Schedule
January 17th
7:00 - 8:00 Breakfast
8:00 - 8:10 Intro by Chairs
8:10 - 9:45 Short Oral Session 1
- 3D Free Form Object Recognition using Rotational Projection Statistics, Yulan Guo, National University of Defense Technology; Mohammed Bennamoun, Ferdous Sohel, The University of Western Australia; Jianwei Wan, National University of Defense Technology; Min Lu, National University of Defense Technology
- Are You Using the Right Approximate Nearest Neighbor Algorithm?, Stephen O'Hara, Colorado State University; Bruce Draper, Colorado State University
- Large-scale Web Video Event Classification by use of Fisher Vectors, Chen Sun, University of Southern California
- Nonuniform Image Patch Exemplars for Low Level Vision, Vincent De Smet, KU Leuven; Vinay Namboodiri, Alcatel-Lucent Bell Labs, Antwerp, Belgium; Luc Van Gool, KU Leuven
- Towards a Practical PTZ Face Detection and Tracking System, Yinghao Cai, USC; Gerard Medioni
- Separation of Specular-Diffuse Reflection Components in the HSI Color Space, Yang Jianwei, CBSR&NLPR. Pulled from proceedings due to no show.
- Image segmentation for large-scale subcategory flower recognition, Anelia Angelova, NEC Labs America; Shenghuo Zhu, Yuanqing Lin
- Heteroscedastic Probabilistic Linear Discriminant Analysis for Manifold Learning in Video-Based Face Recognition, Moh Wibowo, QUT Brisbane Australia; Dian Tjondronegoro, QUT Brisbane Australia; Ligang Zhang, QUT Brisbane Australia; Ivan Himawan, QUT
- MHAD: A Comprehensive Multimodal Human Action Database, Ferda Ofli, UC Berkeley; Rizwan Chaudhry, Johns Hopkins University; Gregorij Kurillo, UC Berkeley; Rene Vidal, Johns Hopkins University; Ruzena Bajcsy, UC Berkeley
- Human Behavior Segmentation and Recognition using Continuous Linear Dynamic System, Jinjun Wang, Epson; Jing Xiao, Epson Research and Development
- Statistical Angular Error-Based Triangulation for Efficient and Accurate Multi-View Scene Reconstruction, Shawn Recker, University of California Davis; Mauricio Hess-Flores, UC Davis; Ken Joy, University of California Davis
- Automatic Region-of-Interest Detection and Prioritisation for Visually Optimised Coding of Low Bit Rate Videos, Ivan Himawan, QUT; Wei Song, QUT; Dian Tjondronegoro, QUT
- Clustering of video-patches on Grassmannian manifold for facial expression recognition from 3D videos, Munawar Hayat, UWA; Mohammed Bennamoun, The University of Western Australia; Amar A. El-Sallam, UWA
- Automatic Identification of Exudates in Retinal Images, Flavio Henrique Araujo, Universidade federal do Piaui; Andre Santana, Universidade federal do Piaui; Rodrigo Veras, Universidade federal do Piaui; Romuere Silva, Universidade Federal do Piauí; Kelson Romulo Aires, UFPI. Pulled from proceedings due to no show.
