NDLI: Unsupervised Semantic Parsing of Video Collections

Please wait, while we are loading the content...

2015 IEEE International Conference on Computer Vision (ICCV)

Table of Contents

Message from the General Chair and Program Chairs

ICCV 2015 Area Chairs

ICCV 2015 Reviewers

Ask Your Neurons: A Neural-Based Approach to Answering Questions about Images

Segment-Phrase Table for Semantic Segmentation, Visual Entailment and Paraphrasing

Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books

Learning Query and Image Similarities with Ranking Canonical Correlation Analysis

Learning to See by Moving

Object Detection Using Generalization and Efficiency Balanced Co-Occurrence Features

Mining And-Or Graphs for Graph Matching and Object Discovery

Pose Induction for Novel Object Categories

Dynamic Texture Recognition via Orthogonal Tensor Dictionary Learning

Convolutional Channel Features

Local Convolutional Features with Unsupervised Training for Image Retrieval

RIDE: Reversal Invariant Descriptor Enhancement

Discrete Tabu Search for Graph Matching

Discriminative Learning of Deep Convolutional Feature Point Descriptors

Amodal Completion and Size Constancy in Natural Scenes

Learning Where to Position Parts in 3D

Query Adaptive Similarity Measure for RGB-D Object Recognition

Listening with Your Eyes: Towards a Practical Visual Speech Recognition System Using Deep Boltzmann Machines

Cluster-Based Point Set Saliency

A Comprehensive Multi-Illuminant Dataset for Benchmarking of the Intrinsic Image Algorithms

PatchMatch-Based Automatic Lattice Detection for Near-Regular Textures

A Data-Driven Metric for Comprehensive Evaluation of Saliency Models

A Matrix Decomposition Perspective to Multiple Graph Matching

Fast and Effective L0 Gradient Minimization by Region Fusion

Generic Promotion of Diffusion-Based Salient Object Detection

Nighttime Haze Removal with Glow and Multiple Light Colors

Conformal and Low-Rank Sparse Representation for Image Restoration

Patch Group Based Nonlocal Self-Similarity Prior Learning for Image Denoising

Automatic Thumbnail Generation Based on Visual Representativeness and Foreground Recognizability

SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural Networks

A Novel Sparsity Measure for Tensor Recovery

Oriented Object Proposals

Learning Nonlinear Spectral Filters for Color Image Reconstruction

Beyond White: Ground Truth Colors for Color Constancy Correction

RGB-Guided Hyperspectral Image Upsampling

Projection onto the Manifold of Elongated Structures for Accurate Extraction

Naive Bayes Super-Resolution Forest

POP Image Fusion -- Derivative Domain Image Fusion without Reintegration

Adaptive Spatial-Spectral Dictionary Learning for Hyperspectral Image Denoising

Fully Connected Guided Image Filtering

Segment Graph Based Image Filtering: Fast Structure-Preserving Smoothing

Deep Networks for Image Super-Resolution with Sparse Prior

Convolutional Color Constancy

Learning Ordinal Relationships for Mid-Level Vision

Thin Structure Estimation with Curvature Regularization

HARF: Hierarchy-Associated Rich Features for Salient Object Detection

Deep Colorization

Image Matting with KL-Divergence Based Sparse Sampling

Intrinsic Decomposition of Image Sequences from Local Temporal Variations

Low-Rank Tensor Approximation with Laplacian Scale Mixture Modeling for Multiframe Image Denoising

Learning Parametric Distributions for Image Super-Resolution: Where Patch Matching Meets Sparse Coding

Improving Image Restoration with Soft-Rounding

See the Difference: Direct Pre-Image Reconstruction and Pose Estimation by Differentiating HOG

An Efficient Statistical Method for Image Noise Level Estimation

Contour Detection and Characterization for Asynchronous Event Sensors

Class-Specific Image Deblurring

High-for-Low and Low-for-High: Efficient Boundary Detection from Deep Object Features and Its Applications to High-Level Vision

Variational Depth Superresolution Using Example-Based Edge Representations

Conditioned Regression Models for Non-blind Single Image Super-Resolution

Video Super-Resolution via Deep Draft-Ensemble Learning

Pan-Sharpening with a Hyper-Laplacian Penalty

Video Restoration Against Yin-Yang Phasing

Rolling Shutter Super-Resolution

Learning Large-Scale Automatic Image Colorization

Compression Artifacts Reduction by a Deep Convolutional Network

Multiple-Hypothesis Affine Region Estimation with Anisotropic LoG Filters

A Self-Paced Multiple-Instance Learning Framework for Co-Saliency Detection

External Patch Prior Guided Internal Clustering for Image Denoising

Self-Calibration of Optical Lenses

Illumination Robust Color Naming via Label Propagation

Unsupervised Cross-Modal Synthesis of Subject-Specific Scans

Learning to Boost Filamentary Structure Segmentation

Weakly-Supervised Structured Output Learning with Flexible and Latent Graphs Using High-Order Loss Functions

