查正军
教授
最新
- A Closer Look at the Reflection Formulation in Single Image Reflection Removal
- Adaptive Texture and Spectrum Clue Mining for Generalizable Face Forgery Detection
- Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation
- Cross-Modal Semantic Alignment Learning for Text-Based Person Search
- DDOD: Dive Deeper into the Disentanglement of Object Detector
- Learning Discriminative Noise Guidance for Image Forgery Detection and Localization
- Neuromorphic Event Signal-Driven Network for Video De-raining
- On Exploring Multiplicity of Primitives and Attributes for Texture Recognition in the Wild
- Prototype-Augmented Self-Supervised Generative Network for Generalized Zero-Shot Learning
- Unleashing Knowledge Potential of Source Hypothesis for Source-Free Domain Adaptation
- Adaptive Frequency Filters As Efficient Global Token Mixers
- Alleviating Spatial Misalignment and Motion Interference for UAV-based Video Recognition
- Category-Stitch Learning for Union Domain Generalization
- Continual Image Deraining With Hypergraph Convolutional Networks
- Decoupling-and-Aggregating for Image Exposure Correction
- Deep Texton-Coherence Network for Camouflaged Object Detection
- Domain Generalization Via Encoding and Resampling in a Unified Latent Space
- DreamWaltz: Make a Scene with Complex 3D Animatable Avatars
- ECENet: Explainable and Context-Enhanced Network for Muti-modal Fact verification
- Edge-aware Regional Message Passing Controller for Image Forgery Localization
- Entity-Enhanced Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding
- Event-Guided Person Re-Identification via Sparse-Dense Complementary Learning
- Exploring Tuning Characteristics of Ventral Stream's Neurons for Few-Shot Image Classification
- Fusion-Based Low-Light Image Enhancement
- Generalized UAV Object Detection via Frequency Domain Disentanglement
- Grounding 3D Object Affordance from 2D Interactions in Images
- Hierarchical Semantic Enhancement Network for Multimodal Fake News Detection
- Image De-Raining Transformer
- Learning Cross-Representation Affinity Consistency for Sparsely Supervised Biomedical Instance Segmentation
- Learning Semantics-Grounded Vocabulary Representation for Video-Text Retrieval
- Learning to Dub Movies via Hierarchical Prosody Models
- Learning Video-Text Aligned Representations for Video Captioning
- Location-Free Camouflage Generation Network
- MaTCR: Modality-Aligned Thought Chain Reasoning for Multimodal Task-Oriented Dialogue Generation
- Neural Dependencies Emerging from Learning Massive Categories
- NTIRE 2023 Challenge on Efficient Super-Resolution: Methods and Results
- Random Shuffle Transformer for Image Restoration
- Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language Models
- Self-Organizing Pathway Expansion for Non-Exemplar Class-Incremental Learning
- Self-supervised Cross-view Representation Reconstruction for Change Captioning
- Semantic and Relation Modulation for Audio-Visual Event Localization
- Spatial-Aware Token for Weakly Supervised Object Localization
- Streaming Video Model
- Synergy between Semantic Segmentation and Image Denoising via Alternate Boosting
- Text-Driven Generative Domain Adaptation with Spectral Consistency Regularization
- A Model-Driven Deep Unfolding Method for JPEG Artifacts Removal
- AS-Net: Class-Aware Assistance and Suppression Network for Few-Shot Learning
- Automatic Relation-aware Graph Network Proliferation
- Bijective Mapping Network for Shadow Removal
- Context-Aware Visual Policy Network for Fine-Grained Image Captioning
- Cross-modal Semantic Alignment Pre-training for Vision-and-Language Navigation
- Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-identification
- Degradation-agnostic Correspondence from Resolution-asymmetric Stereo
- E-Commerce Storytelling Recommendation Using Attentional Domain-Transfer Network and Adversarial Pre-Training
- Efficient Model-Driven Network for Shadow Removal
- EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching
- Enhancement by Your Aesthetic: An Intelligible Unsupervised Personalized Enhancer for Low-Light Images
- Event-driven Video Deblurring via Spatio-Temporal Relation-Aware Network
