Distilled Collections from Textual Image Queries
نویسندگان
چکیده
We present a distillation algorithm which operates on a large, unstructured, and noisy collection of internet images returned from an online object query. We introduce the notion of a distilled set, which is a clean, coherent, and structured subset of inlier images. In addition, the object of interest is properly segmented out throughout the distilled set. Our approach is unsupervised, built on a novel clustering scheme, and solves the distillation and object segmentation problems simultaneously. In essence, instead of distilling the collection of images, we distill a collection of loosely cutout foreground “shapes”, which may or may not contain the queried object. Our key observation, which motivated our clustering scheme, is that outlier shapes are expected to be random in nature, whereas, inlier shapes, which do tightly enclose the object of interest, tend to be well supported by similar shapes captured in similar views. We analyze the commonalities among candidate foreground segments, without aiming to analyze their semantics, but simply by clustering similar shapes and considering only the most significant clusters representing non-trivial shapes. We show that when tuned conservatively, our distillation algorithm is able to extract a near perfect subset of true inliers. Furthermore, we show that our technique scales well in the sense that the precision rate remains high, as the collection grows. We demonstrate the utility of our distillation results with a number of interesting graphics applications.
منابع مشابه
Aletras, Nikolaos, Timothy Baldwin, Jey Han Lau and Mark Stevenson (to appear) Representing Topics Labels for Exploring Digital Libraries, In Proceedings of Digital Libraries 2014, London, UK
Topic models have been shown to be a useful way of representing the content of large document collections, for example via visualisation interfaces (topic browsers). These systems enable users to explore collections by way of latent topics. A standard way to represent a topic is using a set of keywords, i.e. the top-n words with highest marginal probability within the topic. However, alternativ...
متن کاملIntegrating Textual and Visual Information for Cross-Language Image Retrieval
This paper explores the integration of textual and visual information for cross-language image retrieval. An approach which automatically transforms textual queries into visual representations is proposed. The relationships between text and images are mined. We employ the mined relationships to construct visual queries from textual ones. The retrieval results of textual and visual queries are c...
متن کاملUsing Pseudo-relevance Feedback to Improve Image Retrieval Results
In this paper, we propose a pseudo-relevance feedbackmethod to deal with the photographic retrieval and medical retrieval tasks of ImageCLEF 2007. The aim of our participation to ImageCLEF is to evaluate a combination method using both english textual queries and image queries to answer to topics. The approach processes image queries and merges them with textual queries in order to improve resu...
متن کاملFrom Text to Image: Generating Visual Query for Image Retrieval
In this paper, we explore the help of visual features to cross-language image retrieval. We propose an approach that transforms textual queries into visual representations. The relationships between text and images are modeled. Visual queries are constructed from textual queries using the relationships. The retrieval results using textual and visual queries are combined to generate the final ra...
متن کاملSymmetric Statistical Translation Models for Automatic Image Annotation
Automatic image annotation provides means for users to search image collections on the semantic level using natural language queries. In the past, statistical machine translation models have been successfully applied to automatic image annotation. A problem with this approach is that, due to the skewed distribution of term frequency for annotation words, common words have been overly favored, w...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Comput. Graph. Forum
دوره 34 شماره
صفحات -
تاریخ انتشار 2015