Efficient Classifier Training to Minimize False Merges in Electron Microscopy Segmentation

On Statistical Analysis of Neuroimages with Imperfect Registration

Convex Optimization with Abstract Linear Operators

Building Dynamic Cloud Maps from the Ground Up

A Versatile Learning-Based 3D Temporal Tracker: Scalable, Robust, Online

Realtime Edge-Based Visual Odometry for a Monocular Camera

Fill and Transfer: A Simple Physics-Based Approach for Containability Reasoning

On Linear Structure from Motion for Light Field Cameras

3D Object Reconstruction from Hand-Object Interactions

Minimal Solvers for 3D Geometry from Satellite Imagery

An Efficient Minimal Solution for Multi-camera Motion

Learning Shape, Motion and Elastic Models in Force Space

A Versatile Scene Model with Differentiable Visibility Applied to Generative Pose Estimation

Semantic Pose Using Deep Networks Trained on Synthetic RGB-D

Exploiting High Level Scene Cues in Stereo Reconstruction

Point Triangulation through Polyhedron Collapse Using the l∞ Norm

Optimizing the Viewing Graph for Structure-from-Motion

Intrinsic Scene Decomposition from RGB-D Images

3D Hand Pose Estimation Using Randomized Decision Forest with Segmentation Index Points

Accurate Camera Calibration Robust to Defocus Using a Smartphone

High Quality Structure from Small Motion for Rolling Shutter Cameras

Photogeometric Scene Flow for High-Detail Dynamic 3D Reconstruction

Blur-Aware Disparity Estimation from Defocus Stereo Images

Global Structure-from-Motion by Similarity Averaging

Massively Parallel Multiview Stereopsis by Surface Normal Diffusion

Variational PatchMatch MultiView Reconstruction and Refinement

As-Rigid-as-Possible Volumetric Shape-from-Template

General Dynamic Scene Reconstruction from Multiple View Video

The Joint Image Handbook

Direct, Dense, and Deformable: Template-Based Non-rigid 3D Reconstruction from RGB Video

Single Image Pop-Up from Discriminatively Learned Parts

Learning Informative Edge Maps for Indoor Scene Layout Prediction

Multi-view Convolutional Neural Networks for 3D Shape Recognition

Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Images

3D Surface Profilometry Using Phase Shifting of De Bruijn Pattern

A Deep Visual Correspondence Embedding Model for Stereo Matching Costs

Learning Concept Embeddings with Combined Human-Machine Expertise

Deep Multi-patch Aggregation Network for Image Style, Aesthetics, and Quality Estimation

Towards Computational Baby Learning: A Weakly-Supervised Approach for Object Detection

Improving Image Classification with Location Context

HICO: A Benchmark for Recognizing Human-Object Interactions in Images

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

Continuous Pose Estimation with a Spatial Ensemble of Fisher Regressors

Adaptive Hashing for Fast Similarity Search

Single Image 3D without a Single 3D Image

Cross-Domain Image Retrieval with a Dual Attribute-Aware Ranking Network

Attribute-Graph: A Graph Based Approach to Image Ranking

Contextual Action Recognition with R*CNN

What Makes an Object Memorable?

kNN Hashing with Factorized Neighborhood Representation

Multi-View Complementary Hash Tables for Nearest Neighbor Search

Scalable Person Re-identification: A Benchmark

MMSS: Multi-modal Sharable and Specific Feature Learning for RGB-D Object Recognition

Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model

Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks

Cascaded Sparse Spatial Bins for Efficient and Effective Generic Object Detection

Probabilistic Label Relation Graphs with Ising Models

Predicting Good Features for Image Geo-Localization Using Per-Bundle VLAD

Task-Driven Feature Pooling for Image Classification

Cutting Edge: Soft Correspondences in Multimodal Scene Parsing

One Shot Learning via Compositions of Meaningful Patches

FASText: Efficient Unconstrained Scene Text Detector

Multi-scale Recognition with DAG-CNNs

Relaxed Multiple-Instance SVM with Application to Object Discovery

Im2Calories: Towards an Automated Mobile Vision Food Diary

LEWIS: Latent Embeddings for Word Images and Their Semantics

Per-Sample Kernel Adaptation for Visual Recognition and Grouping

Fine-Grained Change Detection of Misaligned Scenes with Varied Illuminations

Aggregating Local Deep Features for Image Retrieval

Learning Deep Object Detectors from 3D Models

Harvesting Discriminative Meta Objects with Deep CNN Features for Scene Classification

