ACCV_MainConference_Program
ACCV 2014 – Main Conference Program
Main Conference - Day 1 (Nov 3rd, 2014)
7:45am Registration Opens
8:00am-8:30am Breakfast
8:30am-9:00am Breakfast + Poster Setup
9:00am Welcome + Announcements
9:15-10:15am Keynote: Deep Convolution Networks as Geometric Image Representations
Speaker: Stéphane Mallat, école Normale Supérieure (France)
10:15am-10:45am Coffee Break
11:00am-12:30pm Oral Session 1 (Recognition)
[15 minutes each: 12 minute talk + 2-3 minute Q&A]
O1: Deep Representations to Model User 'Likes'
O2: Submodular Reranking with Multiple Feature Modalities for Image Retrieval
O3: Accurate Scene Text Recognition based on Recurrent Neural Network
O4: Massive City-scale Surface Condition Analysis using Ground and Aerial Imagery
O5: Can Visual Recognition Benefit from Auxiliary Information in Training?
O6: Low Rank Representation on Grassmann Manifolds
12.30pm Lunch (served until 1.30pm)
1:15pm-3:15pm Poster Session 1 (Recognition, 3D Vision, Performance)
P1-01 Learning Detectors Quickly with Stationary Statistics
P1-02 Age Estimation Based on Complexity-Aware Features
P1-03 Efficient On-the-fly Category Retrieval using ConvNets and GPUs
P1-04 A Latent Clothing Attribute Approach for Human Pose Estimation
P1-05 NOKMeans: Non-Orthogonal K-means Hashing
P1-06 Visual vocabulary with a semantic twist
P1-07 Context Based Re-ranking for Object Retrieval
P1-08 Adaptive Structural Model for Video Based Pedestrian Detection
P1-09 Fusion of Auxiliary Imaging Information for Robust, Scalable and Fast 3D Reconstruction
P1-10 What Visual Attributes Characterize an Object Class ?
P1-11 Accurate Object Detection with Location Relaxation and Regionlets Re-localization
P1-12 Unsupervised Feature Learning for RGB-D Image Classification
P1-13 Non-Maximum Suppression for Object Detection by Passing Messages between Windows
P1-14 Stable Radial Distortion Calibration by Polynomial Matrix Inequalities Programming
P1-15 Pedestrian Verification for Multi-Camera Detection
P1-16 Color Photometric Stereo Using a Rainbow Light for Non-Lambertian Multicolored Surfaces
P1-17 Predicting the location of “interactees” in novel human-object interactions
P1-18 Robust Stereo Matching Using Probabilistic Laplacian Surface Propagation
P1-19 Imposing Differential Constraints on Radial Distortion Correction
P1-20 Automatic Shoeprint Retrieval Algorithm for Real Crime Scenes
P1-21 Lane Detection in Unstructured Environments for Autonomous Navigation Systems
P1-22 Multiple Stage Residual Model for Accurate Image Classification
P1-23 Hybrid-Indexing Multi-type Features for Large-scale Image Search
P1-24 Look Closely: Learning Exemplar Patches for Recognizing Textile Material from High-Resolution Images
P1-25 Action Recognition from a Single Web Image Based on an Ensemble of Pose Experts
P1-26 Scene Text Recognition and Retrieval for Large Lexicons
P1-27 Planar Structures from Line Correspondences in a Manhattan World
P1-28 LBP with Six Intersection Points: Reducing Redundant Information in LBP-TOP for Micro-expression Recognition P1-29 Deep Convolutional Neural Networks for Efficient Pose Estimation in Gesture Videos
P1-30 Robust Edge Aware Descriptor for Image Matching
P1-31 Robust Binary Feature Using Intensity Order
P1-32 Minimal solution for computing pairs of lines in non-central cameras
P1-33 Asymmetric Feature Representation for Object Recognition in Client Server System
P1-34 Leveraging High Level Visual Information for Matching Images and Captions
