位置：成果数据库 > 会议 > 会议详情页
Building Contextual Visual Vocabulary for Large-scale Image Applications
  • 所属机构名称：中国科学院大学
  • 会议名称：18th ACM International Conference on Multimedia (ACM MM Full Paper)
  • 成果类型：会议
  • 相关项目：基于自适应特征的复杂背景下目标检测与跟踪方法研究
作者： Shiliang Zhang, Qingming Huang, et al.|
同会议论文项目
基于自适应特征的复杂背景下目标检测与跟踪方法研究
期刊论文 4 会议论文 21 专利 1
同项目会议论文
Novel Observation Model for Probabilistic Object Tracking
Action Recognition Using Spatial-Temporal Context
Real-time Interactive Multi-Target Tracking Using Kernel-Based Trackers
Nearest-Neighbor Classification Using Unlabeled Data for Real World Image Application
The Third Eye: Mining the Visual Cognition across Multilanguage Communities
Transfer Pedestrian Detector Towards View-Adaptiveness and Efficiency
Spatial-Temporal Attentive Analysis for Home Video
Near-Duplicate Video Matching with Transformation Recognition
Robust Copy Detection by Mining Temporal Self-Similarities
Spatial-temporal Video Browsing for Mobile Application Based on Visual Attention Analysis
Advertise Gently - In-image Advertising with Low Instrusiveness
A Pixel-wise Local Information-based Background Subtraction Approach
People Re-Detection Using AdaBoost with Sift and Color Correlogram
Shot Classification for Action Movies Based on Motion Characteristics
Group Activity Recognition by Gaussian Processes Estimation
Pedestrian Detection via Logistic Multiple Instance Boosting
Object Tracking Using Incremental 2D-LDA Learning and Bayes Inference
Multiple Instance Boost Using Graph Embedding Based Decision Stump for Pedestrian Detection
Lower Attentive Region Detection for Virtual Content Insertion in Broadcast Video
A Generic Virtual Content Insertion System Based on Visual Attention Model