Scalable Nonlinear Embeddings for Semantic Category-Based Image Retrieval

Person Re-Identification Ranking Optimisation by Discriminant Context Information Analysis

Unsupervised Generation of a View Point Annotated Car Dataset from Videos

Structured Indoor Modeling

3D Time-Lapse Reconstruction from Internet Photos

Global, Dense Multiscale Reconstruction for a Billion Points

On the Visibility of Point Clouds

Weakly Supervised Graph Based Semantic Segmentation by Learning Communities of Image-Parts

Piecewise Flat Embedding for Image Segmentation

Semantic Image Segmentation via Deep Parsing Network

Human Parsing with Contextualized Convolutional Neural Network

Holistically-Nested Edge Detection

Minimum Barrier Salient Object Detection at 80 FPS

Learning Image Representations Tied to Ego-Motion

Unsupervised Visual Representation Learning by Context Prediction

Webly Supervised Learning of Convolutional Networks

Bilinear CNN Models for Fine-Grained Visual Recognition

Discovering the Spatial Extent of Relative Attributes

Deep Neural Decision Forests

Deep Fried Convnets

Semantic Component Analysis

Low-Rank Matrix Factorization under General Mixture Noise Distributions

Web-Scale Image Clustering Revisited

Learning Discriminative Reconstructions for Unsupervised Outlier Removal

Learning Deconvolution Network for Semantic Segmentation

Conditional Random Fields as Recurrent Neural Networks

The One Triangle Three Parallelograms Sampling Strategy and Its Application in Shape Regression

Boosting Object Proposals: From Pascal to COCO

Secrets of GrabCut and Kernel K-Means

Video Matting via Sparse and Low-Rank Representation

Joint Object and Part Segmentation Using Deep Learned Potentials

Low-Rank Tensor Constrained Multiview Subspace Clustering

BodyPrint: Pose Invariant 3D Shape Matching of Human Bodies

The Middle Child Problem: Revisiting Parametric Min-Cut and Seeds for Object Proposals

Contour Guided Hierarchical Model for Shape Matching

Robust Image Segmentation Using Contour-Guided Color Palettes

Joint Optimization of Segmentation and Color Clustering

BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

Detection and Segmentation of 2D Curved Reflection Symmetric Structures

Unsupervised Tube Extraction Using Transductive Learning and Dense Trajectories

Compositional Hierarchical Representation of Shape Manifolds for Classification of Non-manifold Shapes

Shell PCA: Statistical Shape Modelling in Shell Space

Learning to Combine Mid-Level Cues for Object Proposal Generation

Enhancing Road Maps by Parsing Aerial Images Around the World

Probabilistic Appearance Models for Segmentation and Classification

A Randomized Ensemble Approach to Industrial CT Segmentation

Semi-Supervised Normalized Cuts for Image Segmentation

StereoSnakes: Contour Based Consistent Object Extraction for Stereo Images

Semantic Segmentation of RGBD Images with Mutex Constraints

Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation

Efficient Decomposition of Image and Mesh Graphs by Lifted Multicuts

Parsimonious Labeling

Volumetric Bias in Segmentation and Reconstruction: Secrets and Solutions

Entropy Minimization for Convex Relaxation Approaches

Adaptively Unified Semi-Supervised Dictionary Learning with Active Points

Constrained Convolutional Neural Networks for Weakly Supervised Segmentation

A Multiscale Variable-Grouping Framework for MRF Energy Minimization

Inferring M-Best Diverse Labelings in a Single One

Convolutional Sparse Coding for Image Super-Resolution

A Wavefront Marching Method for Solving the Eikonal Equation on Cartesian Grids

A Projection Free Method for Generalized Eigenvalue Problem with a Nonsmooth Regularizer

Optimizing Expected Intersection-Over-Union with Candidate-Constrained CRFs

Higher-Order Inference for Multi-class Log-Supermodular Models

Depth-Based Hand Pose Estimation: Data, Methods, and Challenges

Adaptive Dither Voting for Robust Spatial Verification

Alternating Co-Quantization for Cross-Modal Hashing

Learning Deep Representation with Large-Scale Attributes

Deep Learning Strong Parts for Pedestrian Detection

Flowing ConvNets for Human Pose Estimation in Videos

Top Rank Supervised Binary Coding for Visual Search

BubbLeNet: Foveated Imaging for Visual Discovery

PQTable: Fast Exact Asymmetric Distance Neighbor Search for Product Quantization Using Hash Tables