P1-35 Efficient Feature Coding based on Auto-Encoder Network for Image Classification
P1-36 Learning a Representative and Discriminative Part Model with Deep Convolutional Features for Scene Recognition P1-37 Image Representation Learning by Deep Appearance and Spatial Coding
P1-38 On the Exploration of Joint Attribute Learning for Person Re-identification
P1-39 Complimentary geometric and optical information for match-propagation-based 3D reconstruction
P1-40 Exploring Image Specific Structured Loss for Image Annotation with Incomplete Labelling
P1-41 Multi-View Geometry Compression
P1-42 Camera Calibration Based on the Common Self-polar Triangle of Sphere Images
P1-43 Multi-scale Tetrahedral Fusion of a Similarity Reconstruction and Noisy Positional Measurements
P1-44 DEPT: Depth Estimation by Parameter Transfer for Single Still Images
P1-45 Object Ranking on Deformable Part Models with Bagged LambdaMART
P1-46 Representation learning with Smooth Autoencoder
P1-47 Single Image Smoke Detection
P1-48 Adaptive Sparse Coding for Painting Style Analysis
P1-49 Efficient Image Detail Mining
P1-50 Accuracy and specificity trade-off in k-nearest neighbors classification
P1-51 Multi-view Point Cloud Registration using Affine Shape Distributions
P1-52 Part Detector Discovery in Deep Convolutional Neural Networks
P1-53 Performance Evaluation of 3D Local Feature Descriptors
P1-54 Scene Text Detection Based on Robust Stroke Width Transform and Deep Belief Network
P1-55 Cross-Modal Face Matching: Beyond Viewed Sketches
P1-56 3D Aware Correction and Completion of Depth Maps in Piecewise Planar Scenes
P1-57 Regularity Guaranteed Human Pose Correction
P1-58 Accelerated kmeans Clustering using Binary Random Projection
P1-59 Divide and Conquer: Efficient large-scale structure from motion using graph partitioning
P1-60 A homography formulation to the 3pt plus a common direction relative pose problem
P1-61 MoNet: A Deep Learning Framework Using Motion Features for Human Pose Estimation
P1-62 Accelerating Cost Volume Filtering Using Salient Subvolumes and Robust Occlusion Handling
P1-63 3D Human Pose Estimation from Monocular Images with Deep Convolutional Neural Network
P1-64 Plant Leaf Identification via A Growing Convolution Neural Network with Progressive Sample Learning
P1-65 Understanding Convolutional Neural Networks in Terms of Category-level Attributes
P1-66 Robust Scene Classification with Cross-level LLC Coding on CNN Features
P1-67 A graphical model for rapid obstacle image-map estimation from unmanned surface vehicles
P1-68 On the Performance of Pose-based RGB-D Visual Navigation Systems
P1-69 Elastic Shape Analysis of Boundaries of Planar Objects with Multiple Components and Arbitrary Topologies
1:15pm-3:15pm Demo Session 1 (Runs concurrent with Poster Session 1)
D1. Robust Real Time 6-DOF Tracking via Object Coordinate Regression
Alexander Krull, Frank Michel, Eric Brachmann, Stefan Gumhold, Stephan Ihrke, and Carsten Rother
(Technical University Dresden)
D2. "i-Bolt": Image-based Individual Identification of Metal Parts without Tag
Rui Ishiyama and Toru Takahashi (NEC Corporation)
D3. Efficient Image Detail Mining
Andrej Mikulik, Filip Radenovic, Ondrej Chum, and Jiri Matas (Czech Technical University in Prague)
3.15pm-
4.00pm Coffee Break
4.00pm-
5.15pm Oral Session 2 (3D Vision)
[15 minutes each: 12 minute talk + 2-3 minute Q&A]
O-07 A Minimal Solution to Relative Pose with Unknown Focal Length and Radial Distortion
