Apr 3, 2012 · Searching for the co-occurrence of two visual concepts in unlabeled images is an important step towards answering complex user queries.

Abstract—Searching for the co-occurrence of two visual con- cepts in unlabeled images is an important step towards answering complex user queries.

In this paper we introduce the notion of bi-concepts, a new concept-based retrieval method that is directly learned from social-tagged images. As the number of ...

We study the behavior of our bi-concept search engine using 1.2 M social-tagged images as a data source. Our experiments indicate that harvesting examples for ...

Learning to rank images for complex queries in concept-based search · Harvesting visual concepts for image search with complex queries · Linguistic Patterns and ...

examples from social-tagged images for learning bi-concept detectors. Page 5. 74. Chapter 5. Harvesting Social Images for Bi-Concept Search. Bi-concept. e.g. ...

Harvesting Social Images for Bi-Concept Search. Towards an- swering complex visual searches, we introduce in this chapter the notion of bi-concepts as a ...

cently, harvesting social images for bi-concept search was proposed in [16] to retrieve images in which two concepts are co-occurring. However, it is unable ...

Concept search is the process of searching for specific concepts or ideas within a dataset or a collection of documents. Concept search can be accomplished ...

This paper presents a scheme to enhance web image reranking for complex queries by fully exploring the information from simple visual concepts.