Exploring video clips in a vast collection of videos is difficult task. It necessary to provide an efficient system for users express the information need sought events that collection. Thus, we propose develop AVSeeker – active retrieval engine assist finding appropriate moments with two main query types: textual descriptions and visual examples. The characteristic AVSeekeris change from passi...

The majority of algorithms proposed in recommender systems literature has focused on improving recommendation accuracy, other important aspects of recommendation quality, the diversity of recommendations, have often been overlooked. Number of item ranking techniques that can generate substantially more diverse recommendations across all users while maintaining comparable levels of recommendatio...

Recommender systems offer users a more intelligent and personalised mechanism to seek out new information. Content-based recommender systems generally prefer to retrieve a set of items maximally similar to a users’ query and/or profile. We argue that as new types of recommendation domains and tasks emerge, this blind faith in the similarity assumption begins to seem flawed. We show that very of...

In audio based music recommendation, a well known effect is the dominance of songs from the same artist as the query song in recommendation lists. We verify that this effect also exists in a very large data set at the scale of the world wide web (> 250000). Since our data set contains multiple albums from individual artists, we can also show that the album effect is relatively bigger than the a...

In this paper, we present an adaptive graph-based personalized recommendation method based on co-ranking and query-based collaborative diffusion. By utilizing the unique network structure of n-partite heterogeneous graph, we attempt to address the problem of personalized recommendation in a two-layer ranking process with the help of reasonable measure of high and low order relationships and ana...

This paper explores the potential use of fuzzy logic for semantic music recommendation. We show that a set of affective/emotive, structural and kinaesthetic descriptors can be used to formulate a query which allows the retrieval of intended music. A semantic music recommendation system was built, based on an elaborate study of potential users and an analysis of the semantic descriptors that bes...

Recent advancement in day to day life accumulates more data in database hence database grew larger and complex since the number of entities is more and searching through the database is also becoming complex. The users are interested in gathering most relevant information by querying the database initially, by using Structured Query Language (SQL), but this can be done only by the SQL experts. ...

In this paper, we have developed a novel framework called JustClick to enable personalized image recommendation via exploratory search from large-scale collections of manuallyannotated Flickr images. First, a topic network is automatically generated to summarize large-scale collections of manuallyannotated Flickr images at a semantic level. Hyperbolic visualization is further used to enable int...

Recommendation systems help users find items of interest. Meta-recommendation systems provide users with personalized control over the combination of recommendation data from multiple information sources. In the process, they provide users with more helpful recommendations by allowing users to indicate how important each parameter is in their decision process, and how data should be weighted du...