O-08 Simultaneous Entire Shape Registration of Multiple Depth Images Using Depth Difference and Shape Silhouette
O-09 Joint Camera Pose Estimation and 3D Human Pose Estimation in a Multi-Camera Setup
O-10 Singly-Bordered Block-Diagonal Form for Minimal Problem Solvers
O-11 Stereo Fusion using a Refractive Medium on a Binocular Base
5.15-5.45pm Shuttle Buses to Subway Station
Main Conference - Day 2 (Nov 4th, 2014)
7:45am Registration Opens
8:00am-8:30am Breakfast
8:30am-9:00am Breakfast + Poster Setup
9:00am Announcements
9:15-10:15am Keynote: How Changing Mobile and Media Technologies is Changing The Way We Create Innovations
Speaker: Dr. Minoru (Mick) Etoh, NTT Docomo (Japan)
10:15am-10:45am Coffee Break
11:00am-12:30pm Oral Session 3 (Low-Level Vision and Features)
[15 minutes each: 12 minute talk + 2-3 minute Q&A]
O-12 Saliency Detection via Nonlocal L0 Minimization
O-13 N^4-Fields: Neural Network Nearest Neighbor Fields for Image Transforms
O-14 Super-Resolution Using Sub-Band Self-Similarity
O-15 Raindrop Detection and Removal from Long Range Trajectories
O-16 Interest Points via Maximal Self-Dissimilarities
O-17 Improving local features by dithering-based image sampling
12.30pm Lunch (served until 1.30pm)
1:15pm-3:15pm Poster Session 2 (Face and Gesture, Low-Level Vision, Statistical Methods, Medical)
P2-01 Sparse Kernel Learning for Image Set Classification
P2-02 Automatic Feature Learning to Grade Nuclear Cataracts Based on Deep Learning
P2-03 Texture classification using Dense Micro-block Difference (DMD)
P2-04 Nuclear-L1 Norm Joint Regression for Face Reconstruction and Recognition
P2-05 Segmentation of X-ray Images by 3D-2D Registration based on Multibody Physics
P2-06 View-Adaptive Metric Learning for Multi-view Person Re-identification
P2-07 Accurate Vessel Segmentation with Progressive Contrast Enhancement and Canny Refinement
P2-08 Eigen-PEP for Video Face Recognition
P2-09 Local Generic Representation for Face Recognition with Single Sample per Person
P2-10 Unsupervised Image Co-segmentation Based on Cooperative Game
P2-11 A High Performance CRF Model for Clothes Parsing
P2-12 Real-time Head Orientation from a Monocular Camera using Deep Neural Network
P2-13 Jointly Learning Dictionary and Subspace Structure for Video-based Face Recognition
P2-14 Visual Salience Learning via Low Rank Matrix Recovery
P2-15 A New Framework for Multiclass Classification Using Multiview Assisted Adaptive Boosting
P2-16 Age Estimation by Multi-scale Convolutional Network
P2-17 Photorealistic Face de-Identification by Agregating Donors' Face Components
P2-18 Which Image Pairs Will Cosegment Well? Predicting Partners for Cosegmentation
P2-19 Image Restoration via Multi-Prior Collaboration
P2-20 Modeling the Temporality of Saliency
P2-21 Salient Object Detection using Specific Location Prior and Multi-layer Background Contrast
P2-22 A Patch Aware Multiple Dictionary Framework for Demosaicing
P2-23 Large Margin Multi-Metric Learning for Face and Kinship Verification in the Wild
P2-24 A Three-color Coupled Level-Set Algorithm for Simultaneous Multiple Cell Segmentation and Tracking
P2-25 OR-PCA with MRF for Robust Foreground Detection in Highly Dynamic Backgrounds
P2-26 Segmentation of cells from spinning disk confocal images using a multi-stage approach
P2-27 Head Motion Signatures from Egocentric Videos
P2-28 Improving Saliency Models by Predicting Human Fixation Patches