Lending A Hand: Detecting Hands and Recognizing Activities in Complex Egocentric Interactions

Fast and Accurate Head Pose Estimation via Random Projection Forests

An MRF-Poselets Model for Detecting Highly Articulated Humans

Beyond Tree Structure Models: A New Occlusion Aware Graphical Model for Human Pose Estimation

Relaxing from Vocabulary: Robust Weakly-Supervised Deep Learning for Vocabulary-Free Image Tagging

Visual Phrases for Exemplar Face Detection

Spatial Semantic Regularisation for Large Scale Object Detection

Human Pose Estimation in Videos

Contour Box: Rejecting Object Proposals without Explicit Closed Contours

Registering Images to Untextured Geometry Using Average Shading Gradients

Robust Nonrigid Registration by Convex Optimization

Robust and Optimal Sum-of-Squares-Based Point-to-Plane Registration of Image Sets and Structured Scenes

MeshStereo: A Global Stereo Model with Mesh Alignment Regularization for View Interpolation

CV-HAZOP: Introducing Test Data Validation for Computer Vision

Structure from Motion Using Structure-Less Resection

Joint Camera Clustering and Surface Segmentation for Large-Scale Multi-view Stereo

Higher-Order CRF Structural Segmentation of 3D Reconstructed Surfaces

Hyperpoints and Fine Vocabularies for Large-Scale Location Recognition

Globally Optimal 2D-3D Registration from Points or Lines without Correspondences

The HCI Stereo Metrics: Geometry-Aware Performance Analysis of Stereo Algorithms

Merging the Unmatchable: Stitching Visually Disconnected SfM Models

3D Fragment Reassembly Using Integrated Template Guidance and Fracture-Region Matching

Procedural Editing of 3D Building Point Clouds

Semantically-Aware Aerial Reconstruction from Multi-modal Data

Guaranteed Outlier Removal for Rotation Search

Peeking Template Matching for Depth Extension

Deformable 3D Fusion: From Partial Dynamic 3D Observations to Complete 4D Models

Non-parametric Structure-Based Calibration of Radially Symmetric Cameras

Exploiting Object Similarity in 3D Reconstruction

You are Here: Mimicking the Human Thinking Process in Reading Floor-Plans

MAP Disparity Estimation Using Hidden Markov Trees

Wide Baseline Stereo Matching with Convex Bounded Distortion Constraints

Interactive Visual Hull Refinement for Specular and Transparent Object Surface Reconstruction

Hierarchical Higher-Order Regression Forest Fields: An Application to 3D Indoor Scene Labelling

Classical Scaling Revisited

Dense Continuous-Time Tracking and Mapping with Rolling Shutter RGB-D Cameras

Dense Image Registration and Deformable Surface Reconstruction in Presence of Occlusions and Minimal Texture

The Likelihood-Ratio Test and Efficient Robust Estimation

Reflection Modeling for Passive Stereo

Detailed Full-Body Reconstructions of Moving People from Monocular RGB-D Sequences

Efficient Solution to the Epipolar Geometry for Radially Distorted Cameras

Learning a Descriptor-Specific 3D Keypoint Detector

Component-Wise Modeling of Articulated Objects

A Collaborative Filtering Approach to Real-Time Hand Pose Estimation

On the Equivalence of Moving Entrance Pupil and Radial Distortion for Camera Calibration

A Linear Generalized Camera Calibration from Three Intersecting Reference Planes

Towards Pointless Structure from Motion: 3D Reconstruction and Camera Parameters from General 3D Curves

