Social Image Tagging With Diverse Semantics
IEEE Transactions on CyberneticsPublished 19 March 2014
Xueming Qian, Xian‐Sheng Hua, Yuan Yan Tang, Tao Mei
Citations62
SJR quartileQ1
SJR score4.45
SNIP3.22
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This paper proposes an approach to retag social images with diverse semantics where both the relevance of a tag to image as well as its semantic compensations to the already determined tags are fused to determine the final tag list for a given image.
Abstract
We have witnessed the popularity of image-sharing websites for sharing personal experiences through photos on the Web. These websites allow users describing the content of their uploaded images with a set of tags. Those user-annotated tags are often noisy and biased. Social image tagging aims at removing noisy tags and suggests new relevant tags. However, most existing tag enrichment approaches predominantly focus on tag relevance and overlook tag diversity problem. How to make the top-ranked tags covering a wide range of semantic is still an opening, yet challenging, issue. In this paper, we propose an approach to retag social images with diverse semantics. Both the relevance of a tag to image as well as its semantic compensations to the already determined tags are fused to determine the final tag list for a given image. Different from existing image tagging approaches, the top-ranked tags are not only highly relevant to the image but also have significant semantic compensations with each other. Experiments show the effectiveness of the proposed approach.
Keywords
Computer Science
2009 IEEE Conference on Computer Vision and Pattern RecognitionImageNet: A large-scale hierarchical image database
61,841 Citations2009Jia Deng, Wei Dong +4 more
A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
IEEE Transactions on Pattern Analysis and Machine IntelligenceContent-based image retrieval at the end of the early years
6,023 Citations2000A.W.M. Smeulders, Marcel Worring +3 more
The working conditions of content-based retrieval: patterns of use, types of pictures, the role of semantics, and the sensory gap are discussed, as well as aspects of system engineering: databases, system architecture, and evaluation.
NUS-WIDE
3,045 Citations2009Tat‐Seng Chua, Jinhui Tang +4 more
The benchmark results indicate that it is possible to learn effective models from sufficiently large image dataset to facilitate general image retrieval and four research issues on web image annotation and retrieval are identified.
ACM Computing SurveysImage retrieval
3,019 Citations2008Ritendra Datta, Dhiraj Joshi +2 more
Almost 300 key theoretical and empirical contributions in the current decade related to image retrieval and automatic image annotation are surveyed, and the spawning of related subfields are discussed, to discuss the adaptation of existing image retrieval techniques to build systems that can be useful in the real world.
ACM SIGIR ForumThe Use of MMR, Diversity-Based Reranking for Reordering Documents and Producing Summaries
2,210 Citations2017Jaime Carbonell, Jade Goldstein
A method for combining query-relevance with information-novelty in the context of text retrieval and summarization and preliminary results indicate some benefits for MMR diversity ranking in document retrieval and in single document summarization.
The use of MMR, diversity-based reranking for reordering documents and producing summaries
2,144 Citations1998Jaime Carbonell, Jade Goldstein
This paper presents a method for combining query-relevance with information-novelty in the context of text retrieval and summarization, and preliminary results indicate some benefits for MMR diversity ranking in document retrieval and in single document summarization.
IEEE Transactions on Pattern Analysis and Machine Intelligence80 Million Tiny Images: A Large Data Set for Nonparametric Object and Scene Recognition
1,976 Citations2008Antonio Torralba, Rob Fergus +1 more
For certain classes that are particularly prevalent in the dataset, such as people, this work is able to demonstrate a recognition performance comparable to class-specific Viola-Jones style detectors.
Improving recommendation lists through topic diversification
1,839 Citations2005Cai-Nicolas Ziegler, Sean M. McNee +2 more
This work presents topic diversification, a novel method designed to balance and diversify personalized recommendation lists in order to reflect the user's complete spectrum of interests, and introduces the intra-list similarity metric to assess the topical diversity of recommendation lists.