P2-29 Fast Super-Resolution via Dense Local Training and Inverse Regressor Search
P2-30 PSPGC: Part-Based Seeds for Parametric Graph-Cuts
P2-31 Multi-cue mid-level grouping
P2-32 Simple-to-Complex Discriminative Clustering for Hierarchical Image Segmentation
P2-33 Learning One-Shot Exemplar SVM from the Web for Face Verification
P2-34 Unsupervised Segmentation of RGB-D Images
P2-35 Class-driven Color Transformation for Semantic Labeling
P2-36 Discovering Harmony: A Hierarchical Colour Harmony Model for Aesthetic Assessment
P2-37 Deconstructing Binary Classifiers in Computer Vision
P2-38 Effective Drusen Segmentation from Fundus Images for Age-related Macular Degeneration Screening
P2-39 Recognizing People by Their Personal Aesthetics: A Statistical Multi-View Approach
P2-40 FASA: Fast, Accurate, and Size-Aware Salient Object Detection
P2-41 Gesture Modeling by Hanklet-based Hidden Markov Model
P2-42 A Novel Face Spoofing Detection Method based on Gaze Estimation
P2-43 Hybrid Euclidean-and-Riemannian Metric Learning for Image Set Classification
P2-44 Size and Location Matter: a New Baseline for Salient Object Detection
P2-45 Learning Hierarchical Feature Representation in Depth Image
P2-46 Automatic Wrinkle Detection using Hybrid Hessian Filter
P2-47 Transductive Transfer Machine
P2-48 Fully Automatic Segmentation of Hip CT Images via Random Forest Regression-based Atlas Selection and Optimal Graph Search-based Surface Detection
P2-49 Optimal Transportation for Example-Guided Color Transfer
P2-50 Evaluation of Discriminative Models for the Reconstruction of Hand-Torn Documents
P2-51 Hand segmentation with structured convolutional learning
P2-52 Topic-aware Deep Auto-encoders (TDA) for Face Alignment
P2-53 Accelerating the Distribution Estimation for the Weighted Median/Mode Filters
P2-54 Saliency aggregation: Does unity make strength?
P2-55 Spontaneous Subtle Expression Recognition: Imbalanced Databases & Solutions
P2-56 EPML: Expanded Parts based Metric Learning for Occlusion Robust Face Verification
P2-57 Pixel-Level Hand Detection with Shape-aware Structured Forest
P2-58 Beyond procedural facade parsing: Bidirectional alignment via linear programming
P2-59 Shape Matching Using Point Context and Contour Segments
P2-60 A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution
P2-61 Multiple Ocular Diseases Classification with Graph Regularized Probabilistic Multi-label Learning
P2-62 Deeply Learning Deformable Facial Action Parts Model for Dynamic Expression Analysis
P2-63 A Novel Context-Aware Topic Model for Category Discovery in Natural Scenes
P2-64 Robust Sharpness Metrics using Reorganized DCT Coefficients for Auto-Focus Application
P2-65 DisLocation: Scalable descriptor distinctiveness for location recognition
P2-66 Discriminative Collaborative Representation for Classification
P2-67 Thread-Safe: Towards Recognizing Human Action Across Shot Boundaries
1:15pm-3:15pm Demo Session 2 (Runs Concurrent with Poster Session 2)
D-4. Novel Continuous-Multi-Class Cascade for Real-Time Emotional Recognition
Jinhui Chen, Tetsuya Takiguchi and Yasuo Ariki (Kobe University)
D-5. Scyllarus: A Matlab toolbox aimed at supporting the research on imaging spectroscopy for scene analysis
Nariman Habili, Ran Wei and Antonio Robles-Kelly (NICTA, Australian National University)
D-6. Automatic Real Crime Scene Shoeprint Retrieval System
Xinnian Wang, Huihui Sun, Qing Yu and Chi Zhang (Dalian Maritime University)
3.15pm-
4.00pm Coffee Break
4.00pm-
5.00pm Oral Session 4 (Segmentation)
