ICCV 2015

530 papers

Top Research Directions

Research directions most represented by ICCV 2015 papers.

The Irreversible Bottleneck of Superpixel Boundary Errors 9
Eliminating the Optical Flow Bottleneck in Video Understanding 9
Shared Feature Map Computation for Efficient Visual Recognition 8
Scaling Memory Banks for High Dimensional Features 8
Overcoming the Iterative Bottleneck in Sparse Representation 8
Resolving Geometric Symmetry Ambiguity in 3D Pose Estimation 8
Unsupervised Part Discovery for Fine-Grained Recognition 7
Preserving Topological Connectivity in Thin Structure Segmentation 6
Joint Optimization of Camera Poses and Neural Geometry 6
Bridging the Weakly Supervised Localization Gap 6
Relaxing the Manhattan World Assumption 6
Reconstructing Complete Geometry from Partial Point Clouds 6
Resolving Depth Ambiguity in Monocular 3D Reconstruction 6
Resolving Kinematic Ambiguity in Skeleton Based Action Recognition 5
Robust Separation via Low Rank and Sparse Decomposition 5

Top Authors

AuthorPapers
Shuicheng YAN9
Jitendra Malik7
Xiaogang Wang7
Cordelia Schmid6
Jiaya Jia6
Marc Pollefeys6
Sanja Fidler6
Thomas Brox6
Tinne Tuytelaars6
Abhinav Gupta5
Alan Yuille5
Andrew W Fitzgibbon5
Daniel Cremers5
Mathieu Salzmann5
Raquel Urtasun5
Torsten Sattler5
Trevor Darrell5
Alexei A Efros4
Chen Change Loy4
Deva Ramanan4

Impactful Papers

Papers from ICCV 2015 that shaped research clusters.

Foundational

Influential

Papers

Title
Relaxing from Vocabulary: Robust Weakly-Supervised Deep Learning for Vocabulary-Free Image Tagging
Removing Rain from a Single Image via Discriminative Sparse Coding
Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
Rendering of Eyes for Eye-Shape Registration and Gaze Estimation
Resolving Scale Ambiguity via XSlit Aspect Ratio Analysis
RGB-Guided Hyperspectral Image Upsampling
RGB-W: When Vision Meets Wireless
RIDE: Reversal Invariant Descriptor Enhancement
Robust and Optimal Sum-of-Squares-Based Point-to-Plane Registration of Image Sets and Structured Scenes
Robust Facial Landmark Detection Under Significant Head Poses and Occlusion
Robust Heart Rate Measurement from Video Using Select Random Patches
Robust Image Segmentation Using Contour-Guided Color Palettes
Robust Model-Based 3D Head Pose Estimation
Robust Non-rigid Motion Tracking and Surface Reconstruction Using L0 Regularization
Robust Nonrigid Registration by Convex Optimization
Robust Optimization for Deep Regression
Robust Principal Component Analysis on Graphs
Robust RGB-D Odometry Using Point and Line Features
Robust Statistical Face Frontalization
Rolling Shutter Super-Resolution
SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural Networks
Scalable Nonlinear Embeddings for Semantic Category-Based Image Retrieval
Scalable Person Re-identification: A Benchmark
Scene-Domain Active Part Models for Object Representation
Secrets of GrabCut and Kernel K-Means
Secrets of Matrix Factorization: Approximations, Numerics, Manifold Optimization and Random Restarts.
See the Difference: Direct Pre-Image Reconstruction and Pose Estimation by Differentiating HOG
Segment Graph Based Image Filtering: Fast Structure-Preserving Smoothing
Segment-Phrase Table for Semantic Segmentation, Visual Entailment and Paraphrasing
Selecting Relevant Web Trained Concepts for Automated Event Retrieval
Selective Encoding for Recognizing Unreliably Localized Faces
Self-Calibration of Optical Lenses
Self-Occlusions and Disocclusions in Causal Video Object Segmentation
Semantically-Aware Aerial Reconstruction from Multi-modal Data
Semantic Component Analysis
Semantic Image Segmentation via Deep Parsing Network
Semantic Pose Using Deep Networks Trained on Synthetic RGB-D
Semantic Segmentation of RGBD Images with Mutex Constraints
Semantic Segmentation with Object Clique Potential
Semantic Video Entity Linking Based on Visual Content and Metadata
Semi-Supervised Normalized Cuts for Image Segmentation
Semi-Supervised Zero-Shot Classification with Label Representation Learning
Separating Fluorescent and Reflective Components by Using a Single Hyperspectral Image
Sequence to Sequence - Video to Text
Shape Interaction Matrix Revisited and Robustified: Efficient Subspace Clustering with Corrupted and Incomplete Data
Shell PCA: Statistical Shape Modelling in Shell Space.
Similarity Gaussian Process Latent Variable Model for Multi-modal Data Analysis
Simpler Non-Parametric Methods Provide as Good or Better Results to Multiple-Instance Learning
Simultaneous Deep Transfer Across Domains and Tasks
Simultaneous Foreground Detection and Classification with Hybrid Features

« prev Page 9/11 next »