iccv 2015 论文列表
2015 IEEE International Conference on Computer Vision Workshop, ICCV Workshops 2015, Santiago, Chile, December 7-13, 2015.
|
Fast Structure from Motion for Sequential and Wide Area Motion Imagery.
Towards Large-Scale Face Recognition Based on Videos.
Video Summarization via Segments Summary Graphs.
A Scalable Architecture for Operational FMV Exploitation.
Hierarchical Union-of-Subspaces Model for Human Activity Summarization.
Semantic Cross-View Matching.
Single Frame Based Video Geo-Localisation Using Structure Projection.
Geometric Mining: Scaling Geometric Hashing to Large Datasets.
Fisher Encoded Convolutional Bag-of-Windows for Efficient Image Retrieval and Social Image Tagging.
Scalable Sketch-Based Image Retrieval Using Color Gradient Features.
The First Facial Landmark Tracking in-the-Wild Challenge: Benchmark and Results.
Facial Shape Tracking via Spatio-Temporal Cascade Shape Regression.
Facial Landmark Detection via Progressive Initialization.
Shape Augmented Regression Method for Face Alignment.
Multi-view Constrained Local Models for Large Head Angle Facial Tracking.
Facial Landmark Tracking by Tree-Based Deformable Part Model Based Detector.
Offline Deformable Face Tracking in Arbitrary Videos.
Online Stochastic Tensor Decomposition for Background Subtraction in Multispectral Video Sequences.
Adaptive Low Rank Approximation for Tensors.
Background Subtraction via Superpixel-Based Online Matrix Decomposition with Structured Foreground Constraints.
Multi-resolution Dynamic Mode Decomposition for Foreground/Background Separation and Object Tracking.
Visual Tracking via Nonnegative Regularization Multiple Locality Coding.
Object Extraction from Bounding Box Prior with Double Sparse Reconstruction.
Image Saliency Detection with Sparse Representation of Learnt Texture Atoms.
Robust Matrix Regression for Illumination and Occlusion Tolerant Face Recognition.
Pose and Expression-Coherent Face Recovery in the Wild.
Filtrated Spectral Algebraic Subspace Clustering.
Sparse Subspace Clustering for Incomplete Images.
Dual Principal Component Pursuit.
A Simple Method for Subspace Estimation with Corrupted Columns.
Geodesic Convolutional Neural Networks on Riemannian Manifolds.
Reconstruction of Articulated Objects from a Moving Camera.
Dense Rigid Reconstruction from Unstructured Discontinuous Video.
Building the View Graph of a Category by Exploiting Image Realism.
3-D Volumetric Shape Abstraction from a Single 2-D Image.
Depth Compensation Model for Gaze Estimation in Sport Analysis.
Predicting Ball Ownership in Basketball from a Monocular View Using Only Player Trajectories.
Injury Mechanism Classification in Soccer Videos.
Audio-Visual Classification of Sports Types.
Understanding Sport Activities from Correspondences of Clustered Trajectories.
Attributed Graphs for Tracking Multiple Objects in Structured Sports Videos.
Tracking When the Camera Looks Away.
Soccer Jersey Number Recognition Using Convolutional Neural Networks.
Stroboscopic Image Synthesis of Sports Player from Hand-Held Camera Sequence.
Tennis Player Segmentation for Semantic Behavior Analysis.
Person Tracking Using Audio and Depth Cues.
Tracking the Active Speaker Based on a Joint Audio-Visual Observation Model.
Seeing the Sound: A New Multimodal Imaging Device for Computer Vision.
Preface to 3D Reconstruction and Understanding with Video and Sound.
Crowdpainting with Light: Participatory Imaging at the Big Shot.
Exploring the Resolution Limit for In-Air Synthetic-Aperture Audio Imaging.
Estimating a Small Signal in the Presence of Large Noise.
Low Power Depth and Velocity from a Passive Moving Sensor.
FlatCam: Replacing Lenses with Masks and Computation.
Scotopic Visual Recognition.
A Century of Portraits: A Visual Historical Record of American High School Yearbooks.
The Thermal Infrared Visual Object Tracking VOT-TIR2015 Challenge Results.
Tracker Fusion on VOT Challenge: How Does It Perform and What Can We Learn about Single Trackers?
Convolutional Features for Correlation Filter Based Visual Tracking.
Multi-template Scale-Adaptive Kernelized Correlation Filters.
Robust Visual Tracking by Exploiting the Historical Tracker Snapshots.
Joint Scale-Spatial Correlation Tracking with Adaptive Rotation Estimation.
Scalable Kernel Correlation Filter with Sparse Feature Integration.
The Visual Object Tracking VOT2015 Challenge Results.
Pedestrian Detection via Mixture of CNN Experts and Thresholded Aggregated Channel Features.
Fine-Grained Product Class Recognition for Assisted Shopping.
Automatic Emotion Recognition in Robot-Children Interaction for ASD Treatment.
Head Nod Detection from a Full 3D Model.
A Stereo Vision Approach for Cooperative Robotic Movement Therapy.
Quantifying Levodopa-Induced Dyskinesia Using Depth Camera.
