version of the program.⇤
June 6 Tutorial & Workshops (UPB's Library/Conference Center) | June 7 Main Conference (AN010 “Radu Voinea”) | June 8 Main Conference (AN010 “Radu Voinea”) | June 9 Industry Day (AN010 “Radu Voinea”) | ||||
---|---|---|---|---|---|---|---|
08:00- 08:40 | Registration | Registration | Registration | Registration | 08:00- 08:40 | ||
08:40- 08:50 | Welcome | Day opening | Day opening | 08:40- 08:50 | |||
08:50- 09:40 |
Tutorial on "Semantic INdexing" by Georges Quénot Chair: George Awad |
Keynote "Searching for a thing" by Arnold W.M. Smeulders and Ran Tao Chair: Cees Snoek |
Keynote "Making cultural visits with a smart mate" by Alberto del Bimbo Chair: Nicu Sebe |
Industry Keynotes Xiaozheng Huang, Tencent Matei Stroilă, HERE Changhu Wang, Toutiao Chair: Neil O'Hare |
08:50- 09:40 | ||
09:40- 10:00 |
Oral Session 1 Vision and Language Chair: Horia Cucu |
Oral Session 5 Best Papers Candidates Chair: Vasileios Mezaris |
09:40- 10:00 | ||||
10:00- 10:30 |
Coffee break (at the venue) |
10:00- 10:30 | |||||
10:30- 10:45 |
Tutorial on "Zero-Example Video Search" by Chong-Wah Ngo Chair: George Awad |
10:30- 10:45 | |||||
10:45- 11:00 | 10:45- 11:00 | ||||||
11:00- 11:30 |
Coffee break (at the venue) in parallel posters of Oral Session 1, 2, and 3 |
Coffee break (at the venue) in parallel posters of Oral Session 4 and 5 |
Coffee break (at the venue) |
11:00- 11:30 | |||
11:30- 12:15 |
Tutorial on "Ad Hoc Video Search" by Georges Quénot Chair: George Awad |
Special Oral Session Beyond semantics: multimodal understanding of subjective properties Chair: Miriam Redi |
Special Oral Session Identifying and Linking Interesting Content in Large Audiovisual Repositories Chairs: Maria Eskevich, Roeland Ordelman |
Panel session Indicators of Innovation and Signs of Success: Recognizing which Multimedia Information Retrieval Research is Most Valuable to Industry Moderator: Martha Larson |
11:30- 12:15 | ||
12:15- 12:30 |
Oral Session Brave New Ideas Chair: Chong-Wah Ngo |
12:15- 12:30 | |||||
12:30- 12:50 |
Lunch (at the venue) |
Closing remarks and presentation of ICMR 2018 |
12:30- 12:50 | ||||
12:50- 13:00 |
Free evening in Bucharest |
12:50- 13:00 | |||||
13:00- 14:00 |
Lunch (at the venue) in parallel posters of Oral Session 1, 2, and 3 |
Lunch (at the venue) in parallel posters of Oral Session 4, and 5 |
13:00- 14:00 | ||||
14:00- 15:00 |
Tutorial on "Multimedia Event Detection" by Cees Snoek Chair: George Awad |
Oral Session Open Software Chair: Mathias Lux |
Oral Session 4 Cross-media Retrieval Chair: Giorgos Tolias |
14:00- 15:00 | |||
15:00- 15:20 |
Tutorial on "Instance Search" by Shin'ichi Satoh, Duy-Dinh Le, Vinh-Tiep Nguyen Chair: George Awad |
15:00- 15:20 | |||||
15:20- 15:40 |
Oral Session 2 Multimedia Indexing Chair: Adrian Ulges |
Coffee break (at the venue) |
15:20- 15:40 | ||||
15:40- 16:00 |
Posters Chair: Petra Galuščáková and Demos Chair: Jaeyoung Choi |
Oral Session Doctoral Symposium Chair: Tomas Piatrik |
15:40- 16:00 | ||||
16:00- 16:20 |
Coffee break (at the venue) |
16:00- 16:20 | |||||
16:20- 16:30 | 16:20- 16:30 | ||||||
16:30- 16:40 |
Tutorial on "Video to Text" by Cees Snoek Chair: George Awad |
16:30- 16:40 | |||||
16:40- 17:00 |
Coffee break (at the venue) in parallel posters of Oral Session 1, 2, and 3 |
16:40- 17:00 | |||||
17:00- 17:20 |
Oral Session 3 Multimedia Applications Chair: Wei-Ta Chu |
17:00- 17:20 | |||||
17:20- 18:00 | 17:20- 18:00 | ||||||
18:00- 18:05 | 18:00- 18:05 | ||||||
