In this paper we introduce a novel contextual fusion method to improve the detection scores of semantic concepts in images and videos. Our method consists of three phases. For eac...
In recent years, with the rapid proliferation of digital images, the need to search and retrieve the images accurately, efficiently, and conveniently is becoming more acute. Automa...
Text-based search using video speech transcripts is a popular approach for granular video retrieval at the shot or story level. However, misalignment of speech and visual tracks, ...
There is an approach of annotation extraction from printed documents in which annotations are extracted by comparing the image of an annotated document and its original document i...
Methods of retrieving images that incorporate humangenerated metadata, such as keyword annotation and collaborative filtering, are less vulnerable to the semantic gap than content...