|8:45 – 9:00||Opening – BeFIT Overview Presentation|
|9:00 – 9:45||Invited talk: From Benchmarking to an Experimental Discipline |
P. Jonathon Phillips (National Institute of Standards and Technology)
|9:45 – 10:45||Benchmarks, Challenges, Databases I|
|9:45 – 10:05||A Face Biometric Benchmarking Review and Characterisation |
Sandra Mau (NICTA), Farhad Dadgostar (NICTA), Abbas Bigdeli (NICTA), Brian Lovell (NICTA & UQ), Ian Cullinan (NICTA)
|10:05 – 10:25||Evaluation of Face Recognition System in Heterogeneous Environments (Visible vs NIR) |
Debaditya Goswami (University of Surrey), Chi ho Chan (University of Surrey), David Windridge (University of Surrey), Josef Kittler (University of Surrey)
|10:25 – 10:45||Single- and Cross- Database Benchmarks for Gender Classification Under Unconstrained Settings |
Pablo Dago-Casas (Gradiant), Daniel Gonzalez-Jimenez (Gradiant), Long Long Yu (Gradiant), José Luis Alba-Castro (Universidade de Vigo)
|10:45 – 11:00||Coffee break|
|11:00 – 12:00||Benchmarks, Challenges, Databases II|
|11:00 – 11:20||Static Facial Expression in the Wild: Data, Evaluation Protocol and Benchmark |
Abhinav Dhall (Australian National University), Roland Goecke (University of Canberra), Simon Lucey (CSIRO), Tom Gedeon (Australian National University)
|11:20 – 11:40||Facial Landmarks in the Wild: A Large-scale, Real-world Database for Facial Landmark Localization |
Martin Köstinger (Graz University of Technology), Paul Wohlhart (Graz University of Technology), Peter Roth (Graz University of Technology), Horst Bischof (Graz University of Technology)
|11:40 – 12:00||VADANA: A Dense Dataset for Facial Image Analysis |
Gowri Somanath (University of Delaware), Rohith MV (University of Delaware), Chandra Kambhamettu (University of Delaware)
|12:00 – 13:00||Benchmarks, Challenges, Databases III|
|12:00 – 12:20||3D Twins and Expression Challenge |
Vipin Vijayan (University of Notre Dame), Kevin Bowyer (University of Notre Dame), Patrick Flynn (University of Notre Dame)
|12:20 – 12:40||High-Resolution Comprehensive 3-D Dynamic Database for Facial Articulation Analysis |
Bogdan Matuszewski (University of Central Lancashire), Wei Quan (University of Central Lancashire), Lik-Kwan Shark (University of Central Lancashire)
|12:40 – 13:00||UMB-DB: A Database of Partially Occluded 3D Faces |
Alessandro Colombo (University of Milano-Bicocca), Claudio Cusano (University of Milano-Bicocca), Raimondo Schettini (University of Milano-Bicocca)
|13:00 – 13:10||Award Session|
|13:10 – 14:30||Lunch Break|
|14:30 – 15:15||Invited talk: Facial Behaviour Analysis |
Maja Pantic (Imperial College London)
|15:15 – 16:35||Facial Expression Analysis|
|15:15 – 15:35||Criteria and Metrics for Thresholded AU Detection |
Jeff Girard (University of Pittsburgh), Jeffrey Cohn (University of Pittsburgh)
|15:35 – 15:55||Facial Action Unit Detection Using Kernel Partial Least Squares |
Tobias Gehrig (Karlsruhe Institute for Technology), Hazim Ekenel (Karlsruhe Institute for Technology)
|15:55 – 16:15||Manifold Based Sparse Representation for Robust Expression Recognition without Neutral Subtraction |
Raymond Ptucha (Rochester Institute of Technology), Andreas Savakis (Rochester Institute of Technology), Grigorios Tsagkatakis (Rochester Institute of Technology)
|16:15 – 16:35||High Quality Facial Expression Recognition in Video Streams Using Shape Related Information Only |
Laszlo Jeni (University of Tokyo), Daniel Takacs (Realeyes Data Services Ltd), Andras Lorincz (Eotvos Lorand University)
|16:35 – 16:50||Coffee break|
|16:50 – 17:30||Face Processing|
|16:50 – 17:10||Face Detection Using SURF Cascade |
Jianguo Li (Intel Labs), Tao Wang (Intel Labs), Yimin Zhang (Intel Labs)
|17:10 – 17:30||Object Representation Based on Gabor Wave Vector Bining: An Application to Human Head Pose Detection |
Mohamed Dahmane (Diro University of Montreal)
Dr. P. Jonathon Phillips
National Institute of Standards and Technology
Gaithersburg, MD 20899, USA
Summary of talk
During the FERET program in the mid 1990’s I wondered if the FERET evaluation could be published. Now benchmarking, challenge problems, and evaluations are integral parts of face recognition, biometrics, and computer vision research. At CVPR and ICCV there are workshops devoted to benchmarking problems. These benchmarking efforts are a first step in establishing an experimental discipline in face recognition and computer vision. I will discuss three aspects of extending this experimental discipline beyond benchmarking. The first is designing benchmarking efforts to allow for meta-analysis across multiple benchmarking efforts. A Meta-analysis draws conclusions across multiple benchmarks. The second aspect is conducting experiments to explicitly ask questions about specific properties of data and algorithms. For example, are pose, illumination, and expression the key factors that effect performance of face recognition algorithms? The human visual system is the most robust face recognition algorithm. Establishing goals for benchmarking based on human performance would set realistic goals for algorithm developers. In addition, benchmarks based on human performance have the potential to increase our understanding of how humans’ process faces.