The MIR flickr retrieval evaluation
1,811 Citations2008Mark J. Huiskes, Michael S. Lew
This paper presents a collection for the MIR community comprising 25000 images from the Flickr website which are redistributable for research purposes and represent a real community of users both in the image content and image tags.
IEEE Transactions on Knowledge and Data EngineeringThe Google Similarity Distance
1,764 Citations2007Rudi Cilibrasi, Paul Vitányi
A new theory of similarity between words and phrases based on information distance and Kolmogorov complexity is presented, which is applied to construct a method to automatically extract similarity, the Google similarity distance, of Words and phrases from the WWW using Google page counts.
Flickr tag recommendation based on collective knowledge
931 Citations2008Börkur Sigurbjörnsson, Roelof van Zwol
This paper analyzes a representative snapshot of Flickr and presents and evaluates tag recommendation strategies to support the user in the photo annotation task by recommending a set of tags that can be added to the photo.
Why we tag
838 Citations2007Morgan G. Ames, Mor Naaman
The incentives for annotation in Flickr, a popular web-based photo-sharing system, and ZoneTag, a cameraphone photo capture and annotation tool that uploads images to Flickr are investigated to offer a taxonomy of motivations for annotation along two dimensions (sociality and function).
ACM SIGIR ForumBeyond Independent Relevance
567 Citations2015ChengXiang Zhai, William W. Cohen +1 more
A framework for evaluating subtopic retrieval is proposed which generalizes the traditional precision and recall metrics by accounting for intrinsic topic difficulty as well as redundancy in documents and a maximal marginal relevance (MMR) ranking strategy is proposed.
IEEE Transactions on Pattern Analysis and Machine IntelligenceReal-Time Computerized Annotation of Pictures
511 Citations2008Jia Li, James Z. Wang
Tag ranking
481 Citations2009Dong Liu, Xian‐Sheng Hua +3 more
This paper proposes a tag ranking scheme, aiming to automatically rank the tags associated with a given image according to their relevance to the image content, and applies tag ranking into three applications: tag-based image search, tag recommendation, and group recommendation.
IEEE Transactions on Circuits and Systems for Video TechnologyCBSA: content-based soft annotation for multimodal image retrieval using bayes point machines
452 Citations2003Edward Yi Chang, King-Shy Goh +2 more
This work proposes a content-based soft annotation procedure for providing images with semantical labels, and experiments with two learning methods, support vector machines (SVMs) and Bayes point machines (BPMs), to select a base binary-classifier for CBSA.
IEEE Transactions on Image ProcessingVisual-Textual Joint Relevance Learning for Tag-Based Social Image Search
442 Citations2012Yue Gao, Meng Wang +4 more
An approach that simultaneously utilizes both visual and textual information to estimate the relevance of user tagged images is proposed, and the relevance estimation is determined with a hypergraph learning approach.
IEEE Transactions on Pattern Analysis and Machine IntelligenceA Multimedia Retrieval Framework Based on Semi-Supervised Ranking and Relevance Feedback
410 Citations2011Yi Yang, Feiping Nie +4 more
A new semi-supervised algorithm called ranking with Local Regression and Global Alignment (LRGA) to learn a robust Laplacian matrix for data ranking and a semi- supervised long-term RF algorithm to refine the multimedia data representation.
IEEE Transactions on MultimediaLearning Social Tag Relevance by Neighbor Voting
386 Citations2009Xirong Li, Cees G. M. Snoek +1 more
This paper proposes a neighbor voting algorithm which accurately and efficiently learns tag relevance by accumulating votes from visual neighbors and proves that the algorithm is a good tag relevance measurement for both image ranking and tag ranking.
IEEE Transactions on Image ProcessingMultimodal Graph-Based Reranking for Web Image Search
344 Citations2012Meng Wang, Hao Li +3 more
Experimental results demonstrate that the proposed reranking approach is more robust than using each individual modality, and it also performs better than many existing methods.
Hierarchical clustering of WWW image search results using visual, textual and link information
320 Citations2004Deng Cai, Xiaofei He +3 more
A hierarchical clustering method using visual, textual and link analysis to cluster the search results into different semantic clusters of image search results is proposed.
