Content-Based Image Retrieval at the End of the Early Years

By Arnold M. W. Smeulders, Marcel Worring, S. Santini, Amarnath Gupta, Ramesh C. Jain. 2000

2,409 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Information Retrieval & Search

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

In Information Retrieval & Search

Citations in the corpus

Webly Supervised Learning of Convolutional Networks (2015, neutral): “One possibility is to use commercial text-based image search engine to increase di-3 versity in the training data.”
Image-Based Recommendations on Styles and Substitutes (2015, background): “The system shares these characteristics with more common forms of recommender system, but does so on the basis of the appearance of the object, rather than metadata, reviews, or similar.”
Deep Multimodal Distance Metric Learning Using Click Constraints for Image Ranking (2017, background): “Most approaches can be categorized into text-based image retrieval (TBIR) [3], [4] and content-based image retrieval (CBIR) [5]–[7].”
High-level event recognition in unconstrained videos (2012, neutral): “) [129].”
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.”
What Do Different Evaluation Metrics Tell Us About Saliency Models? (2016, methodology): “Similarity metrics operating on image features have been a subject of investigation and application to different computer vision domains [51], [75], [83], [94].”
Applying Fuzzy DLs in the Extraction of Image Semantics (2009, background): “Semantic image analysis has challenged researchers for decades in the quest for generalisable approaches to alleviate the so called semantic gap [1–4], i.”
Asymmetric bagging and random subspace for support vector machines-based relevance feedback in image retrieval (2006, methodology): “R ELEVANCE feedback [21] is an important tool to improve the performance of content-based image retrieval (CBIR) [22].”
Exploring Context and Content Links in Social Media: A Latent Space Method (2012, methodology): “The CMR approach attempts to model high-level concepts from low-level concepts extracted from the MOs.”
Deep Hashing Network for Efficient Similarity Retrieval (2016, background): “While unsupervised methods are more general and can be trained without semantic labels or relevances, they are restricted by the semantic gap dilemma (Smeulders et al. 2000) that high-level semantic description of an object often differs from low-level feature descriptors.”
VisualRank: Applying PageRank to Large-Scale Image Search (2008, methodology): “Many systems proposed in the past [2], [3], [4], [5] are considered as “pure” CBIR systems—”
Learning to Hash for Indexing Big Data—A Survey (2015, background): “This discrepancy between semantic and metric spaces has been recognized in the computer vision and machine learning communities, namely as semantic gap [15].”
Performance evaluation of local colour invariants (2009, neutral): “In this paper, we consider the extension to colour-based descriptors. colour has high discriminative power; in many cases, objects can well be recognized merely by their colour characteristics [15] [16] [17] [18] [19] [20].”
Content-based Image Retrieval in Medical Applications (2004, background): “In addition to the requirements originating from content-based retrieval in general [11],the design of a medical image retrieval system requires attention to several other aspects and domain-specific properties [10].”
Deep Visual-Semantic Hashing for Cross-Modal Retrieval (2016, background): “To date, eﬀective and eﬃcient cross-modal hashing remains a challenge, due to the heterogeneity across diﬀerent modalities [31, 38], and the semantic gap between low-level features and high-level semantics [32].”
50 Years of object recognition: Directions forward (2013, methodology): “Local image-based features are also used for vision based localization and mapping with some success [165], [166], [167] and are currently quite popular in content-based image retrieval [168].”
Directional multiresolution image representations (2002, methodology): “Euclidean distance) on the extracted feature set as a similarity function [155].”