18:05- 18:20 | 18:05- 18:20 | ||||||
18:20- | 18:20- |
ORAL SESSION 1: Vision and Language
Session Chair: Horia Cucu Wednesday, June 7, AN010 “Radu Voinea”
9:40-10:45 Oral presentations Shizhe Chen, Jia Chen and Qin Jin, Generating Video Descriptions with Topic Guidance Christian Andreas Henning and Ralph Ewerth, Estimating the Information Gap between Textual and Visual Representations Kan Chen, Rama Kovvuri, Jiyang Gao and Ram Nevatia, MSRC: Multimodal Spatial Regression with Semantic Context for Phrase Grounding Junwei Liang, Lu Jiang, Deyu Meng and Alexander Hauptmann, Leveraging Multi-modal Prior Knowledge for Large-scale Concept Learning in Noisy Web Data
10:45-11:00 Spotlight presentations Xing Xu, Fumin Shen, Yang Yang, Jie Shao and Zi Huang, Transductive Visual-Semantic Embedding for Zero-shot Learning Ricardo Carrapiço, Isabel Guimarães, Margarida Grilo, Sofia Cavaco and Joao Magalhães, 3D Facial Video Retrieval and Management for Decision Support in Speech and Language Therapy Thomas Mensink, Thomas Jongstra, Pascal Mettes and Cees G.M. Snoek, Music-Guided Video Summarization using Quadratic Assignments
SPECIAL ORAL SESSION: Beyond Semantics: Multimodal Understanding of Subjective Properties
Session Chair: Miriam Redi Wednesday, June 7, AN010 “Radu Voinea”
11:30-12:15 Oral presentations Darshan Santani, Salvador Ruiz-Correa and Daniel Gatica-Perez, Insiders and Outsiders: Comparing Urban Impressions between Population Groups Claudio Baecchi, Tiberio Uricchio, Marco Bertini and Alberto Del Bimbo, Deep Sentiment Features of Context and Faces for Affective Video Analysis Jiarui Gao, Yanwei Fu, Yu-Gang Jiang and Xiangyang Xue, Frame-Transformer Emotion Classification Network
ORAL SESSION: Brave New Ideas
Session Chair: Chong-Wah Ngo Wednesday, June 7, AN010 “Radu Voinea”
12:15-13:00 Oral presentations Jaeyoung Choi, Martha Larson, Xinchao Li, Kevin Li, Gerald Friedland and Alan Hanjalic, The Geo-Privacy Bonus of Popular Photo Enhancements Eduardo Nigri and Ognjen Arandjelovic, Light Curve Analysis From Kepler Spacecraft Collected Data Nitish Nag, Vaibhav Pandey and Ramesh Jain, Health Multimedia: Lifestyle Recommendations Based on Diverse Observations
ORAL SESSION: Open Software
Session Chair: Mathias Lux Wednesday, June 7, AN010 “Radu Voinea”
14:00-15:20 Oral presentations Lucas Pascotti Valem and Daniel Carlos Guimarães Pedronette, An Unsupervised Distance Learning Framework for Multimedia Retrieval Konstantin Pogorelov, Michael Riegler, Pål Halvorsen and Carsten Griwodz, ClusterTag: Interactive Visualization, Clustering and Tagging Tool for Big Image Collections Chris A. Mattmann and Madhav Sharan, Scalable Hadoop-Based Pooled Time Series of Big Video Data from the Deep Web Federico Bartoli, Giuseppe Lisanti, Lorenzo Seidenari and Alberto Del Bimbo, PACE: Prediction-based Annotation for Crowded Environments
ORAL SESSION 2: Multimedia Indexing
Session Chair: Adrian Ulges Wednesday, June 7, AN010 “Radu Voinea”
15:20-16:20 Oral presentations Rao Muhammad Anwer, Fahad Shahbaz Khan, Joost van de Weijer and Jorma Laaksonen, TEX-Nets: Binary Patterns Encoded Convolutional Neural Networks for Texture Recognition Jie Lin, Olivier Morère, Antoine Veillard, Ling-Yu Duan, Hanlin Goh and Vijay Chandrasekhar, DeepHash for Image Instance Retrieval: Getting Regularization, Depth and Fine-Tuning Right André Mourão and Joao Magalhães, Balanced Search Space Partitioning for Distributed Media Redundant Indexing Dayan Wu, Zheng Lin, Bo Li, Mingzhen Ye and Weiping Wang, Deep Supervised Hashing for Multi-Label and Large-Scale Image Retrieval