- Exploring Figure-Ground Assignment Mechanism in Perceptual Organization
- Exploring Fourier Prior for Single Image Rain Removal
- Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment
- I(^mbox2)Transformer: Intra- and Inter-Relation Embedding Transformer for TV Show Captioning
- JPEG Artifacts Removal via Contrastive Representation Learning
- JPEG Compression-aware Image Forgery Localization
- Learning Degradation-Invariant Representation for Robust Real-World Person Re-Identification
- Learning Dual Convolutional Dictionaries for Image De-raining
- Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation
- Lightweight Wavelet-Based Network for JPEG Artifacts Removal
- Long Short-Term Relation Transformer With Global Gating for Video Captioning
- Long-Range Feature Dependencies Capturing for Low-Resolution Image Classification
- Modality-Adaptive Mixup and Invariant Decomposition for RGB-Infrared Person Re-identification
- Online Residual Quantization Via Streaming Data Correlation Preserving
- Principled Knowledge Extrapolation with GANs
- Progressive Pan-Sharpening via Cross-Scale Collaboration Networks
- ProgressiveMotionSeg: Mutually Reinforced Framework for Event-Based Motion Segmentation
- Rank Diminishing in Deep Neural Networks
- S2N: Suppression-Strengthen Network for Event-Based Recognition Under Variant Illuminations
- Single Image Shadow Detection via Complementary Mechanism
- Stochastic Window Transformer for Image Restoration
- Unsupervised Coherent Video Cartoonization with Perceptual Motion Consistency
- Weakly Supervised High-Fidelity Clothing Model Generation
- A Decomposition-based Network for Non-uniform Illuminated Retinal Image Enhancement
- A Mutually Attentive Co-Training Framework for Semi-Supervised Recognition
- Attack-Guided Perceptual Data Generation for Real-world Re-Identification
- Cluster and Scatter: A Multi-grained Active Semi-supervised Learning Framework for Scalable Person Re-identification
- Cross-Patch Graph Convolutional Network for Image Denoising
- Deep Coattention-Based Comparator for Relative Representation Learning in Person Re-Identification
- Disentangle Your Dense Object Detector
- Domain-Oriented Semantic Embedding for Zero-Shot Learning
- End-to-end Boundary Exploration for Weakly-supervised Semantic Segmentation
- Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification
- Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers
- Group-aware Label Transfer for Domain Adaptive Person Re-identification
- Human activity recognition by manifold regularization based dynamic graph convolutional networks
- Image De-Raining via Continual Learning
- Improving De-raining Generalization via Neural Reorganization
- Language-Conditioned Region Proposal and Retrieval Network for Referring Expression Comprehension
- Laplacian Pyramid Neural Network for Dense Continuous-Value Regression for Complex Scenes
- Learning and Fusing Multiple User Interest Representations for Micro-Video and Movie Recommendations
- Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessment
- Learning Dual Priors for JPEG Compression Artifacts Removal
- Leveraging Deep Statistics for Underwater Image Enhancement
- Light Field Super-Resolution With Zero-Shot Learning
- Local-binarized very deep residual network for visual categorization
- Low-Rank Subspaces in GANs
- Multifocal Attention-Based Cross-Scale Network for Image De-raining
- One-Shot Texture Retrieval Using Global Grouping Metric
- Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification
- Rain Streak Removal via Dual Graph Convolutional Network
- Rethinking Graph Neural Architecture Search From Message-Passing
- Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning
- Self-Supervised Visual Representations Learning by Contrastive Mask Prediction
- SLiKER: Sparse loss induced kernel ensemble regression
- Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos
- Structure-Guided Deep Video Inpainting
- Structured Multi-Level Interaction Network for Video Moment Localization via Language Query
- Successive Graph Convolutional Network for Image De-raining
- Training Spiking Neural Networks with Accumulated Spiking Flow
- Uncertainty Principles of Encoding GANs
- Understanding Noise Injection in GANs