- Classification of Human Epithelial Type 2 Cell Indirect Immunofluoresence Images via Codebook Based Descriptors, Arnold Wiliem, National ICT Australia, NICTA; Yongkang Wong, NICTA; Conrad Sanderson, NICTA; Shaokang Chen, NICTA; Peter Hobson, Sullivan Nicolaides Pathology; Brian Lovell, University of Queensland
- Spatio-Temporal Covariance Descriptors for Action and Gesture Recognition, Andres Sanin, NICTA; Conrad Sanderson, NICTA; Mehrtash Harandi, NICTA; Brian Lovell, University of Queensland
- Relational Divergence Based Classification on Riemannian Manifolds, Azadeh Alavi, NICTA; Mehrtash Harandi, NICTA; Conrad Sanderson, NICTA; Brian Lovell, University of Queensland
- Relative Ranking of Facial Attractiveness, Hani Altwaijry, UCSD; Serge Belongie, UCSD
- Robust classification system with reliability prediction for semi-automatic traffic-sign inventory systems, Lykele Hazelhoff, CycloMedia Technology B.V.; Ivo Creusen, Peter de With, Eindhoven University of Technology
9:45 - 10:15 Coffee Break
10:15 - 11:00 Plenary Talk
11:00 - 12:30 Short Oral Session 2
- A Lip Extraction Algorithm Using Region-based ACM With Automatic Contour Initialization, Chao Sui*, UniversityOfWesternAustralia; Mohammed Bennamoun, ; Roberto Togneri, University of Western Australia; Serajul Haque, University of Western Australia
- Scene Image Categorization and Video Event Detection using Naive Bayes Nearest Neighbor, Shiv Vitaladevuni, Raytheon BBN Technologies; Pradeep Natarajan, Raytheon BBN Technologies; Shuang Wu, Raytheon BBN Technologies; Rohit Prasad, Raytheon BBN Technologies; Premkumar Natarajan, Raytheon BBN Technologies
- Accurate Motion Deblurring using Camera Motion Tracking and Scene Depth, Hyeoungho Bae, University of California, Irvi; Charless Fowlkes, UC Irvine; Pai Chou, UC Irvine
- DIRSAC: A Directed Sampling And Consensus Approach to Quasi-Degenerate Data Fitting, Chris Baker, NREC; William Hoff, CSM
- Scallop Detection in Multiple Maritime Environments, Matthew Dawkins, RPI/Kitware; Charles Stewart, RPI
- What is the Space of Spectral Sensitivity Functions for Digital Color Cameras? JUN JIANG, Rochester Institute of Technol; Dengyu Liu, Rochester Institute of Technology; Jinwei Gu, Rochester Institute of Technology; Sabine Susstrunk, EPFL
- Robust Rank-4 Affine Factorization for Structure from Motion, Guanghui Wang, University of Waterloo; John Zelek, University of Waterloo; Q.M. Jonathan Wu, University of Windsor; Ruzena Bajcsy, UC Berkeley
- Using Kinect for Face Recognition Under Varying Poses, Expressions, Illumination and Disguise, Y.L. Billy Li, Curtin University; Ajmal Mian, University of Western Australia; Wanquan Liu, Curtin University; Aneesh Krishna, Curtin University
- Expanding gait identification methods from straight to curved trajectorie, Yumi Iwashita, Kyushu University; Koichi Ogawara, ; Ryo Kurazumes
- Wildfire Smoke Detection Using SpatioTemporal Bag-of-Features of Smoke, ByoungChul Ko, Keimyung University; Jun-Oh Park, Keimyung University; Jae-Yeal Nam, Keimyung University; SooYeong Kwak
- Animal Recognition in the Mojave Desert: Vision Tools for Field Biologists, Michael Wilber, University of Colorado; Walter Scheirer, Securics, Inc.; Terry Boult, University of Colorado at Colorado Springs
- Webcam2Satellite: Estimating Cloud Maps from Ground Sensors, Calvin Murdock, WUSTL; Nathan Jacobs, University of Kentucky; Robert Pless, WUSTL
- A low cost 3D markerless system for the reconstruction of athletic techniques, Amar A. El-Sallam, UWA; Mohammed Bennamoun, The University of Western Australia; Andrew Lyttle, Univ of Western Australia; Ferdous Sohel, Univ. of Western Australia; jacqueline Alderson, Univ of Western Australia