A Fast and Accurate Eye Tracker Using Stroboscopic Differential Lighting.
Single-Frame Indexing for 3D Hand Pose Estimation.
A Structured Committee for Food Recognition.
Deep Learning of Mouth Shapes for Sign Language.
Saliency Detection Using Quaternion Sparse Reconstruction.
Visual Attention-Guided Approach to Monitoring of Medication Dispensing Using Multi-location Feature Saliency Patterns.
Evaluating Real-Time Mirroring of Head Gestures Using Smart Glasses.
Summarizing While Recording: Context-Based Highlight Detection for Egocentric Videos.
Accurate Human-Limb Segmentation in RGB-D Images for Intelligent Mobility Assistance Robots.
Estimating Body Pose of Infants in Depth Images Using Random Ferns.
Improving Indoor Mobility of the Visually Impaired with Depth-Based Spatial Sound.
An Intuitive Mobility Aid for Visually Impaired People Based on Stereo Vision.
An Evaluation of Supervised, Novelty-Based and Hybrid Approaches to Fall Detection Using Silmee Accelerometer Data.
Recognizing Personal Contexts from Egocentric Images.
When Face Recognition Meets with Deep Learning: An Evaluation of Convolutional Neural Networks for Face Recognition.
Facial Landmark Localization in Depth Images Using Supervised Ridge Descent.
Coordinated Local Metric Learning.
An End-to-End System for Unconstrained Face Verification with Deep Convolutional Neural Networks.
Unconstrained Age Estimation with Deep Convolutional Neural Networks.
Deep Label Distribution Learning for Apparent Age Estimation.
Deeply Learned Rich Coding for Cross-Dataset Facial Age Estimation.
Person Attribute Recognition with a Jointly-Trained Holistic CNN Model.
Motion Recognition Employing Multiple Kernel Learning of Fisher Vectors Using Local Skeleton Features.
Skeleton-Free Body Pose Estimation from Depth Images for Movement Analysis.
Moving Poselets: A Discriminative and Interpretable Skeletal Motion Representation for Action Recognition.
DLDR: Deep Linear Discriminative Retrieval for Cultural Event Classification from a Single Image.
Better Exploiting OS-CNNs for Better Event Recognition in Images.
Deep Spatial Pyramid Ensemble for Cultural Event Recognition.
Exploiting Feature Hierarchies with Convolutional Neural Networks for Cultural Event Recognition.
A Study on Apparent Age Estimation.
AgeNet: Deeply Learned Regressor and Classifier for Robust Apparent Age Estimation.
DEX: Deep EXpectation of Apparent Age from a Single Image.
ChaLearn Looking at People 2015: Apparent Age and Cultural Event Recognition Datasets and Results.
Scene Intrinsics and Depth from a Single Image.
Efficient and Robust Inverse Lighting of a Single Face Image Using Compressive Sensing.
Multi-Shot Deblurring for 3D Scenes.
Bilayer Blind Deconvolution with the Light Field Camera.
Joint Estimation of Depth, Reflectance and Illumination for Depth Refinement.
A Modified Sequential Monte Carlo Bayesian Occupancy Filter Using Linear Opinion Pool for Grid Mapping.
A Multi-View Pedestrian Tracking Method in an Uncalibrated Camera Network.
Surface Recovery: Fusion of Image and Point Cloud.
Video Event Recognition by Combining HDP and Gaussian Process.
Incremental Division of Very Large Point Clouds for Scalable 3D Surface Reconstruction.
Fusion of Inertial and Visual Measurements for RGB-D SLAM on Mobile Devices.
Goal-Directed Pedestrian Prediction.
Sequential Score Adaptation with Extreme Value Theory for Robust Railway Track Inspection.
Semantic Mapping of Large-Scale Outdoor Scenes for Autonomous Off-Road Driving.
Latent Hierarchical Part Based Models for Road Scene Understanding.
The Statistics of Driving Sequences - And What We Can Learn from Them.
Direct Visual Localisation and Calibration for Road Vehicles in Changing City Environments.
Position Interpolation Using Feature Point Scale for Decimeter Visual Localization.
Anatomical Landmark Detection in Medical Applications Driven by Synthetic Data.
Adapted Domain Specific Class Means.
Beyond Photo-Domain Object Recognition: Benchmarks for the Cross-Depiction Problem.
N-to-SRGB Mapping for Single-Sensor Multispectral Imaging.
Learning a Deep Convolutional Network for Light-Field Image Super-Resolution.
A Hybrid Strategy for Illuminant Estimation Targeting Hard Images.
HDR Recovery Under Rolling Shutter Distortions.
Metamer Mismatching and Its Consequences for Predicting How Colours are Affected by the Illuminant.
FaceCept3D: Real Time 3D Face Tracking and Analysis.
Do Deep Neural Networks Learn Facial Action Units When Doing Expression Recognition?
Facial Action Unit Detection Using Active Learning and an Efficient Non-linear Kernel Approximation.
Facial Micro-Expression Recognition Using Spatiotemporal Local Binary Pattern with Integral Projection.
