Similarity Search with Implicit Object Features
نویسندگان
چکیده
Driven by many real applications, in this paper we study the problem of similarity search with implicit object features; that is, the features of each object are not pre-computed/evaluated. As the existing similarity search techniques are not applicable, a novel and efficient algorithm is developed in this paper to approach the problem. The R-tree based algorithm consists of two steps: feature evaluation and similarity search. Our performance evaluation demonstrates that the algorithm is very efficient for large spatial datasets.
منابع مشابه
Identification of the underlying factors affecting information seeking behavior of users interacting with the visual search option in EBSCO: a grounded theory study
Background and Aim: Information seeking is interactive behavior of searcher with information systems and this active interaction occurs in a real environment known as background or context. This study investigated the factors influencing the formation of layers of context and their impact on the interaction of the user with search option dialoge in EBSCO database. Method: Data from 28 semi-stru...
متن کاملCognitive Residues of Similarity: After-Effects of Similarity Computations in Visual Search
What are the “cognitive after-effects” of making a similarity judgement? What, cognitively, is left behind and what effect might these residues have on subsequent processing? In this paper, we probe for such after-effects using a visual search task, performed after a task in which pictures of real-world objects were compared. So, target objects were first presented in a comparison task (e.g., r...
متن کاملCognitive residues of similarity
What are the “cognitive after-effects” of making a similarity judgement? What, cognitively, is left behind and what effect might these residues have on subsequent processing? In this paper, we probe for such after-effects using a visual search task, performed after a task in which pictures of real-world objects were compared. So, target objects were first presented in a comparison task (e.g., r...
متن کاملConvolutional Neural Networks for Text Hashing
Hashing, as a popular approximate nearest neighbor search, has been widely used for large-scale similarity search. Recently, a spectrum of machine learning methods are utilized to learn similarity-preserving binary codes. However, most of them directly encode the explicit features, keywords, which fail to preserve the accurate semantic similarities in binary code beyond keyword matching, especi...
متن کاملLearning Dense Models of Query Similarity from User Click Logs
The goal of this work is to integrate query similarity metrics as features into a dense model that can be trained on large amounts of query log data, in order to rank query rewrites. We propose features that incorporate various notions of syntactic and semantic similarity in a generalized edit distance framework. We use the implicit feedback of user clicks on search results as weak labels in tr...
متن کامل