位置：成果数据库 > 会议 > 会议详情页
Cross Modal Metric Learning with Multi-level Semantic Relevance
  • 所属机构名称：北京邮电大学
  • 会议名称：IEEE International Conference on Image Processing
  • 时间：2014.10.27
  • 成果类型：会议
  • 相关项目：视觉注意模型在语义视频搜索中的应用
作者： Yan hua, Zhicheng Zhao, Anni Cai|
同会议论文项目
视觉注意模型在语义视频搜索中的应用
期刊论文 7 会议论文 38
同项目会议论文
An improved system for concept-based video retrieval
An output aggregation system for large scale cross-modal retrieval
Person Re-Identification by Local Feature Based on Super Pixel
<span>A Probabilistic Saliency Model With Memory-guided Top-down Cues for Free-Viewing</spa
BUPT-MCPRL at TRECVID 2012
Bagging-Based Metric Learning for Person Re-identification
A multi modal content-based copy detection approach
Content-based social image retrieval with context regularization
A Real-time Fall Detection System Based on HMM and RVM
BUPT-MCPRL at TRECVID2013
Find dominant bins of a histogram by sparse representation
An Improved System for Concept-based Video Retrieval
Person Re-identification Using Matrix Completion
Tree-based Shape Descriptor for Scalable Logo Detection
Anchor-supported Multi-modality Hashing Embedding for Person Re-identification
Find dominant bins of a histogram by sparse representation
Supervised sparse representation with coefficients' group constraint
A novel interactive image retrieval method based on LSH and SVM
Metric Learning with Trace-norm Regularization for Person Re-identification
A Multimodal Content-based Copy Detection Approach
Robust Motion Segmentation via Refined Sparse Subspace Clustering
A Robust Moving Object Segmentation Algorithm Using Integrated Mask-based Background Maintenance
An Adaptive Symmetry Detection Algorithm Based on Local Features
BUPT-MCPRL at TRECVID2013
Spatio-Temporal LBP based Moving Object Segmentation in Compressed Domain
Tag-Based Social Image Search with Hyperedges Correlation
A robust instance-based video search method by re-ranking for multiple visual codebooks
A Novel Interactive Image Retrieval Method Based On LSH and SVM
A Robust Instance-based Video Search Method by Re-ranking for Multiple Visual Codebooks
BUPT-MCPRL at TRECVID 2012
Robust 3D Human Pose Estimation via Dual Dictionaries Learning
Hierarchical Codebook Background Model Using Haar-like Features
Parametric Local Multi-Modal metric learning for Person Re-identification
Pedestrian Detection in Single Frame by Edgelet-LBP Part Detectors
An Improved Method of Crowd Counting Based on Regression
BUPT-MCPRL at TRECVID 2014
Supervised Sparse Representation with Coefficients Group Constraint