Attributed Grammars for Joint Estimation of Human Attributes, Part and Pose

Real-Time Pose Estimation Piggybacked on Object Detection

Understanding and Predicting Image Memorability at a Large Scale

Multiple Granularity Descriptors for Fine-Grained Categorization

Guiding the Long-Short Term Memory Model for Image Caption Generation

Just Noticeable Differences in Visual Attributes

VQA: Visual Question Answering

Localize Me Anywhere, Anytime: A Multi-task Point-Retrieval Approach

Dense Optical Flow Prediction from a Static Image

Unsupervised Domain Adaptation for Zero-Shot Learning

Visual Madlibs: Fill in the Blank Description Generation and Question Answering

Actions and Attributes from Wholes and Parts

DeepBox: Learning Objectness with Convolutional Networks

Active Object Localization with Deep Reinforcement Learning

Scene-Domain Active Part Models for Object Representation

A Unified Multiplicative Framework for Attribute Learning

Contractive Rectifier Networks for Nonlinear Maximum Margin Classification

Augmenting Strong Supervision Using Web Data for Fine-Grained Categorization

Learning Like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images

Learning Common Sense through Visual Abstraction

Domain Generalization for Object Recognition with Multi-task Autoencoders

Square Localization for Efficient and Accurate Object Detection

Box Aggregation for Proposal Decimation: Last Mile of Object Detection

DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers

Semantic Segmentation with Object Clique Potential

Automatic Concept Discovery from Parallel Text and Visual Corpora

Simpler Non-Parametric Methods Provide as Good or Better Results to Multiple-Instance Learning

Monocular Object Instance Segmentation and Depth Ordering with CNNs

Multimodal Convolutional Neural Networks for Matching Image and Sentence

Structural Kernel Learning for Large Scale Multiclass Object Co-detection

Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models

Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture

AttentionNet: Aggregating Weak Directions for Accurate Object Detection

Common Subspace for Model and Similarity: Phrase Learning for Caption Generation from Images

3D-Assisted Feature Synthesis for Novel Views of an Object

Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views

Lost Shopping! Monocular Localization in Large Indoor Spaces

Camera Pose Voting for Large-Scale Image-Based Localization

MANTRA: Minimum Maximum Latent Structural SVM for Image Classification and Ranking

DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving

Active Transfer Learning with Zero-Shot Priors: Reusing Past Datasets for Future Tasks

HD-CNN: Hierarchical Deep Convolutional Neural Networks for Large Scale Visual Recognition

Learning the Structure of Deep Convolutional Networks

FlowNet: Learning Optical Flow with Convolutional Networks

Learning Semi-Supervised Representation Towards a Unified Optimization Framework for Semi-Supervised Learning

Context-Guided Diffusion for Label Propagation on Graphs

Learning to Rank Based on Subsequences

Unsupervised Learning of Visual Representations Using Videos

A Nonparametric Bayesian Approach toward Stacked Convolutional Independent Component Analysis

Robust Principal Component Analysis on Graphs

Projection Bank: From High-Dimensional Data to Medium-Length Binary Codes

Robust Optimization for Deep Regression

Multi-class Multi-annotator Active Learning with Robust Gaussian Process for Visual Recognition

Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation

An Exploration of Parameter Redundancy in Deep Networks with Circulant Projections

Additive Nearest Neighbor Feature Maps

Understanding Deep Features with Computer-Generated Imagery

Interpolation on the Manifold of K Component GMMs

Context-Aware CNNs for Person Head Detection

Mode-Seeking on Hypergraphs for Robust Geometric Model Fitting

Highly-Expressive Spaces of Well-Behaved Transformations: Keeping it Simple

Entropy-Based Latent Structured Output Prediction

Fast Orthogonal Projection Based on Kronecker Product

PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization

Predicting Multiple Structured Visual Interpretations

Look and Think Twice: Capturing Top-Down Visual Attention with Feedback Convolutional Neural Networks

Matrix Backpropagation for Deep Networks with Structured Layers

Introducing Geometry in Active Learning for Image Segmentation

Joint Fine-Tuning in Deep Neural Networks for Facial Expression Recognition

Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression

Discriminative Low-Rank Tracking

SOWP: Spatially Ordered and Weighted Patch Descriptor for Visual Tracking

Live Repetition Counting

Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor

Multi-kernel Correlation Filter for Visual Tracking

Joint Probabilistic Data Association Revisited

Tracking-by-Segmentation with Online Gradient Boosting Decision Tree

Exploring Causal Relationships in Visual Object Tracking

Hierarchical Convolutional Features for Visual Tracking

Robust Non-rigid Motion Tracking and Surface Reconstruction Using L0 Regularization

Online Object Tracking with Proposal Selection

Understanding and Diagnosing Visual Tracking Systems

Integrating Dashcam Views through Inter-Video Mapping

Visual Tracking with Fully Convolutional Networks

Multiple Feature Fusion via Weighted Entropy for Visual Tracking

Pedestrian Travel Time Estimation in Crowded Scenes

Unsupervised Synchrony Discovery in Human Interaction

Efficient Video Segmentation Using Parametric Graph Partitioning

Learning to Track for Spatio-Temporal Action Localization

Unsupervised Object Discovery and Tracking in Video Collections

Car that Knows Before You Do: Anticipating Maneuvers via Learning Temporal Driving Models

