Scenery of Shanghai

Accepted Papers

Full Papers

1   A Privacy-Preserving Bipartite Graph Matching Framework for Multimedia Analysis and Retrieval
15  Image Classification and Retrieval are ONE
18  Describing Images with Hierarchical Concepts and Object Class Localization
23  Supervised Multi-scale Locality Sensitive Hashing
26  Nonnegative Sparse Neighborhood Propagation
29  Fast Democratic Aggregation and Query Fusion for Image Search
33  Bundling Centre For Landmark Image Discovery
49  Fine-Grained Image Categorization by Localizing Tiny Object Parts from Unannotated Images
51  DeepIndex for Accurate and Efficient Image Retrieval
53  A Novel Visual-Region-Descriptor-based Approach to Sketch-based Image Retrieval
58  Hierarchical Encoding of Binary Descriptors for Image Matching
63  Location Prediction of Social Images via Generative Model
69  Scalable Multimodal Search with Distributed Indexing by Sparse Hashing
71  Facial Action Unit Classification with Hidden Knowledge under Incomplete Annotation
73  MInsight in Image Collections by Multimedia Pivot Tables
74  Social Event Mining in Large Photo Collections
82  Distribution Regularized Nonnegative Matrix Factorization for Transfer Visual Feature Learning
83  Robust and Discriminative Concept Factorization for Image Representation
94  Heterogeneous Semantic Level Features Fusion for Action Recognition
101 Social Friend Recommendation Based on Network Correlation and Feature Co-Clustering
111 Kernelizing Spatially Consistent Visual Matches for Fine-Grained Classification
118 Extracting 3D Trajectories of Objects from 2D Videos using Particle Filter
123 Space-time histograms and their application to person re-identification in TV shows
125 Improving Diversity in Image Search via Supervised Relevance Scoring
126 Unsupervised Distance Learning by Rank Correlation Measures for Image Retrieval
127 Effective, Efficient, and Scalable Unsupervised Distance Learning in Image Retrieval Tasks
130 Exploring Pooling Strategies based on Idiosyncrasies of Spatio-Temporal Interest Points
131 Temporal-Order Preserved Dynamic Quantization for Human Action Recognition from Multimodal Sensor Streams
133 Image-Text Cross-Modal Retrieval via Modality-Specific Feature Learning
136 Unified YouTube Video Recommendation via Cross-network Collaboration
138 Twin Feature and Similarity Maximal Matching for Image Retrieval
158 Location-Based Parallel Tag Completion for Geo-tagged Social Photo Retrieval
161 Exploiting Spatial Relationship between Scenes for Hierarchical Video Geotagging
173 Fusing Pointwise and Pairwise Labels for Supporting Personalized Image Retrieval
178 USING VIEWER’S FACIAL EXPRESSION AND HEART RATE FOR SPORTS VIDEO HIGHLIGHTS DETECTION
189 A Deep Neural Network for Modeling Music
201 Robust Seed Detection and Growing with Deep Convolutional Features for Scene Text Detection
202 High-Dimensional Indexing by Sparse Approximation
213 To Keep or not to Keep: An Expectation-oriented Photo Selection Method for Personal Photo Collections
214 Swap Retrieval: Retrieving images of cats when the query shows a dog
222 Diffusion-on-Manifold Aggregation of Local Features for Shape-based 3D Model Retrieval
224 Graph Learning on K Nearest Neighbours for Automatic Image Annotation
227 Scalable organization of collections of motion capture data via quantitative and qualitative analysis
240 Content-Based Video Search over 1 Million Videos with 1 Core in 1 Second
241 Bridging the Ultimate Semantic Gap: A Semantic Search Engine for Internet Videos
246 Encoding Concept Prototypes for Video Event Detection and Summarization
247 Discovering Semantic Vocabularies for Cross-Media Retrieval
248 Bag-of-Fragments: Selecting and encoding video fragments for event detection and recounting
249 Latent Factors of Visual Popularity Prediction
251 Building A Deep Learning System for Video Classification: An In-depth Study           
253 Visual Event Summarization on Social Media using Topic Modelling and Graph-based Ranking Algorithms

