位置：成果数据库 > 会议 > 会议详情页
Video Shrinking by Auditory and Visual Cues
  • 所属机构名称：中国科学院计算技术研究所
  • 会议名称：IEEE Pacific-Rim Conference on Multimedia, PCM2009
  • 成果类型：会议
  • 相关项目：融合时间空间信息的视频关注分析理论与方法研究及其在手机视频中的应用
作者： Shuqiang Jiang|Qianqian Xu|Qingming Huang |Yu Gong|Huiying Liu|
同会议论文项目
融合时间空间信息的视频关注分析理论与方法研究及其在手机视频中的应用
期刊论文 9 会议论文 29 专利 3 著作 1
同项目会议论文
S3MKL: Scalable Semi-supervised Multiple Kernel Learning for Image Data Mining
FAST COPY DETECTION BASED ON SLICE ENTROPY SCATTERGRAPH
Advertise Gently - In-image advertising with Low Intrusiveness
Robust Copy Detection by Mining Temporal Self-Similarities
Visual ContextRank for Web Image Retrieval
Shot Classification for Action Movies Based on Motion Characteristics
Lower Attentive Region Detection for Virtual Content Insertion in Broadcast Video
A Generic Virtual Content Insertion System Based on Visual Attention Model
A Pixel-wise Local Information-based Background Subtraction Approach
Naming Faces in Broadcast News Video By Image Google
iMTV - An Integrated System for MTV Affective Analysis
Spatial-Temporal Attentive Analysis for Home Video
Multiple Instance Boost Using Graph Embedding Based Decision Stump for Pedestrian Detection
Object Tracking Using Incremental 2D-LDA Learning and Bayes Inference
Fast and Effective Text Detection
Event based news video people classification and ranking using multimodality features
Vicept: Link Visual Features to Concepts for Large-scale Image Understanding
Memory Matrix: A Novel User Experience for Home Video
Multiple Kernel Learning with High Order Kernels, Analysis and Search
Multi-description of Local Interest Point for Partial-duplicate Image Retrieval
Personalized Online Video Recommendation by Neighborhood Score Propagation Based Global Ranking
Personalized MTV Affective Analysis Using User Profile
Coarse-to-fine Video Text Detection
Visual-Aural Attention Modeling for Talk Show Video Highlight Detection
AFFECTIVE MTV ANALYSIS BASED ON AROUSAL AND VALENCE FEATURES
People Redetection Using Adaboost with Sift and Correlogram
A Two-Stage Approach to Highlight Extraction in Sports Video by Using AdaBoost and Multi-modal
Pedestrian Detection via Logistic Multiple Instance Boosting