[15 minutes each: 12 minute talk + 2-3 minute Q&A]
O-18 Consistent Foreground Co-segmentation
O-19 On Multiple Image Group Cosegmentation
O-20 Reconstructive Sparse Code Transfer for Contour Detection and Semantic Labeling
O-21 A Message Passing Algorithm for MRF Inference with Unknown Graphs and Its Applications
5.00-
6.00pm Transport to Banquet
6.00pm-9.00pm Conference Banquet (Hilton Hotel)
Main Conference - Day 3 (Nov 5th, 2014)
7:45am Registration Opens
8:00am-8:30am Breakfast
8:30am-9:00am Breakfast + Poster Setup
9:00am Announcements
9:15-10:15am Keynote: RGB-D Perception in Robotics
Speaker: Prof. Dieter Fox, University of Washington (USA)
10:15am-10:45am Coffee Break
11:00am-12:30pm Oral Session 5 (Face and Gesture, Tracking)
[15 minutes each: 12 minute talk + 2-3 minute Q&A]
O-22 Joint Estimation of Pose and Face Landmark
O-23 Probabilistic Subpixel Temporal Registration for Facial Expression Analysis
O-24 Depth Recovery with Face Prior
O-25 Inlier Estimation for Moving Camera Motion Segmentation
O-26 Real-time Tracking of Multiple Objects by Linear Motion and Repulsive Motion
O-27 6-DOF Model Based Tracking via Object Coordinate Regression
12.30pm Lunch (served until 1.30pm)
1:15pm-3:15pm Poster Session 3 (Video & Activities, Motion and Tracking, Vision for X)
P3-01 Probabilistic state space decomposition for tracking articulated objects
P3-02 Spectral Graph Skeletons for 3D Action Recognition
P3-03 Robust Point Matching using Mixture of Asymmetric Gaussians for Nonrigid Transformation
P3-04 Multiple Object Tracking by Efficient Graph Partitioning
P3-05 Fast Approximate Nearest-Neighbor Field by Cascaded Spherical Hashing
P3-06 Coupling Semi-supervised Learning and Example Selection for Online Object Tracking
P3-07 Reconstructing Shape and Appearance of Thin Film Objects with Hyper Spectral Sensor
P3-08 A Two-Stage Approach for Bag Detection in Pedestrian Images
P3-09 Recognizing Daily Activities from First-person Videos with Multi-task Clustering
P3-10 Multi-View Recognition Using Weighted View Selection
P3-11 Graph Transduction Learning of Object Proposals for Video Object Segmentation
P3-12 Forecasting Event using an Augmented Hidden Conditional Random Field
P3-13 Camera Movement and Surrounding Scene Appearance as Contextual Features for Action Recognition P3-14 Semi-Supervised Ranking for Re-Identification with Few Labeled Image Pairs
P3-15 Robust Visual Tracking with Dual Group Structure
P3-16 3D Reconstruction of Specular Objects with Occlusion: A Shape-from-Scattering Approach
P3-17 2D Or Not 2D: Bridging the Gap Between Tracking and Structure from Motion
P3-18 Clouds in The Cloud
P3-19 Fast segmentation of sparse 3D point trajectories using group theoretical invariants
P3-20 Superpixels for Video Content Using a Contour-based EM Optimization
P3-21 Transformed Principal Gradient Orientation for Robust and Precise Batch Face Alignment
P3-22 Improving Human Action Recognition using Score Distribution and Ranking
P3-23 Context-Aware Activity Forecasting
P3-24 DMM-Pyramid Based Deep Architetures for Action Recognition with Depth Cameras
P3-25 Discriminative Orderlet Mining For Real-time Recognition of Human-Object Interaction
P3-26 Anomaly Detection via Local Coordinate Factorization and Spatio-temporal Pyramid
P3-27 Intrinsic Image Decomposition from Pair-wise Shading Ordering
P3-28 Never Get Lost Again: Vision Based Navigation using StreetView Images
