位置：成果数据库 > 会议 > 会议详情页
Learning compact visual descriptor for low bit rate mobile landmark search
  • 所属机构名称：哈尔滨工业大学
  • 会议名称：22nd International Joint Conference on Artificial Intelligence, IJCAI 2011
  • 时间：2011
  • 成果类型：会议
  • 相关项目：基于视觉动态认知特性的上下文视频语义捕捉
作者： Ji, Rongrong|Duan, Ling-Yu|Chen, Jie|Yao, Hongxun|Huang, Tiejun|Gao, Wen|
同会议论文项目
基于视觉动态认知特性的上下文视频语义捕捉
期刊论文 17 会议论文 37
同项目会议论文
The Scale of Edges
Action Segmentation in Dance Video
Flexible Presentation of Videos Based on Affective Content Analysis
Real-time visual tracking using L2 norm regularization based collaborative representation
Video Stabilization based on Saliency driven SIFT Matching and discriminative Ransac
Age classification based on back-propagation network
Video Indexing and Recommendation Based on Affective Analysis of Viewers
Sparse Coding Based Motion Attention for Abnormal Event Detection
On Dense Sampling Size
Probe the Potts States in the Minicolumn Dynamics
ROBUST VISUAL TRACKING VIA CONTEXT OBJECTS COMPUTING
CONTOUR TRACKING VIA ON-LINE DISCRIMINATIVE APPEARANCE MODELING BASED LEVEL SETS
A Novel Supervised Level Set Method for Non-Rigid Object Tracking
Learning heterogeneous data for hierarchical web video classification
A spatiotemporal context phrase description for general dynamic texture
Contextual dictionaries for image super resolution
Robust object tracking via inertial potential based mean shift
Structured Testons for Texture Representation
Unsupervised Fast Anomaly Detection in Crowds
NIGHT VIDEO ENHANCEMENT USING IMPROVED DARK CHANNEL PRIOR
A lowbit rate vocabulary coding scheme for mobile landmark search
Towards Low Bit Rate Mobile Visual Search with Multiple Channel Coding
SPARSE REPRESENTATION BASED VISUAL ELEMENT ANALYSIS
Edge-Respecting Image Smoothing via Extrema Interpolation
A spatial-temporal constraint-based action recognition method
The Shortest Warping Paht Based Multiple Images Alignment
NON-RIGID OBJECT TRACKING BY ADAPTIVE DATA-DRIVEN KERNEL
Learning the trip suggestion from landmark photos on the web
PKUBench: A context rich mobile visual search benchmark
What Are We Looking For: Towards Statistical Modeling of Saccadic Eye Movement and Visual Saliency
Aesthetic Composition Represetation for Portrait Photographing Recommendation
Memorable Basis: Towards Human-Centralized Sparse Representation
Real-Time Viewfinder Composition Assessment and Recommendation to Mobile Photographing
Action Retrieval Based on Generalized Dynamic Depth Data Matching
Exploring Implicit Image Statistics for Visual Representativeness Modeling
Affective Video Classification Based on Spatio-Temporal Feature Fusion