ICCV 2013

458 papers

Top Research Directions

Research directions most represented by ICCV 2013 papers.

Geometric Degeneracy in Camera Pose Estimation 9
Constant Time Spatial Aggregation with Integral Images 8
The Irreversible Bottleneck of Superpixel Boundary Errors 8
Optical Flow Sensitivity in Downstream Video Tasks 6
Modeling Non-Rigid Deformations in Dynamic 3D Scenes 6
Decoupling Rotation and Translation in Pose Estimation 5
Curvature Regularization for Boundary and Surface Optimization 5
Geometric Verification for Robust Feature Matching 5
Architectures for Streaming Video Understanding 5
Geometric Drift in Incremental 3D Reconstruction 5
Achieving Viewpoint Invariance in Computer Vision 5
Robust Feature Extraction for Unconstrained Video Analysis 5
Overcoming the Iterative Bottleneck in Sparse Representation 5
Basins of Attraction in Nonconvex Optimization 5
Resolving the Hollow Effect in Object Saliency Maps 4

Top Authors

AuthorPapers
Shuicheng YAN11
Luc Van Gool10
Cordelia Schmid8
Song-Chun Zhu8
Daniel Cremers6
Lei Zhang6
Ming-Hsuan Yang6
Antonio Torralba5
Kristen Grauman5
Marc Pollefeys5
Tinne Tuytelaars5
Bernt Schiele4
Chunhua Shen4
Devi Parikh4
In So Kweon4
Jiaya Jia4
Karteek Alahari4
Lei Zhang4
Li Fei-Fei4
Raquel Urtasun4

Impactful Papers

Papers from ICCV 2013 that shaped research clusters.

Foundational

Influential

Papers

Title
Stacked Predictive Sparse Coding for Classification of Distinct Regions in Tumor Histopathology
STAR3D: Simultaneous Tracking and Reconstruction of 3D Objects Using RGB-D Data
Street View Motion-from-Structure-from-Motion
Strong Appearance and Expressive Spatial Models for Human Pose Estimation
Structured Forests for Fast Edge Detection
Structured Learning of Sum-of-Submodular Higher Order Energy Functions
Structured Light in Sunlight
Style-Aware Mid-level Representation for Discovering Visual Connections in Space and Time
Subpixel Scanning Invariant to Indirect Lighting Using Quadratic Code Length
SUN3D: A Database of Big Spaces Reconstructed Using SfM and Object Labels
Super-resolution via Transform-Invariant Group-Sparse Regularization
Supervised Binary Hash Code Learning with Jensen Shannon Divergence
Support Surface Prediction in Indoor Scenes
Symbiotic Segmentation and Part Localization for Fine-Grained Categorization
SYM-FISH: A Symmetry-Aware Flip Invariant Sketch Histogram Shape Descriptor
Synergistic Clustering of Image and Segment Descriptors for Unsupervised Scene Understanding
Target-Driven Moire Pattern Synthesis by Phase Modulation
Temporally Consistent Superpixels
Text Localization in Natural Images Using Stroke Feature Transform and Text Covariance Descriptors
The Interestingness of Images
The Moving Pose: An Efficient 3D Kinematics Descriptor for Low-Latency Action Recognition and Detection
The Way They Move: Tracking Multiple Targets with Similar Appearance
To Aggregate or Not to aggregate: Selective Match Kernels for Image Search
Topology-Constrained Layered Tracking with Latent Flow
Total Variation Regularization for Functions with Values in a Manifold
Toward Guaranteed Illumination Models for Non-convex Objects
Towards Motion Aware Light Field Video for Dynamic Scenes
Towards Understanding Action Recognition
Tracking Revisited Using RGBD Camera: Unified Benchmark and Baselines
Tracking via Robust Multi-task Multi-view Joint Sparse Representation
Training Deformable Part Models with Decorrelated Features
Transfer Feature Learning with Joint Distribution Adaptation
Translating Video Content to Natural Language Descriptions
Tree Shape Priors with Connectivity Constraints Using Convex Relaxation on General Graphs
Two-Point Gait: Decoupling Gait from Body Shape
Unbiased Metric Learning: On the Utilization of Multiple Datasets and Web Images for Softening Bias
Uncertainty-Driven Efficiently-Sampled Sparse Graphical Models for Concurrent Tumor Segmentation and Atlas Registration
Understanding High-Level Semantics by Modeling Traffic Patterns
Unifying Nuclear Norm and Bilinear Factorization Approaches for Low-Rank Matrix Decomposition
Unsupervised Domain Adaptation by Domain Invariant Projection
Unsupervised Intrinsic Calibration from a Single Frame Using a "Plumb-Line" Approach
Unsupervised Random Forest Manifold Alignment for Lipreading
Unsupervised Visual Domain Adaptation Using Subspace Alignment
Video Co-segmentation for Meaningful Action Extraction
Video Event Understanding Using Natural Language Descriptions
Video Motion for Every Visible Point
Video Segmentation by Tracking Many Figure-Ground Segments
Video Synopsis by Heterogeneous Multi-source Correlation
Viewing Real-World Faces in 3D
Visual Reranking through Weakly Supervised Multi-graph Learning

« prev Page 9/10 next »