Activity Auto-Completion: Predicting Human Activities from Partial Videos

Person Re-Identification with Correspondence Structure Learning

Adaptive Exponential Smoothing for Online Filtering of Pixel Prediction Maps

P-CNN: Pose-Based CNN Features for Action Recognition

Fully Connected Object Proposals for Video Segmentation

Video Segmentation with Just a Few Strokes

Actionness-Assisted Recognition of Actions

COUNT Forest: CO-Voting Uncertain Number of Targets Using Random Forest for Crowd Density Estimation

Multi-cue Structure Preserving MRF for Unconstrained Video Segmentation

Motion Trajectory Segmentation via Minimum Cost Multicuts

Action Localization in Videos through Context Walk

RGB-W: When Vision Meets Wireless

Action Detection by Implicit Intentional Motion Clustering

Simultaneous Foreground Detection and Classification with Hybrid Features

Training a Feedback Loop for Hand Pose Estimation

Opening the Black Box: Hierarchical Sampling Optimization for Estimating Human Hand Pose

Panoptic Studio: A Massively Multiview System for Social Motion Capture

Where to Buy It: Matching Street Clothing Photos in Online Shops

Multi-task Recurrent Neural Network for Immediacy Prediction

Learning Complexity-Aware Cascades for Deep Pedestrian Detection

Polarized 3D: High-Quality Depth Sensing with Polarization Cues

Airborne Three-Dimensional Cloud Tomography

Leave-One-Out Kernel Optimization for Shadow Detection

Removing Rain from a Single Image via Discriminative Sparse Coding

Mutual-Structure for Joint Filtering

Photometric Stereo in a Scattering Medium

Resolving Scale Ambiguity via XSlit Aspect Ratio Analysis

Single-Shot Specular Surface Reconstruction with Gonio-Plenoptic Imaging

TransCut: Transparent Object Segmentation from a Light-Field Image

Depth Recovery from Light Field Using Focal Stack Symmetry

Depth Map Estimation and Colorization of Anaglyph Images Using Local Color Prior and Reverse Intensity Distribution

Learning Data-Driven Reflectance Priors for Intrinsic Image Decomposition

Photometric Stereo with Small Angular Variations

Occlusion-Aware Depth Estimation Using Light-Field Cameras

Oriented Light-Field Windows for Scene Flow

Extended Depth of Field Catadioptric Imaging Using Focal Sweep

Intrinsic Depth: Improving Depth Transfer with Intrinsic Images

Separating Fluorescent and Reflective Components by Using a Single Hyperspectral Image

Frequency-Based Environment Matting by Compressive Sensing

Complementary Sets of Shutter Sequences for Motion Deblurring

Hyperspectral Compressive Sensing Using Manifold-Structured Sparsity Prior

A Gaussian Process Latent Variable Model for BRDF Inference

Active One-Shot Scan for Wide Depth Range Using a Light Field Projector Based on Coded Aperture

Model-Based Tracking at 300Hz Using Raw Time-of-Flight Observations

Hyperspectral Super-Resolution by Coupled Spectral Unmixing

Depth Selective Camera: A Direct, On-Chip, Programmable Technique for Depth Selectivity in Photography

A Groupwise Multilinear Correspondence Optimization for 3D Faces

Selective Encoding for Recognizing Unreliably Localized Faces

Confidence Preserving Machine for Facial Action Unit Detection

Learning Social Relation Traits from Face Images

Robust Heart Rate Measurement from Video Using Select Random Patches

Robust Model-Based 3D Head Pose Estimation

Robust Facial Landmark Detection Under Significant Head Poses and Occlusion

Conditional Convolutional Neural Network for Modality-Aware Face Recognition

From Facial Parts Responses to Face Detection: A Deep Learning Approach

Efficient PSD Constrained Asymmetric Metric Learning for Person Re-Identification

Pose-Invariant 3D Face Alignment

From Emotions to Action Units with Hidden and Semi-Hidden-Task Learning

Automated Facial Trait Judgment and Election Outcome Prediction: Social Dimensions of Face

Simultaneous Local Binary Feature Learning and Encoding for Face Recognition

Deep Learning Face Attributes in the Wild

Multi-Task Learning with Low Rank Attribute Embedding for Person Re-Identification

Regressing a 3D Face Shape from a Single Image

Rendering of Eyes for Eye-Shape Registration and Gaze Estimation

Multi-Scale Learning for Low-Resolution Person Re-Identification

Learning to Transfer: Transferring Latent Task Structures and Its Application to Person-Specific Facial Action Unit Detection