- HotSpotter - Species Independent Animal Instance Recognition, Jonathan Crall, RPI; Charles Stewart, RPI; Tanya Berger-Wolf, University of Illinois; Daniel Rubenstein, Princeton University
- Reconstructing a Fragmented Face from a Cryptographic Identification Protocol, Andy Luong, University of Texas at Austin; Michael Gerbush, Brent Waters, UT Austin; Kristen Grauman, UT Austin
- Periocular Biometric Recognition using Image Sets, Muhammad Uzair, CSSE, UWA; Arif Mahmood, CSSE, UWA; Ajmal Mian, University of Western Australia; Chris McDonald, CSSE, UWA
- An Experimental Study of Pupil Constriction for Liveness Detection, Xinyu Huang, North Carolina Central Univ.; Changepeng Ti, University of Kentucky; Alade Tokuta, North Carolina Central University; Ruigang Yang, University of Kentucky
- Automatic Content-Based Temporal Alignment of Image Sequences with Varying Spatio-Temporal Resolution, Sam Ogden, Brigham Young University; Bryan Morse, Brigham Young University
12:30 - 13:30 Lunch
12:30 - 15:00 Day 1 Poster Session
January 18th
7:00 - 8:00 Breakfast
8:05 - 9:45 Short Oral Session 3
- Ridge Regression based Classifiers for Large Scale Class Imbalanced Datasets, Devansh Arpit, Raytheon BBN Technologies; Shuang Wu, Raytheon BBN Technologies; Pradeep Natarajan*, Raytheon BBN Technologies; Rohit Prasad, Raytheon BBN Technologies; Premkumar Natarajan, Raytheon BBN Technologies
- A Relational Kernel-based Approach to Scene Classification, Laura Antanas, KUL; McElory Hoffmann, KUL; Paolo Frasconi, KUL; UNIFI; Tinne Tuytelaars, KUL; Luc De Raedt, KUL
- Person Re-identification using Semantic Color Names and RankBoos, Cheng-Hao Kuo*, Siemens Corporate Research; Sameh Khamis, University of Maryland; Vinay Shet, Siemens Corporate Researcht
- OpenVL: A Task-Based Abstraction for Developer-Friendly Computer Vision, Gregor Miller*, University of British Columbia; Sidney Fels, University of British Columbia
- Image Quality Quantification for Fingerprints Using Quality-Impairment Assessmen, Anurag Awasthi*, IIT Kanpur; Krithika Venkataramani, IIT Kanpur; Avani Nandini, IIT Kanpurt
- Shape and Image Retrieval by Organizing Instances Using Population Cues, Andrew Temlyakov, University of South Carolina; Pahal Dalal, ; Jarrell Waggoner, ; Dhaval Salvi, ; Song Wang
- "RegionCut" - Interactive Multi-Label Segmentation Utilizing Cellular Automaton, Björn Scheuermann, Inst. f. Informationsverarbeit; Jakob Arndt, ; Bodo Rosenhahn
- A High Resolution 3D Tire and Footprint Impression Acquisition for Forensics Applications, Ruwan Egoda Gamage, IUPUI; Abhishek Joshi, IUPUI; Jiang Zheng , IUPUI; Mihran Tuceryan, IUPUI
- Domain Adaptive Object Detection, Fatemeh Mirrashed, University of Maryland; Larry Davis, University of Maryland; vlad Morariu, ; Behjat Siddiquie, Rogerio Feris
- A Weakly Supervised Approach for Object Detection Based on Soft-Label Boosting, Weihong Wang, Nitional ICT Australia; Yang Wang, National ICT Australia; Fang Chen, National ICT Australia (NICTA); Arcot Sowmya, University of New South Wales
- Video Event Recognition Using Concept Attributes, Jingen Liu, SRI International Sarnoff; Qian Yu, SRI International
- Single View Pose Estimation of Mobile Devices in Urban Environments, Aaron Hallquist, UC Berkeley; Avideh Zakhor
- A Full-Spherical Device for Simultaneous Geometry and Reflectance Acquisition, Johannes Koehler, DFKI GmbH; Tobias Nöll, ; Gerd Reis, ; Didier Stricker
- Depth SEEDS: Recovering Incomplete Depth Data using Superpixels, Michael Van den Bergh, ETH Zurich; Luc Van Gool, ETH Zurich, KU Leuven
- Unwrapping the Eye for Visible-Spectrum Gaze Tracking on Wearable Devices, Bernardo Pires, Carnegie Mellon University; Michael Devyver, Carnegie Mellon University; Akihiro Tsukada, Takeo Kanade, Carnegie Mellon University
- Semantic Tie Points, Javier Montoya, ETHZ; Konrad Schindler, ; Christian Leistner
