.png){kind=icon}
Return
Constructing Visual Phrases for Effective and Efficient Object-Based Image Retrieval
.png){kind=icon}
PRE
AI
DOI：10.1145/1404880.1404887.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The explosion of multimedia data necessitates effective and efficient ways for us to get access to our desired ones. In this article, we draw an analogy between image retrieval and text retrieval and propose a visual phrase-based approach to retrieve images containing desired objects (object-based image retrieval). The visual phrase is defined as a pair of frequently co-occurred adjacent local image patches and is constructed using data mining. We design methods on how to construct visual phrase and how to index/search images based on visual phrase. We demonstrate experiments to show our visual phrase-based approach can be very efficient and more effective than current visual word-based approach.
Keywords:
Algorithms
Experimentation
Performance
Content-based image retrieval
inverted index
local image descriptor
SIFT
object-based image retrieval
visual phrase
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6
Papers:
2.0K
Citations:
5.4K
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSave
ShareSaveShareSave
View more