Pairwise Conditional Random Forests for Facial Expression Recognition

Multi-conditional Latent Variable Model for Joint Facial Action Unit Detection

Leveraging Datasets with Varying Annotations for Face Alignment via Deep Regression Network

A Spatio-Temporal Appearance Representation for Viceo-Based Pedestrian Re-Identification

Two Birds, One Stone: Jointly Learning Binary Code for Large-Scale Face Image Retrieval and Attributes Prediction

An Accurate Iris Segmentation Framework Under Relaxed Imaging Constraints Using Total Variation Model

Discriminative Pose-Free Descriptors for Face and Object Matching

Bi-Shifting Auto-Encoder for Unsupervised Domain Adaptation

Regressive Tree Structured Model for Facial Landmark Localization

Person Recognition in Personal Photo Collections

Robust Statistical Face Frontalization

PIEFA: Personalized Incremental and Ensemble Face Alignment

Understanding Everyday Hands in Action from RGB-D Images

Example-Based Modeling of Facial Texture from Deficient Data

Learning to Predict Saliency on Face Images

Group Membership Prediction

Extraction of Virtual Baselines from Distorted Document Images Using Curvilinear Projection

Robust RGB-D Odometry Using Point and Line Features

Learning a Discriminative Model for the Perception of Realism in Composite Images

What Makes Tom Hanks Look Like Tom Hanks

Wide-Area Image Geolocalization with Aerial Reference Imagery

Personalized Age Progression with Aging Dictionary

FaceDirector: Continuous Control of Facial Performance in Video

Synthesizing Illumination Mosaics from Internet Photo-Collections

Hot or Not: Exploring Correlations between Appearance and Temperature

SPM-BP: Sped-Up PatchMatch Belief Propagation for Continuous MRFs

Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation

Dense Semantic Correspondence Where Every Pixel is a Classifier

Multi-image Matching via Fast Alternating Minimization

Differential Recurrent Neural Networks for Action Recognition

Similarity Gaussian Process Latent Variable Model for Multi-modal Data Analysis

Learning Ensembles of Potential Functions for Structured Prediction with Latent Variables

Simultaneous Deep Transfer Across Domains and Tasks

Low Dimensional Explicit Feature Maps

Unsupervised Learning of Spatiotemporally Coherent Metrics

Multi-label Cross-Modal Retrieval

Improving Ferns Ensembles by Sparsifying and Quantising Posterior Probabilities

Beyond Gauss: Image-Set Matching on the Riemannian Manifold of PDFs

Unsupervised Domain Adaptation with Imbalanced Cross-Domain Data

Secrets of Matrix Factorization: Approximations, Numerics, Manifold Optimization and Random Restarts

Geometry-Aware Deep Transform

Learning Binary Codes for Maximum Inner Product Search

ML-MG: Multi-label Learning with Missing Labels Using a Mixed Graph

Zero-Shot Learning via Semantic Similarity Embedding

Bayesian Model Adaptation for Crowd Counts

An NMF Perspective on Binary Hashing

Multi-view Domain Generalization for Visual Recognition

Infinite Feature Selection

Semi-Supervised Zero-Shot Classification with Label Representation Learning

A Supervised Low-Rank Method for Learning Invariant Subspaces

Recursive Fréchet Mean Computation on the Grassmannian and Its Applications to Computer Vision

Multi-view Subspace Clustering

Predicting Deep Zero-Shot Convolutional Neural Networks Using Textual Descriptions

Structured Feature Selection

Conditional High-Order Boltzmann Machine: A Supervised Learning Model for Relation Learning

Learning Image and User Features for Recommendation in Social Networks

Dual-Feature Warping-Based Motion Model Estimation

An Adaptive Data Representation for Robust Point-Set Registration and Merging

Local Subspace Collaborative Tracking

Learning Spatially Regularized Correlation Filters for Visual Tracking

SpeDo: 6 DOF Ego-Motion Sensor Using Speckle Defocus Imaging

Unsupervised Trajectory Clustering via Adaptive Multi-kernel-Based Shrinkage

TRIC-track: Tracking by Regression with Incrementally Learned Cascades

Recurrent Network Models for Human Dynamics

Contour Flow: Middle-Level Motion Estimation by Combining Motion Segmentation and Contour Alignment

FollowMe: Efficient Online Min-Cost Flow Tracking with Bounded Memory and Computation