- Weakly Supervised Neuron Reconstruction From Optical Microscopy Images With Morphological Priors
- A generalized least-squares approach regularized with graph embedding for dimensionality reduction
- A Structured Graph Attention Network for Vehicle Re-Identification
- Adversarial Attribute-Text Embedding for Person Search With Natural Language Query
- ASTA-Net: Adaptive Spatio-Temporal Attention Network for Person Re-Identification in Videos
- CircleNet for Hip Landmark Detection
- Co-Saliency Spatio-Temporal Interaction Network for Person Re-Identification in Videos
- ContourNet: Taking a Further Step Toward Accurate Arbitrary-Shaped Scene Text Detection
- Deep Degradation Prior for Low-Quality Image Classification
- Deep Structure-Revealed Network for Texture Recognition
- DeepFacePencil: Creating Face Images from Freehand Sketches
- Domain-Aware Visual Bias Eliminating for Generalized Zero-Shot Learning
- Dual Context-Aware Refinement Network for Person Search
- Dual Path Interaction Network for Video Moment Localization
- Filtration and Distillation: Enhancing Region Attention for Fine-Grained Visual Categorization
- Fine-grained Feature Alignment with Part Perspective Transformation for Vehicle ReID
- Frank-Wolfe Network: An Interpretable Deep Structure for Non-Sparse Coding
- Hierarchical Granularity Transfer Learning
- Hierarchical Gumbel Attention Network for Text-based Person Search
- Iterative Context-Aware Graph Inference for Visual Dialog
- Joint Sketch-Attribute Learning for Fine-Grained Face Synthesis
- JPEG Artifacts Removal via Compression Quality Ranker-Guided Networks
- Learning Rich Part Hierarchies With Progressive Attention Networks for Fine-Grained Image Recognition
- Learning Semantic-aware Normalization for Generative Adversarial Networks
- Learning to Discretely Compose Reasoning Module Networks for Video Captioning
- March on Data Imperfections: Domain Division and Domain Generalization for Semantic Segmentation
- Memory-Augmented Relation Network for Few-Shot Learning
- Multi-Objective Matrix Normalization for Fine-Grained Visual Recognition
- Multi-Scale Group Transformer for Long Sequence Modeling in Speech Separation
- Multi-Scale Spatial-Temporal Integration Convolutional Tube for Human Action Recognition
- Neuronal Population Reconstruction From Ultra-Scale Optical Microscopy Images via Progressive Learning
- Nighttime Dehazing with a Synthetic Benchmark
- Object Relational Graph With Teacher-Recommended Learning for Video Captioning
- Parsing-Based View-Aware Embedding Network for Vehicle Re-Identification
- Posterior-Guided Neural Architecture Search
- Real-World Image Denoising with Deep Boosting
- Real-World Person Re-Identification via Degradation Invariance Learning
- Robust Deep Co-Saliency Detection With Group Semantic and Pyramid Attention
- Self-Supervised Domain-Aware Generative Network for Generalized Zero-Shot Learning
- Semantic Image Analogy with a Conditional Single-Image GAN
- Space-Time Video Super-Resolution Using Temporal Profiles
- Spatiotemporal Fusion in 3D CNNs: A Probabilistic View
- State-Relabeling Adversarial Active Learning
- Structural Semantic Adversarial Active Learning for Image Captioning
- Towards Neuron Segmentation from Macaque Brain Images: A Weakly Supervised Approach
- Towards Semantically Scalable Image Coding using Semantic Map
- Transferrable Referring Expression Grounding with Concept Transfer and Context Inheritance
- Visual Object Tracking via Guessing and Matching
- A generalized multi-dictionary least squares framework regularized with multi-graph embeddings
- A Two-Stream Mutual Attention Network for Semi-Supervised Biomedical Segmentation with Noisy Labels
- Abstract Reasoning with Distracting Features
- Accurate Segmentation of Synaptic Cleft with Contour Growing Concatenated with a Convnet
- Adaptive Alignment Network for Person Re-identification
- Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding
- Adaptive Transfer Network for Cross-Domain Person Re-Identification
- BERT4SessRec: Content-Based Video Relevance Prediction with Bidirectional Encoder Representations from Transformer
- Camera Lens Super-Resolution
- Context-Reinforced Semantic Segmentation
