A General Method for Appearance-Based People Search Based on Textual Queries
نویسندگان
چکیده
Person re-identification consists of recognising a person appearing in different video sequences, using an image as a query. We propose a general approach to extend appearance-based re-identification systems, enabling also textual queries describing clothing appearance (e.g., “person wearing a white shirt and checked blue shorts”). This functionality can be useful, e.g., in forensic video analysis, when textual descriptions of individuals of interest given by witnesses are available, instead of images. Our approach is based on turning any given appearance descriptor into a dissimilarity-based one. This allows us to build detectors of the clothing characteristics of interest using supervised classifiers trained in a dissimilarity space, independently on the original descriptor. Our approach is evaluated using the descriptors of three different re-identification methods, on a benchmark data set.
منابع مشابه
People Search with Textual Queries About Clothing Appearance Attributes
Person re-identification consists of searching for an individual of interest in video sequences acquired by a camera network, using an image of that individual as a query. Here we consider a related task, named people search with textual queries, which consists of searching images of individuals that match a textual description of clothing appearance, given by a Boolean combination of predefine...
متن کاملIdentifying and Ranking the Important Textual and Paratextual Elements in Fiction Retrieval
Purpose: The purpose of this study is to identify the textual and paratextual elements in retrieving fiction from the readers’ perspective in order to provide the most appropriate access points for the readers and to improve access to fictions based on the readers’ needs. Method: The current research is an applied study in terms of purpose, applying a mixed method that was conducted using the ...
متن کاملAn Effective Path-aware Approach for Keyword Search over Data Graphs
Abstract—Keyword Search is known as a user-friendly alternative for structured languages to retrieve information from graph-structured data. Efficient retrieving of relevant answers to a keyword query and effective ranking of these answers according to their relevance are two main challenges in the keyword search over graph-structured data. In this paper, a novel scoring function is proposed, w...
متن کاملمدل جدیدی برای جستجوی عبارت بر اساس کمینه جابهجایی وزندار
Finding high-quality web pages is one of the most important tasks of search engines. The relevance between the documents found and the query searched depends on the user observation and increases the complexity of ranking algorithms. The other issue is that users often explore just the first 10 to 20 results while millions of pages related to a query may exist. So search engines have to use sui...
متن کاملExternal Plagiarism Detection based on Human Behaviors in Producing Paraphrases of Sentences in English and Persian Languages
With the advent of the internet and easy access to digital libraries, plagiarism has become a major issue. Applying search engines is one of the plagiarism detection techniques that converts plagiarism patterns to search queries. Generating suitable queries is the heart of this technique and existing methods suffer from lack of producing accurate queries, Precision and Speed of retrieved result...
متن کامل