Learning to Divide and Conquer for Online Multi-target Tracking

Minimizing Human Effort in Interactive Tracking by Incremental Learning of Model Parameters

A Novel Representation of Parts for Accurate 3D Object Detection and Tracking in Monocular Images

Linearization to Nonlinear Learning for Visual Tracking

Self-Occlusions and Disocclusions in Causal Video Object Segmentation

Large Displacement 3D Scene Flow with Occlusion Reasoning

Co-Interest Person Detection from Multiple Wearable Camera Videos

Sparse Dynamic 3D Reconstruction from Unsynchronized Videos

Category-Blind Human Action Recognition: A Practical Recognition System

Temporal Subspace Clustering for Human Motion Segmentation

Weakly-Supervised Alignment of Video with Text

Learning Temporal Embeddings for Complex Video Analysis

Unsupervised Semantic Parsing of Video Collections

Learning Spatiotemporal Features with 3D Convolutional Networks

Temporal Perception and Prediction in Ego-Centric Video

Describing Videos by Exploiting Temporal Structure

Person Re-Identification with Discriminatively Trained Viewpoint Invariant Dictionaries

Storyline Representation of Egocentric Videos with an Applications to Story-Based Search

Sequence to Sequence -- Video to Text

Context Aware Active Learning of Activity Recognition Models

Action Recognition by Hierarchical Mid-Level Action Elements

Selecting Relevant Web Trained Concepts for Automated Event Retrieval

Beyond Covariance: Feature Representation with Nonlinear Kernel Matrices

Multiresolution Hierarchy Co-Clustering for Semantic Segmentation in Sequences with Small Variations

Objects2action: Classifying and Localizing Actions without Any Video Example

Human Action Recognition Using Factorized Spatio-Temporal Convolutional Networks

Bayesian Non-parametric Inference for Manifold Based MoCap Representation

Semantic Video Entity Linking Based on Visual Content and Metadata

Love Thy Neighbors: Image Annotation by Exploiting Image Metadata

Unsupervised Extraction of Video Highlights via Robust Recurrent Auto-Encoders

Learning Visual Clothing Style with Heterogeneous Dyadic Co-Occurrences

Text Flow: A Unified Text Detection System in Natural Scene Images

Uncovering Interactions and Interactors: Joint Estimation of Head, Body Orientation and F-Formations from Surveillance Videos

Generating Notifications for Missing Actions: Don't Forget to Turn the Lights Off!

Partial Person Re-Identification

Shape Interaction Matrix Revisited and Robustified: Efficient Subspace Clustering with Corrupted and Incomplete Data

Multiple Hypothesis Tracking Revisited

Learning to Track: Online Multi-object Tracking by Decision Making

Publisher's Information

2013 IEEE International Conference on Computer Vision

2011 International Conference on Computer Vision

2009 IEEE 12th International Conference on Computer Vision

2007 IEEE 11th International Conference on Computer Vision

Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1

Proceedings Ninth IEEE International Conference on Computer Vision

Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001

Proceedings of the Seventh IEEE International Conference on Computer Vision

Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271)

Proceedings of IEEE International Conference on Computer Vision

1993 (4th) International Conference on Computer Vision

[1990] Proceedings Third International Conference on Computer Vision

[1988 Proceedings] Second International Conference on Computer Vision

Unsupervised Semantic Parsing of Video Collections

Content Provider	IEEE Xplore Digital Library
Author	Sener, Ozan Zamir, Amir R. Savarese, Silvio Saxena, Ashutosh
Copyright Year	2015
Abstract	Human communication typically has an underlying structure. This is reflected in the fact that in many user generated videos, a starting point, ending, and certain objective steps between these two can be identified. In this paper, we propose a method for parsing a video into such semantic steps in an unsupervised way. The proposed method is capable of providing a semantic "storyline" of the video composed of its objective steps. We accomplish this utilizing both visual and language cues in a joint generative model. The proposed method can also provide a textual description for each of identified semantic steps and video segments. We evaluate this method on a large number of complex YouTube videos and show results of unprecedented quality for this new and impactful problem.
Starting Page	4480
Ending Page	4488
File Size	15934471
Page Count	9
File Format	PDF
ISSN	23807504
e-ISBN	9781467383912
DOI	10.1109/ICCV.2015.509
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2015-12-07
Publisher Place	Chile
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Visualization Proposals Semantics YouTube Atomic measurements Conferences Computer vision
Content Type	Text
Resource Type	Article

Central Library (ISO-9001:2015 Certified)
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal, India | PIN - 721302

See location in the Map
03222 282435
Mail: support@ndl.gov.in

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in