16:20-16:40 Spotlight presentations Fabien André, Anne-Marie Kermarrec and Nicolas Le Scouarnec, Accelerated Nearest Neighbor Search with Quick ADC Christian Eggert, Dan Zecha, Stephan Brehm and Rainer Lienhart, Improving Small Object Proposals for Company Logo Detection Rui Yang, Yuliang Shi and Xin-Shun Xu, Discrete Multi-view Hashing for Effective Image Retrieval Omar Seddati, Stéphane Dupont and Saïd Mahmoudi, Quadruplet Networks for Sketch-Based Image Retrieval
ORAL SESSION 3: Multimedia Applications
Session Chair: Wei-Ta Chu Wednesday, June 7, AN010 “Radu Voinea”
17:00-18:05 Oral presentations Karthik Yadati, Cynthia C. S. Liem, Martha Larson and Alan Hanjalic, On the Automatic Identification of Music for Common Activities Martin Pichl, Eva Zangerle and Günther Specht, Improving Context-Aware Music Recommender Systems: Beyond the Pre-filtering Approach Michal Koperski, Slawomir Bak and Peter Carr, Groups Re-identification with Temporal Context Ionuț C. Duță, Bogdan Ionescu, Kiyoharu Aizawa and Nicu Sebe, Simple, Efficient and Effective Encodings of Local Deep Features for Video Action Recognition
18:05-18:20 Spotlight presentations Olga Slizovskaia, Emilia Gómez and Gloria Haro, Musical Instrument Recognition in User-generated Videos using a Multimodal Convolutional Neural Network Architecture Gijs Overgoor, Masoud Mazloom, Marcel Worring, Robert Rietveld and Willemijn van Dolen, A Spatio-Temporal Category Representation for Brand Popularity Prediction Miriam Redi, Frank Z. Liu and Neil O'Hare, Bridging the Aesthetic Gap: The Wild Beauty of Web Imagery
ORAL SESSION 5: Best Papers Candidates
Session Chair: Vasileios Mezaris Thursday, June 8, AN010 “Radu Voinea”
9:40-11:00 Oral presentations Mohammad Soleymani, Michael Riegler and Pål Halvorsen, Multimodal Analysis of Image Search Intent - Intent Recognition in Multimedia Search from User Behavior and Multimedia Content Olivier Morere, Jie Lin, Antoine Veillard, Ling-Yu Duan, Vijay Chandrasekhar and Tomaso Poggio, Nested Invariance Pooling and RBM Hashing for Image Instance Retrieval Yusuke Uchida, Yuki Nagai, Shigeyuki Sakazawa and Shin'ichi Satoh, Embedding Watermarks into Deep Neural Networks Christina Boididou, Symeon Papadopoulos, Lazaros Apostolidis and Yiannis Kompatsiaris, Learning to Detect Misleading Content on Twitter
SPECIAL ORAL SESSION: Identifying and Linking Interesting Content in Large Audiovisual Repositories
Session Chairs: Maria Eskevich and Roeland Ordelman Thursday, June 8, AN010 “Radu Voinea”
11:30-13:00 Oral presentations Zhi-Qi Cheng, Hao Zhang, Xiao Wu and Chong-Wah Ngo, On the Selection of Anchors and Targets for Video Hyperlinking Petra Galuščáková, Michal Batko, Jan Čech, Jiří Matas, David Novák and Pavel Pecina, Visual Descriptors in Methods for Video Hyperlinking Rémi Bois, Guillaume Gravier, Eric Jamet, Emmanuel Morin, Maxime Robert and Pascale Sébillot, Linking Multimedia Content for Efficient News Browsing Yang Liu, Zhonglei Gu, Yiu-Ming Cheung and Kien A. Hua, Multi-view Manifold Learning for Media Interestingness Prediction Keith Curtis, Gareth J.F. Jones and Nick Campbell, Utilising High-Level Features in Summarisation of Academic Presentations
ORAL SESSION 4: Cross-media Retrieval
Session Chair: Giorgos Tolias Thursday, June 8, AN010 “Radu Voinea”