P3-29 Qualitative and Quantitative Spatio-Temporal Relations in Daily Living Activity Recognition
P3-30 Blur-Resilient Tracking Using Group Sparsity
P3-31 Visual Tracking via Supervised Similarity Matching
P3-32 Multi-State Discriminative Video Segment Selection for Complex Event Classification
P3-33 Action Recognition in the Presence of One Egocentric and Multiple Static Cameras
P3-34 Robust Online Visual Tracking with an Single Convolutional Neural Network
P3-35 Bi-Stage Large Point Set Registration Using Gaussian Mixture Models
P3-36 Enhanced Sequence Matching for Action Recognition from 3D Skeletal Data
P3-37 Multi-label Discriminative Weakly-Supervised Human Activity Recognition and Localization
P3-38 Action-Gons: Action Recognition with A Discriminative Dictionary of Structured Elements with Varying Granularity
P3-39 Fast Inference of Contaminated Data for Real Time Object Tracking
P3-40 Data mining for Action Recognition
P3-41 A Rotation-Invariant Regularization Term for Optical Flow Related Problems
P3-42 Landmark-based Inductive Model for Robust Discriminative Tracking
P3-43 Extended Co-occurrence HOG with Dense Trajectories for Fine-grained Activity Recognition
P3-44 Motion Based Foreground Detection and Poselet Motion Features for Action Recognition
P3-45 Global Motion Estimation from Relative Measurements in the Presence of Outliers
P3-46 Clustering Ensemble Tracking
P3-47 Query Based Adaptive Re-Ranking for Person Re-Identification
P3-48 Improved Color Patch Similarity Measure Based Weighted Median Filter
P3-49 Efficient Pose-based Action Recognition
P3-50 Tracking Multiple People Online and in Real Time
P3-51 Optimizing Storage Intensive Vision Applications to Device Capacity
P3-52 MTS: A Multiple Temporal Scale Tracker Handling Occlusion and Abrupt Motion Variation
P3-53 Video Annotation by Incremental Learning from Grouped Heterogeneous Sources
P3-54 A Novel Group Sparsity Optimization based Feature Selection Model for Complex Interaction Recognition
P3-55 Boosting-based Visual Tracking using Structural Local Sparse Descriptors
P3-56 Coupling Multiple Alignments and Re-ranking for Low-Latency Online Multi-target Tracking
P3-57 Determining Interacting Objects in Human-Centric Activities via Qualitative Spatio-Temporal Reasoning
P3-58 Enhanced Laplacian Group Sparse Learning with Lifespan Outlier Rejection for Visual Tracking
P3-59 Cross-view Action Recognition via Dual-Codebook and Hierarchical Transfer Framework
1:15pm-3:15pm Demo Session 3 (Runs Concurrent with Poster Session 3)
D-7. Stereo Fusion using a Refractive Medium on a Binocular Base
Seung-Hwan Baek and Min H. Kim (KAIST)
D-8. VideoSum: A Video Storing, Processing and Summarization Platform
Vasileios Chasanis, Costas Voglis Antonios Ioannidis, Aristidis Likas (University of Ioannia), Aris Lanaridis, Eleni Vathi, Geogios Siolas, and Andreas Stafylopatis (University of Athens)
9. Audio and Video Surveillance System for Public Safety
Takeshi Arikuma, Masahiro Tani and Tsunehisa Kawamata (NEC Labatorites Singapore)
3.15pm-
4.00pm Coffee Break
4.00pm-
5.15pm Oral Session 6 (Stereo, Physics, Video & Events)
O-28 Stereo Ground Truth With Error Bars
O-29 Separation of Reflection Components by Sparse Non-negative Matrix Factorization
O-30 Spatiotemporal Derivative Pattern: A Dynamic Texture Descriptor for Video Matching
O-31 Weakly Supervised Action Recognition and Localization using Web Images
O-32 A Game-Theoretic Probabilistic Approach for Detecting Conversational Groups
5.15pm Closing Remarks