Statistical Models For Automatic Video Annotation And Retrieval
ICASSP (3)（2004）
摘要
We apply a continuous relevance model (CRM) to the problem of directly retrieving the visual content of videos using text queries. The model computes a joint probability model for image features and words using a training set of annotated images. The model may then be used to annotate unseen test images. The probabilistic annotations are used for retrieval using text queries. We also propose a modified model - the normalized CRM - which substantially improves performance on a subset of the TREC Video dataset.
更多查看译文
关键词
associative processing,content-based retrieval,feature extraction,image retrieval,query formulation,relevance feedback,statistics,video signal processing,annotated image training set,automatic video annotation,content based video retrieval,continuous relevance model,image associated words,image features,image segmentation,normalized CRM,probabilistic annotations,real-valued feature vectors,statistical models,text queries,video retrieval,video visual content,
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要