14:00-15:00 Oral presentations Aliaksandr Siarohin, Gloria Zen, Cveta Majtanovic, Xavier Alameda-Pineda, Elisa Ricci and Nicu Sebe, How to Make an Image More Memorable? A Deep Style Transfer Approach Fabian Junkert, Markus Eberts, Adrian Ulges and Ulrich Schwanecke, Cross-modal Image-Graphics Retrieval by Neural Transfer Learning Samet Hicsonmez, Nermin Samet, Fadime Sener and Pinar Duygulu, DRAW: Deep Networks for Recognizing Styles of Artists Who Illustrate Children’s Books Ines Chami, Youssef Tamaazousti and Hervé Le Borgne, AMECON: Abstract Meta-Concept Features for Text-Illustration
15:00-15:20 Spotlight presentations Elaheh Momeni, Reza Rawassizadeh and Eytan Adar, Leveraging Semantic Facets for Adaptive Ranking of Social Comments Zhanxiong Wang, Keke He, Yanwei Fu, Rui Feng, Yu-Gang Jiang and Xiangyang Xue, Multi-task Deep Neural Network for Joint Face Recognition and Facial Attribute Prediction Kuikui Wang, Lu Yang, Gongping Yang, Xin Luo, Kun Su and Yilong Yin, Finger Vein Image Retrieval via Coding Scale-varied Superpixel Feature Haoyue Shi, Jia Chen and Alexander G. Hauptmann, Joint Saliency Estimation and Matching using Image Regions for Geo-Localization of Online Video
POSTERS
Session Chair: Petra Galuščáková Thursday, June 8, Hallway
15:40-18:00 Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Teddy Furon and Ondrej Chum, Panorama to Panorama Matching for Location Recognition Damianos Galanopoulos, Foteini Markatopoulou, Vasileios Mezaris and Ioannis Patras, Concept Language Models and Event-based Concept Number Selection for Zero-example Event Detection Shilun Lin, Pengfei Xiong and Hailong Liu, Tiny Transform Net for Mobile Image Stylization Foteini Markatopoulou, Damianos Galanopoulos, Vasileios Mezaris and Ioannis Patras, Query and Keyframe Representations for Ad-hoc Video Search Wei-Ta Chu and Wei-Wei Li, Manga FaceNet: Face Detection in Manga based on Deep Neural Network Vedran Vukotić, Christian Raymond and Guillaume Gravier, Generative Adversarial Networks for Multimodal Representation Learning in Video Hyperlinking Giuseppe Amato, Fabio Carrara, Fabrizio Falchi and Claudio Gennaro, Efficient Indexing of Regional Maximum Activations of Convolutions using Full-Text Search Engines Junkang Zhang, Siyu Xia, Ming Shao and Yun Fu, Family Photo Recognition via Multiple Instance Learning Shan Sun, Feng Wang, Qi Liang and Liang He, TaiChi: A Fine-Grained Action Recognition Dataset Keiji Yanai and Ryosuke Tanno, Conditional Fast Style Transfer Network Anuvabh Dutt, Denis Pellerin and Georges Quénot, Improving Image Classification using Coarse and Fine Labels Mridula Verma and Kaushal Kumar Shukla, Fast Multi-Modal Unified Sparse Representation Learning Wei-Ta Chu and Samuel Situmeang, Badminton Video Analysis based on Spatiotemporal and Stroke Features Xing Xu, Fumin Shen, Yang Yang, Jie Shao and Zi Huang, Transductive Visual-Semantic Embedding for Zero-shot Learning Joao Magalhaes and Sofia Cavaco, 3D Facial Video Retrieval and Management for Decision Support in Speech and Language Therapy Thomas Mensink, Thomas Jongstra, Pascal Mettes and Cees Snoek, Music-Guided Video Summarization: Linking Audio Visual Content using Quadratic Assignments Fabien André, Anne-Marie Kermarrec and Nicolas Le Scouarnec, Accelerated Nearest Neighbor Search with Quick ADC Christian Eggert, Dan Zecha, Stephan Brehm and Rainer Lienhart, Improving Small Object Proposals for Company Logo Detection Rui Yang, Yuliang Shi and Xin-Shun Xu, Discrete Multi-view Hashing for Effective Image Retrieval Omar Seddati, Stéphane Dupont and Saïd Mahmoudi, Quadruplet Networks