Semantic concept based video retrieval using convolutional neural network

摘要

Retrieval of videos efficiently and effectively has become a challenging issue nowadays and dealing with multi-conceptvideos is the center of focus. The aim of the work presented here is to propose an improved semantic concept-based videoretrieval method using a novel ranked intersection filtering technique and a foreground driven concept co-occurrencematrix. In the proposed ranked intersection filtering technique, an intersection of ranked concept probability scores istaken from key-frames associated with a query shot to identify concepts to be used in retrieval. Convolutional neuralnetwork is used as a baseline. The proposed method is implemented using a classifier built with a fusion of asymmetricallytrained deep CNNs to deal with data imbalance problem, a novel foreground driven concept co-occurrence matrix toexploit concept co-occurrence information and a ranked intersection filtering approach. Performance is evaluated by ameasure, mean average precision on TRECVID multi-label dataset. The results are compared with state-of-the-art otherexisting methods in its class and shown its superiority.