Oral Session 1: Multiple View and Stereo -- Multiple View Reconstruction of a Quadric of Revolution from Its Occluding Contours -- Robust Focal Length Estimation by Voting in Multi-view Scene Reconstruction -- Support Aggregation via Non-linear Diffusion with Disparity-Dependent Support-Weights for Stereo Matching -- Oral Session 2: Face and Pose Analysis -- Manifold Estimation in View-Based Feature Space for Face Synthesis across Poses -- Estimating Human Pose from Occluded Images -- Head Pose Estimation Based on Manifold Embedding and Distance Metric Learning -- 3D Reconstruction of Human Motion and Skeleton from Uncalibrated Monocular Video -- Oral Session 3: Motion Analysis and Tracking -- Mean-Shift Object Tracking with a Novel Back-Projection Calculation Method -- A Shape Derivative Based Approach for Crowd Flow Segmentation -- Learning Group Activity in Soccer Videos from Local Motion -- Combining Discriminative and Descriptive Models for Tracking -- Oral Session 4: Segmentation -- From Ramp Discontinuities to Segmentation Tree -- Natural Image Segmentation with Adaptive Texture and Boundary Encoding -- Gradient Vector Flow over Manifold for Active Contours -- 3D Motion Segmentation Using Intensity Trajectory -- Oral Session 5: Feature Extraction and Object Detection -- Vehicle Headlights Detection Using Markov Random Fields -- A Novel Visual Organization Based on Topological Perception -- Multilevel Algebraic Invariants Extraction by Incremental Fitting Scheme -- Towards Robust Object Detection: Integrated Background Modeling Based on Spatio-temporal Features -- Oral Session 6: Image Enhancement and Visual Attention -- Image Enhancement of Low-Light Scenes with Near-Infrared Flash Images -- A Novel Hierarchical Model of Attention: Maximizing Information Acquisition -- Interactive Shadow Removal from a Single Image Using Hierarchical Graph Cut -- Visual Saliency Based on Conditional Entropy -- Oral Session 7: Machine Learning Algorithms for Vision -- Evolving Mean Shift with Adaptive Bandwidth: A Fast and Noise Robust Approach -- An Online Framework for Learning Novel Concepts over Multiple Cues -- Efficient Partial Shape Matching of Outer Contours -- Level Set Segmentation Based on Local Gaussian Distribution Fitting -- Oral Session 8: Object Categorization and Face Recognition -- Categorization of Multiple Objects in a Scene without Semantic Segmentation -- Distance-Based Multiple Paths Quantization of Vocabulary Tree for Object and Scene Retrieval -- Image-Set Based Face Recognition Using Boosted Global and Local Principal Angles -- Incorporating Spatial Correlogram into Bag-of-Features Model for Scene Categorization -- Oral Session 9: Biometrics and Surveillance -- Human Action Recognition under Log-Euclidean Riemannian Metric -- Clustering-Based Descriptors for Fingerprint Indexing and Fast Retrieval -- Temporal-Spatial Local Gaussian Process Experts for Human Pose Estimation -- Finger-Vein Recognition Based on a Bank of Gabor Filters.

It gives us greatpleasureto presentthe proceedings of the 9th Asian Conference on Computer Vision (ACCV 2009), held in Xi’an, China, in September 2009. This was the ?rst ACCV conference to take place in mainland China. We received a total of 670 full submissions, which is a new record in the ACCV series. Overall, 35 papers were selected for oral presentation and 131 as posters, yielding acceptance rates of 5.2% for oral, 19.6% for poster, and 24.8% in total. In the paper reviewing, we continued the tradition of previous ACCVsbyconductingthe processinadouble-blindmanner.Eachofthe33Area Chairs received a pool of about 20 papers and nominated a number of potential reviewers for each paper. Then, Program Committee Chairs allocated at least three reviewers to each paper, taking into consideration any con?icts of interest and the balance of loads. Once the reviews were ?nished, the Area Chairs made summaryreportsforthepapersintheirpools,basedonthereviewers’comments and on their own assessments of the papers.