- Convolutional Attention Networks for Scene Text Recognition
- Cross-Fiber Spatial-Temporal Co-enhanced Networks for Video Action Recognition
- Cross-Modality Feature Learning via Convolutional Autoencoder
- DADNet: Dilated-Attention-Deformable ConvNet for Crowd Counting
- Deep Adversarial Graph Attention Convolution Network for Text-Based Person Search
- Deep Multiple-Attribute-Perceived Network for Real-World Texture Recognition
- Dense 3D-Convolutional Neural Network for Person Re-Identification in Videos
- Densely Supervised Hierarchical Policy-Value Network for Image Paragraph Generation
- Domain-Specific Embedding Network for Zero-Shot Recognition
- Dynamically building diversified classifier pruning ensembles via canonical correlation analysis
- Exploring the Task Cooperation in Multi-goal Visual Navigation
- Extract Bone Parts Without Human Prior: End-to-end Convolutional Neural Network for Pediatric Bone Age Assessment
- Fast and Accurate Electron Microscopy Image Registration with 3D Convolution
- Ground-Aware Point Cloud Semantic Segmentation for Autonomous Driving
- Hierarchical Global-Local Temporal Modeling for Video Captioning
- Hybrid Image Enhancement With Progressive Laplacian Enhancing Unit
- Illumination-Invariant Person Re-Identification
- Instance Segmentation from Volumetric Biomedical Images Without Voxel-Wise Labeling
- JPEG Artifacts Reduction via Deep Convolutional Sparse Coding
- Knowing User Better: Jointly Predicting Click-Through and Playtime for Micro-Video
- Knowledge-guided Pairwise Reconstruction Network for Weakly Supervised Referring Expression Grounding
- Learning Compact Appearance Representation for Video-Based Person Re-Identification
- Learning Deep Bilinear Transformation for Fine-grained Image Representation
- Learning to Assemble Neural Module Tree Networks for Visual Grounding
- LinesToFacePhoto: Face Photo Generation From Lines With Conditional Self-Attention Generative Adversarial Networks
- Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-Grained Image Recognition
- Making History Matter: History-Advantage Sequence Training for Visual Dialog
- Manifold Alignment via Global and Local Structures Preserving PCA Framework
- MLTS: A Multi-Language Scene Text Spotter
- Mutually Reinforced Spatio-Temporal Convolutional Tube for Human Action Recognition
- Near-Duplicate Video Retrieval Through Toeplitz Kernel Partial Least Squares
- Neural Network-Based Arithmetic Coding for Inter Prediction Information in HEVC
- One-Shot Texture Retrieval with Global Context Metric
- Progressive Learning for Neuronal Population Reconstruction from Optical Microscopy Images
- Progressive Retinex: Mutually Reinforced Illumination-Noise Perception Network for Low-Light Image Enhancement
- Question-Aware Tube-Switch Network for Video Question Answering
- Robust Deep Co-Saliency Detection with Group Semantic
- Semantic-Embedding and Shape-Aware U-Net for Ultrasound Eyeball Segmentation
- Spatiotemporal-Textual Co-Attention Network for Video Question Answering
- Structure-Aware Residual Pyramid Network for Monocular Depth Estimation
- 3D Cnn-Based Soma Segmentation from Brain Images at Single-Neuron Resolution
- A CNN-Based In-Loop Filter with CU Classification for HEVC
- A Fast Uyghur Text Detector for Complex Background Images
- A Feature-Adaptive Semi-Supervised Framework for Co-saliency Detection
- Attention and Language Ensemble for Scene Text Recognition with Convolutional Sequence Modeling
- CA(_mbox3)Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification
- CCLBR: Congestion Control-Based Load Balanced Routing in Unstructured P2P Systems
- CCNet: Cluster-Coordinated Net for Learning Multi-agent Communication Protocols with Reinforcement Learning
- Co-occurrent Structural Edge Detection for Color-Guided Depth Map Super-Resolution
- Collaborative Detection and Caption Network
- Connectionist Temporal Fusion for Sign Language Translation
- Content-Based Video Relevance Prediction with Second-Order Relevance and Attention Modeling
- Context-Aware Visual Policy Network for Sequence-Level Image Captioning
- Deep Residual Attention Network for Spectral Image Super-Resolution