Short Papers

3   Content-based Image Retrieval Using Rotation-invariant Histograms of Oriented Gradients
4   Augmented Feature Fusion for Image Retrieval System
30  Parallel AP Clustering and Re-ranking for Automatic Image-Text Alignment and Large-Scale Web Image Search
37  Accio: A Data Set for Face Track Retrieval in Movies Across Age
38  A Two-step Approach to Cross-modal Hashing
39  Cross-Scenario Eyeglasses Retrieval via EGYPT Model
52  People News Search via Name-Face Association Analysis
57  Discovering the Latent Similarities of the KNN Graph by Metric Transformation
59  Formation period matters: Towards socially consistent group detection via dense subgraph seeking
60  Memory vectors for particular object retrieval with multiple queries
62  Semantic-aware Hashing for Social Image Retrieval
67  Zero-shot Image Categorization via Image Correlation Exploration
76  Deep Bottleneck Feature for Image Classification
78  Maximally Visual-Homogeneous Region Detector for Large Scale Image Retrieval
87  Rapid Clothing Retrieval via Deep Learning of Binary Codes and Hierarchical Search
93  Information gain study for visual vocabulary construction
97  Discriminative Latent Feature Space Learning for Cross-Modal Retrieval
103 Image Retrieval by User-oriented Ranking
105 Spatial Constraint for Image Location Estimation
115 Shape-based Object Matching Using Point Context
117 Large Scale Image Annotation via Deep Representation Learning and Tag Embedding Learning
124 Probabilistic Matrix Factorization With Semantic And Visual Neighborhoods For Image Tag Completion
129 Exploiting multiple web resources towards collecting positive training samples for visual concept learning
134 CRMActive : An Active Learning Based Approach For Effective Video Annotation And Retrieval
135 Personalized Egocentric Video Summarization for Cultural Experience
140 EMIF: Towards a Scalable and Effective Indexing Framework for Large Scale Music Retrieval
142 Specific Person Retrieval via Incomplete Text Description
146 Combining generic and specific information for cross-modal retrieval
148 3D Sketch-Based 3D Model Retrieval
151 Boosting Prediction of Geo-location for Web Images Through Integrating Multiple Knowledge Sources
162 Expression Recognition from Visible Images with the Help of Thermal Images
164 Multi-facet Learning using Deep Convolutional Neural Network for Person-Related Categories in Photos
176 Sketch-based Image Retrieval via Shape Words
180 Multiple Aesthetic Attribute Assessment by Exploiting Relations Among Aesthetic Attributes
181 Emotion recognition from users' eeg signals using hierarchical bayesian model with privileged information
184 Multi-Label Active Learning with Chi-Square Statistics for Image Classification
188 Multiple Measurements and Joint Dimensionality Reduction for Large Scale Image Search with Short Vectors
193 Exploring EEG for Object Detection and Retrieval
221 Kernel Local Descriptors with Implicit Rotation Matching
229 Semantic Concept Annotation for User Generated Videos Using Soundtracks
230 Automatic Image Annotation using Deep Learning Representations
231 “My Day in Review” Visually Summarising Noisy Lifelog Data
232 Audio-Based Multimedia Event Detection with DNNs and Sparse Sampling
236 Learning Binary Codes for Hashing via Feature Decomposition
243 Multimodal Learning with Deep Boltzmann Machine for Emotion Prediction in User Generated Videos
244 Improving Automatic Name-Face Association using Celebrity Images on the Web

Demos

100 Music Positioning and Annotation For Television Videos
149 KinectSBR: A Kinect-Assisted 3D Sketch-Based 3D Model Retrieval System
153 An Improved System For Real-Time Scene Text Recognition
198 DigInPix: visual named-entities identification in images and videos
256 Mobile Media Thumbnailing
257 IdeaPanel: A Large Scale Interactive Sketch-based Image Search System
258 A Sparse Ensemble Learning System For Efficient Semantic Indexing
260 A Multi-Sensory Gesture-Based Occupational Therapy Environment for Controlling Home Appliances
261 Incremental Multimodal Query Construction for Video Search

Special Session Papers

96  End-to-End Photo-Sketch Generation via Fully Convolutional Representation Learning
128 Attribute Guided Dictionary Learning
166 Teaching Video Analytics Based on Human Behavior Mining
179 Online Multi-modal Co-indexing and Retrieval for Weakly Supervised Web Image Collections
217 Weakly Supervised Random Forest for Multi-Label Image Clustering and Segmentation
223 Harvesting Multiple Sources for User Profile Learning: a Big Data Study
254 Multi-view Face Detection Using Deep Convolutional Neural Networks          

Sponsors and Partners