- Multi-Pose Multi-Target Tracking for Activity Understanding, Hamid Izadinia,; Varun Ramakrishna, Kris Kitani, Carnegie Mellon University; Daniel Huber
- Estimation of Camera Pose with Respect to Terrestrial LiDAR Data, Wei Guan, University of Southern Califor; Suya You, University of Southern California
- Fusing appearance and geometric constrains for estimating the epipolar geometry, Miguel Lourenço, ISR-UC; Nuno Gonçalves, ISR
- Illumination Invariant Mean-Shift Tracking, Gargi Phadke, IIT,Bombay
9:45 - 10:15 Coffee Break
10:15 - 11:00 Plenary Talk
11:00 - 12:30 Short Oral Session 4
- Image to LIDAR Matching for Geotagging in Urban Environments, Bogdan Matei, SRI International; Nicholas Vander Valk, SRI International; Zhiwei Zhu, SRI International; Hui Cheng, SRI International; Harpreet Sawhney, SRI International
- Improving Pollen Classification with Less Training Effort, Nhat Nguyen, UNC Charlotte; Min Shin, UNC Charlotte; Matina Donaldson-Matasci, University of Arizona
- Boosting Object Detection Performance in Crowded Surveillance Videos, Rogerio Feris, Ankur Datta, IBM Research; Sharath Pankanti, IBM Research; Ming-Ting Sun, University of Washington
- Robust Autocalibration for Surveillance Camera Network, Jingchen Liu, Penn State Univ; Robert Collins, Penn. State; Yanxi Liu, Penn. State
- Real-time Tracking of Low-Resolution Vehicles for Wide-Area Persistent Surveillance, Mark Keck, BAE Systems; Luis Galup, ; Chris Stauffer, BAE
- Laparoscopic Instrument Localization using a 3-D Time-of-Flight/RGB Endoscope, Sven Haase, Friedrich-Alexander-Universität Erlangen-Nürnberg; Thomas Kilgus, German Cancer Research Center; Jakob Wasza, Friedrich-Alexander-Universität Erlangen-Nürnberg; Joachim Hornegger, Friedrich-Alexander-Universität Erlangen-Nürnberg
- Automatic curve selection for lens distortion correction using Hough transform energy, Jinhai Cai, University of South Australia
- Gender Recognition Using 2-D Ear Images and Sparse Representation, Rahman Khorsandi, University of Miami; Mohamed Abdel-Mottaleb, University of Miami
- Geometric Calibration for a Multi-Camera-Projector System, Ricardo Garcia, UC Berkeley; Avideh Zakhor
- SAGE: A Principled Approach and Implementation Empowering Quick and Reliable Quantitative Analysis for Segmentation Comparison, Danna Gurari, Boston University; Seule Ki Kim, ; Eugene Yang, ; Brett Isenberg, ; Tuan Pham, ; Alberto Purwada, ; Patricia Solski, ; Matthew Walker, ; Joyce Wong, ; Margrit Betke
- A Bayesian Non-parametric Viewpoint to Visual Tracking, Yi Wang, UNSW/NICTA; Zhidong Li, ; Yang Wang, National ICT Australia; Fang Chen, National ICT Australia (NICTA)
- A Graph-Based Algorithm for Multi-Target Tracking with Occlusion, Dhaval Salvi, Jarrell Waggoner, Andrew Temlyakov, University of South Carolina; Song Wang
- The Gixel Array Descriptor (GAD) for Multi-Modal Image Matching, Guan Pang, Univ of Southern California; Ulrich Neumann, Univ of Southern California
- Handwritten Text Segmentation using Average Longest Path Algorithm, Dhaval Salvi, Jun Zhou, University of South Carolina; Jarrell Waggoner, Song Wang
- Spatial-Temporal Structural and Dynamics Features for Surveillance Video Fire Detection, Hongcheng Wang, UTRC
- Whale Blow Detection in Infrared Video using Fractal Analysis as Tool for Representing Dynamic Shape Variation, Varun Santhaseelan, University of Dayton; Vijayan Asari, University of Dayton
- Mass Anomaly Depth Estimation From Full Tensor Gradient Gravity Data, Daniel Wedge, The University of Western Aust
- Tracking Multiple Ants in a Colony, Thomas Fasciano, UNC Charlotte; Hoan Nguyen, UNCC; Anna Dornhaus, University of Arizona; Min Shin, UNC Charlotte
12:30 - 13:30 Lunch
12:30 - 15:00 Day 2 Poster Session + Awards