- LA-Net: Layout-Aware Dense Network for Monocular Depth Estimation
- MiCT: Mixed 3D/2D Convolutional Tube for Human Action Recognition
- Object Trajectory Proposal via Hierarchical Volume Grouping
- Particle Swarm Programming-Based Interactive Content-Based Image Retrieval
- PIRM2018 Challenge on Spectral Image Super-Resolution: Methods and Results
- Session details: Vision-2 (Object & Scene Understanding)
- Session details: Vision-3 (Applications in Multimedia)
- Temporal Hierarchical Attention at Category- and Item-Level for Micro-Video Click-Through Prediction
- Temporal-Contextual Attention Network for Video-Based Person Re-identification
- Towards Human-Level License Plate Recognition
- Adaptive Pooling in Multi-instance Learning for Web Video Annotation
- Diversity-induced weighted classifier ensemble learning
- Guest Editorial: Knowledge-Based Multimedia Computing
- Improving triplet-wise training of convolutional neural network for vehicle re-identification
- Progressive tone mapping of brain images at single-neuron resolution
- A robust vision inspection system for detecting surface defects of film capacitors
- A Unified Scheme for Super-Resolution and Depth Estimation From Asymmetric Stereoscopic Video
- Action recognition with novel high-level pose features
- Building Locally Discriminative Classifier Ensemble Through Classifier Fusion Among Nearest Neighbors
- Collaborative Q-Learning Based Routing Control in Unstructured P2P Networks
- Comparative Deep Learning of Hybrid Representations for Image Recommendations
- Guest Editorial: Large-Scale Multimedia Content Analysis on Social Media
- Linear Distance Preserving Pseudo-Supervised and Unsupervised Hashing
- Multi-Scale Triplet CNN for Person Re-Identification
- p-Laplacian Regularized Sparse Coding for Human Activity Recognition
- Social media analytics and learning
- An Attribute-Assisted Reranking Model for Web Image Search
- Corrections to \"Exploiting Web Images for Semantic Video Indexing Via Robust Sample-Specific Loss\"
- Depth map super-resolution using stereo-vision-assisted model
- Guest editorial: selected papers from ICIMCS 2012
- Learning Multi-view Deep Features for Small Object Retrieval in Surveillance Scenarios
- Robust Multiview Feature Learning for RGB-D Image Understanding
- Semantic-Based Location Recommendation With Multimodal Venue Semantics
- Sparse canonical correlation analysis for recognition
- Sparse principle motion component for one-shot gesture recognition
- The AdaBoost algorithm for vehicle detection based on CNN features
- A novel segmentation based video-denoising method with noise level estimation
- A Stereo-Vision-Assisted model for depth map super-resolution
- Achieving dynamic load balancing through mobile agents in small world P2P networks
- Adaptive Learning for Celebrity Identification With Video Context
- Attribute-Augmented Semantic Hierarchy: Towards a Unified Framework for Content-Based Image Retrieval
- Exploiting Web Images for Semantic Video Indexing Via Robust Sample-Specific Loss
- Gradient-domain-based enhancement of multi-view depth video
- Improving Color Constancy with Internet Photo Collections
- Introduction to the Special Issue Best Papers of ACM Multimedia 2013
- Product Aspect Ranking and Its Applications
- Robust (Semi) Nonnegative Graph Embedding
- A Pattern Matching Based Model for Implicit Opinion Question Identification
- Attribute-augmented semantic hierarchy: towards bridging semantic gap and intention gap in image retrieval
- Beyond Text QA: Multimedia Answer Generation by Harvesting Web Information
- Click-boosting random walk for image search reranking
- Detecting Group Activities With Multi-Camera Context
- GPSView: A scenic driving route planner
- Hierarchical Organization of Collaboratively Constructed Content
- Interactive social group recommendation for Flickr photos
- Learning attribute-aware dictionary for image classification and search
- Marginalized multi-layer multi-instance kernel for video concept detection
- Multimedia encyclopedia construction by mining web knowledge
- Partial-Duplicate Image Retrieval via Saliency-Guided Visual Matching
- Robust Semantic Video Indexing by Harvesting Web Images