for Sketch-Based Image Retrieval Olga Slizovskaia, Emilia Gomez and Gloria Haro, Musical Instrument Recognition in User-Generated Videos using a Multimodal Convolutional Neural Network Architecture Gijs Overgoor, Masoud Mazloom, Robert Rietveld, Marcel Worring and Willemijn van Dolen, A Spatio-Temporal Category Representation for Brand Popularity Prediction Miriam Redi, Frank Liu and Neil O'Hare, Bridging the Aesthetic Gap: The Wild Beauty of Web Imagery Elaheh Momeni, Reza Rawassizadeh and Eytan Adar, Leveraging Semantic Facets for Adaptive Ranking of Social Comments Zhanxiong Wang, Keke He, Yanwei Fu, Yugang Jiang, Rui Feng and Xiangyang Xue, Multi-Task Deep Neural Network for Joint Face Recognition and Facial Attribute Prediction Kuikui Wang, Lu Yang, Gongping Yang, Xin Luo, Kun Su and Yilong Yin, Finger Vein Image Retrieval via Coding Scale-varied Superpixel Feature Haoyue Shi, Jia Chen and Alexander Hauptmann, Joint Saliency Estimation and Matching using Image Regions for Geo-Localization of Online Video
DEMONSTRATIONS
Session Chair: Jaeyoung Choi Thursday, June 8, Hallway
15:40-18:00 Andrea Ceroni, Vassilios Solachidis, Claudia Niederée, Olga Papadopoulou and Vasileios Mezaris, Expo: An Expectation-oriented System for Selecting Important Photos from Personal Collections Luca Rossetto, Ivan Giangreco, Claudiu Tănase and Heiko Schuldt, Multimodal Video Retrieval with the 2017 IMOTION System Kashif Ahmad, Michael Riegler, Ans Riaz, Nicola Conci, Duc-Tien Dang-Nguyen and Pål Halvorsen, The JORD System - Linking Sky and Social Multimedia Data to Natural Disasters Mathias Lux, Michael Riegler, Pål Halvorsen and Glenn MacStravic, LireSolr - A Visual Information Retrieval Server Chrysa Collyda, Evlampios Apostolidis, Alexandros Pournaras, Foteini Markatopoulou, Vasileios Mezaris and Ioannis Patras, VideoAnalysis4ALL: An On-line Tool for the Automatic Fragmentation and Concept-based Annotation, and the Interactive Exploration of Videos Kai Uwe Barthel, Nico Hezel and Klaus Jung, Visually Browsing Millions of Images Using Image Graphs
ORAL SESSION: Doctoral Symposium
Session Chair: Tomas Piatrik Thursday, June 8, AN010 “Radu Voinea”
15:40-17:00 Oral presentations Shengsheng Qian, Tianzhu Zhang and Changsheng Xu, A Generic Framework for Social Event Analysis Stefan Petscharnig, Semi-Automatic Retrieval of Relevant Segments from Laparoscopic Surgery Videos Yash Garg and Silvestro Roberto Poccia, On the Effectiveness of Distance Measures for Similarity Search in Multi-Variate Sensory Data Karim Aderghal, Jenny Benois-Pineau and Karim Afdel, Classification of sMRI for Alzheimer’s disease Diagnosis with CNN: Single Siamese Networks with 2D+epsilon Approach and Fusion on ADNI
INDUSTRY KEYNOTES
Session Chair: Neil O'Hare Friday, June 9, AN010 “Radu Voinea”
8:50-11:00 Xiaozheng Huang, Tencent With 5G Approaching, How will Audio/Video Technology that Serves 800 Million QQ Users Bring Forth New Ideas Matei Stroilă, HERE Information Retrieval from Multi-Sensor Data for Enriching Location Services at HERE Technologies Changhu Wang, Toutiao Intelligently Connecting People with Information
PANEL SESSION
Moderator: Martha Larson Friday, June 9, AN010 “Radu Voinea”
11:30-12:30 Vasileios Mezaris, CERTH, Greece, Matei Stroilă, HERE, USA, Ramesh Jain, University of California, Irvine, USA, Changhu Wang, Toutiao AI Lab, China Indicators of Innovation and Signs of Success: Recognizing which Multimedia Information Retrieval Research is Most Valuable to Industry