A survey of content-based image retrieval with high-level semantics

By Ying Liu, Dengsheng Zhang, Guojun Lu, Wei-Ying Ma. Pattern Recognition, 2007

1,963 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/3c52a42b68696ba85abb12db3b4bdf9e128ed15a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

A Decade Survey of Content Based Image Retrieval Using Deep Learning (2020, neutral): “[2] in 2000, [20] in 2002, [21] in 2004, [22] in 2006, [23] in 2007, [24] in 2008, [25] in 2014 and [26] in 2017.”
Local Tetra Patterns: A New Feature Descriptor for Content-Based Image Retrieval (2012, background): “A comprehensive and extensive literature survey on CBIR is presented in [1]–[4].”
Medical image retrieval using deep convolutional neural network (2017, background): “The performance of a CBIR system mainly depends on these selected features [7].”
Processing Social Media Messages in Mass Emergency (2014, background): “In addition, there are cases of websites being set up in response to crises in 2003 [Palen and Liu 2007].”
Joint embeddings of shapes and images via CNN image purification (2015, methodology): “The difference between these two levels is referred to as the semantic gap [Smeulders et al. 2000], and is the main focus of CBIR methods, as surveyed in [Liu et al. 2007].”
Understanding Deep Learning Techniques for Image Segmentation (2019, background): “Image segmentation is useful in many cases as they are representative of spatial relations among various objects [12, 127].”
Generating Semantically Precise Scene Graphs from Textual Descriptions for Improved Image Retrieval (2015, background): “Rui et al. (1999), Liu et al. (2007), and Siddiquie et al. (2011) provide overviews of the developments of this ﬁeld over the last twenty years.”
A fully automatic end-to-end method for content-based image retrieval of CT scans with similar liver lesion annotations (2017, background): “The semantic annotations bridge the sematic gap by adding amiddle layer between the high-levelmedical content of the image and the low-level image features [12].”
What Do Different Evaluation Metrics Tell Us About Saliency Models? (2016, background): “Similarity metrics operating on image features have been a subject of investigation and application to different computer vision domains [47], [71], [80], [92].”
Ranking consistency for image matching and object retrieval (2014, methodology): “In this paper, we focus on local features that are used to compute a BoW vector for each image, whose similarity can then be measured by a dot-product similarity [1,5], set similarity [26] or a liner-SVM classifier [8].”
Image retrieval based on micro-structure descriptor (2011, background): “Content-based image retrieval (CBIR) was then emerging in 1980s [1].”
Deep multiple instance learning for image classification and auto-annotation (2015, background): “Image annotation aims at producing rich image descriptions at different levels [26].”
Integration of numeric and symbolic information for semantic image interpretation (2016, neutral): “The main challenge in SII is bridging the so called semantic gap [22], which is the complex correlation between low-level image features and high-level semantic concepts.”
Emotion related structures in large image databases (2010, methodology): “…Lenz ITN, Linköping University ITN, Linköping University SE-60174 Norrköping, Sweden SE-60174 Norrköping, Sweden martin.solli@liu.se reiner.lenz@liu.se ABSTRACT We introduce two large databases consisting of 750 000 and 1.2 million thumbnail-sized images, labeled with emotionrelated keywords.”