Dr. Jonathon Phillips is a leading researcher in the fields of computer vision, face recognition, biometrics, and human identification. He is at the National Institute of Standards and Technology (NIST), where he directs challenge problems and evaluations in face recognition and biometrics. His efforts include the Multiple Biometrics Evaluation 2010, the Iris Challenge Evaluations (ICE), the Face Recognition Vendor Test (FRVT) 2006 and the Face Recognition Grand Challenge and FERET. From 2000-2004, Dr. Phillips was assigned to the Defense Advanced Research Projects Agency (DARPA) as program manager for the Human Identification at a Distance program. He was test director for the FRVT 2002. For his work on the FRVT 2002 he was awarded the Dept. of Commerce Gold Medal. His work has been reported in print media of record including the New York Times and the Economist. He has appeared on NPR’s ScienceFriday. He received his Ph.D. in operations research from Rutgers University. From 2004-2008 he was an Associate Editor for the IEEE Trans. on Pattern Analysis and Machine Intelligence and guest editor of an issue of the Proceedings of the IEEE on biometrics. In an Essential Science Indicators analysis of face recognition publication over the past decade, Jonathon Phillips’ work ranks at #2 by total citations and #1 by citations per paper. He is a Fellow of the IEEE and the IAPR.
Professor Maja Pantic
Imperial College London, Computing Dept., UK
University of Twente, EEMCS, Netherlands
Summary of talk
"A widely accepted prediction is that computing will move to the background, weaving itself into the fabric of our everyday living spaces and projecting the human user into the foreground. To realize this prediction, next-generation computing should develop anticipatory user interfaces that are human-centred, built for humans, and based on naturally occurring multimodal human behaviour such as affective and social signaling.
The facial behaviour is our preeminent means to communicating affective and social signals. This talk discusses a number of components of human facial behavior, how they can be automatically sensed and analysed by computer, what is the past research in the field conducted by the iBUG group at Imperial College London, and how far we are from enabling computers to understand human facial behavior."
Maja Pantic received the M.S. and PhD degrees in computer science from Delft University of Technology, the Netherlands, in 1997 and 2001. From 2001 to 2005, she was an Assistant and then an Associate professor at Delft University of Technology, Computer Science Department. In 2006, she joined the Imperial College London, Department of Computing, UK, where she is Professor of Affective & Behavioural Computing and the leader of the iBUG group, working on machine analysis of human non-verbal behaviour and its applications to HCI. From November 2006, she also holds an appointment as the Professor of Affective & Behavioural Computing at the University of Twente, Computer Science Department, the Netherlands.
In 2002, for her research on Facial Information for Advanced Interface (FIFAI), she received Innovational Research Award of Dutch Research Council as one of the 7 best young scientists in exact sciences in the Netherlands.
In 2007, for her research on Machine Analysis of Human Naturalistic Behavior (MAHNOB), she received European Research Council Starting Grant (ERC StG) as one of 2% best junior scientists in any research field in Europe. She is also the Scientific Director of the large European project on Social Signal Processing.
In 2011, Prof. Pantic received BCS Roger Needham Award, awarded annually to a UK based researcher for a distinguished research contribution in computer science within ten years of their PhD.
She is the Editor in Chief of the Image and Vision Computing Journal (IVCJ/ IMAVIS), Associate Editor of the IEEE Transactions on Systems, Man, and Cybernetics - Part B: Cybernetics (IEEE TSMC-B), Associate Editor of the IEEE Transactions on Pattern Analysis and Machine Intelligenve (IEEE TPAMI), and a member of the Steering Committee of the IEEE Transactions on Affective Computing. She is also a member of the IEEE Systems, Man and Cybernetics Society Board of Governers.
Prof. Pantic is one of the world's leading experts in the research on machine understanding of human behavior including vision-based detection, tracking, and analysis of human behavioral cues like facial expressions and body gestures, and multimodal analysis of human behaviors like laughter, social signals, and affective states. She is also one of the pioneers in design and development of fully automatic, affect-sensitive human-centered anticipatory interfaces, built for humans based on human models. She has published more than 150 technical papers in the areas of machine analysis of facial expressions and emotions, machine analysis of human body gestures, and human-computer interaction. Her work is widely cited and has more than 25 popular press coverage (including New Scientist, BBC Radio, and NL TV 1 and 3).See also: http://ibug.doc.ic.ac.uk