- Visual-Textual Joint Relevance Learning for Tag-Based Social Image Search
- A comprehensive representation scheme for video semantic ontology and its applications in semantic concept detection
- Active learning for social image retrieval using Locally Regressive Optimal Design
- Answering Opinion Questions on Products by Exploiting Hierarchical Organization of Consumer Reviews
- Attribute feedback
- Attribute feedback
- Attribute-assisted reranking for web image retrieval
- Automatic labeling hierarchical topics
- Combining SIFT and Global Features for Web Image Classification
- Difficulty Guided Image Retrieval Using Linear Multiple Feature Embedding
- Event Driven Web Video Summarization by Tag Localization and Key-Shot Identification
- Interactive Video Indexing With Statistical Active Learning
- k-Partite graph reinforcement and its application in multimedia information retrieval
- Mining Travel Patterns from Geotagged Photos
- Multimedia Question Answering
- Oracle in Image Search: A Content-Based Approach to Performance Prediction
- Parallel Lasso for Large-Scale Video Concept Detection
- Robust Non-negative Graph Embedding: Towards noisy data, unreliable graphs, and noisy labels
- Semantic-Gap-Oriented Active Learning for Multilabel Image Annotation
- Text Mining in Multimedia
- The 4th International Conference on Internet Multimedia Computing and Service, ICIMCS '12, Wuhan, China, September 9-11, 2012
- Topology Adaptation Based on Mobile Agent in Unstructured P2P Networks
- Video Browser Showdown by NUS
- Visual query attributes suggestion
- Aspect Ranking: Identifying Important Product Aspects from Online Consumer Reviews
- Difficulty guided image retrieval using linear multiview embedding
- Domain-Assisted Product Aspect Hierarchy Generation: Towards Hierarchical Organization of Unstructured Consumer Reviews
- Hierarchical organization of unstructured consumer reviews
- Integrating rich information for video recommendation with multi-task rank aggregation
- Learning \"verb-object\" concepts for semantic image annotation
- Learning concept bundles for video search with complex queries
- Less is More: Efficient 3-D Object Retrieval With Query View Selection
- Locally regressive G-optimal design for image retrieval
- Matching Content-based Saliency Regions for partial-duplicate image retrieval
- Mining Travel Patterns from GPS-Tagged Photos
- Multimedia answering: enriching text QA with media information
- Optimizing multimodal reranking for web image search
- Product comparison using comparative relations
- Query expansion by spatial co-occurrence for image retrieval
- Research and applications on georeferenced multimedia: a survey
- Semi-automatic Flickr Group Suggestion
- ShotTagger: tag location for internet videos
- Utilizing Related Samples to Enhance Interactive Concept-Based Video Search
- Evaluation of histogram based interest point detector in web image classification and search
- Joint Learning of Labels and Distance Metric
- Mediapedia: Mining Web Knowledge to Construct Multimedia Encyclopedia
- TRECVID 2010 Known-item Search by NUS
- Utilizing related samples to learn complex queries in interactive concept-based video search
- Visual query suggestion: Towards capturing user intent in internet image search
- Which Tags Are Related to Visual Content?
- An efficient sparse metric learning in high-dimensional space via emphl(_mbox1)-penalized log-determinant regularization
- Graph-based semi-supervised learning with multiple labels
- Robust Distance Metric Learning with Auxiliary Knowledge
- Visual query suggestion
- A joint appearance-spatial distance for kernel-based image categorization
- Feature Detection and Correspondence for Camera Calibration
- Graph-based semi-supervised learning with multi-label
- Joint multi-label multi-instance learning for image classification
- MSRA atT TRECVID 2008: High-Level Feature Extraction and Automatic Search
- Optimized video scene segmentation
- Unbiased active learning for image retrieval
- Building a comprehensive ontology to refine video concept detection
- MSRA-USTC-SJTU at TRECVID 2007: High-Level Feature Extraction and Search
- Refining video annotation by exploiting pairwise concurrent relation