IEEE Transactions on MultimediaEvent Driven Web Video Summarization by Tag Localization and Key-Shot Identification
272 Citations2012Meng Wang, Richang Hong +4 more
This paper presents an approach for event driven web video summarization by tag localization and key-shot mining, and provides two types of summaries, i.e., threaded video skimming and visual-textual storyboard.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>Image annotation using SVM</title>
259 Citations2003Claudio Cusano, Gianluigi Ciocca +1 more
An innovative image annotation tool for classifying image regions in one of seven classes - sky, skin, vegetation, snow, water, ground, and buildings - or as unknown is described.
Image tag refinement towards low-rank, content-tag prior and error sparsity
245 Citations2010Guangyu Zhu, Shuicheng Yan +1 more
This work decomposition of the user-provided tag matrix D into a low-rank refined matrix A and a sparse error matrix E, namely D = A + E, targeting the optimality measured by four aspects, constitute a constrained yet convex optimization problem.
Image annotations by combining multiple evidence & wordNet
243 Citations2005Yohan Jin, Latifur Khan +2 more
This paper proposes a novel approach that augments the classical model with generic knowledge-based, WordNet to prune irrelevant keywords by the usage of WordNet and shows that by augmenting knowledge- based with classical model the authors can improve annotation accuracy by removing irrelevant keywords.
IEEE Transactions on MultimediaTowards a Relevant and Diverse Search of Social Images
230 Citations2010Meng Wang, Kuiyuan Yang +2 more
A diverse relevance ranking scheme that is able to take relevance and diversity into account by exploring the content of images and their associated tags, and it is shown that the diversity of search results can be enhanced while maintaining a comparable level of relevance.
Visual diversification of image search results
214 Citations2009Reinier H. van Leuken, Lluis Garcia +2 more
Based on a performance evaluation, the outcome of the methods for visual diversification of image search results closely resembles human perception of diversity, which was established in an extensive clustering experiment carried out by human assessors.
IEEE Transactions on Pattern Analysis and Machine IntelligenceAnnotating Images by Mining Image Search Results
197 Citations2008Xinjing Wang, Lei Zhang +2 more
This paper proposes a novel attempt at model-free image annotation, which is a data-driven approach that annotates images by mining their search results, and enables annotating with unlimited vocabulary and is highly scalable and robust to outliers.
Improving web search results using affinity graph
196 Citations2005Benyu Zhang, Hua Li +6 more
A novel ranking scheme named Affinity Ranking (AR) is proposed to re-rank search results by optimizing two metrics: diversity -- which indicates the variance of topics in a group of documents; and information richness -- which measures the coverage of a single document to its topic.
IEEE Transactions on MultimediaWeb Image Annotation Via Subspace-Sparsity Collaborated Feature Selection
192 Citations2012Zhigang Ma, Feiping Nie +3 more
A novel feature selection method that can jointly select the most relevant features from all the data points by using a sparsity-based model and apply it to automatic image annotation is proposed and validated.
IEEE Transactions on Pattern Analysis and Machine IntelligenceA Thousand Words in a Scene
186 Citations2007Pedro Quelhas, Florent Monay +3 more
Learning to tag
186 Citations2009Lei Wu, Linjun Yang +2 more
A multi-modality recommendation based on both tag and visual correlation is proposed, and the tag recommendation is formulates as a learning problem, and Rankboost algorithm is applied to learn an optimal combination of these ranking features from different modalities.
Learning tag relevance by neighbor voting for social image retrieval
180 Citations2008Xirong Li, Cees G. M. Snoek +1 more
A novel algorithm that scalably and reliably learns tag relevance by accumulating votes from visually similar neighbors is proposed, and treated as tag frequency, learned tag relevance is seamlessly embedded into current tag-based social image retrieval paradigms.
To search or to label?
177 Citations2006Lyndon S. Kennedy, Shih‐Fu Chang +1 more
This work proposes a system for predicting which visual concepts will show the greatest increase in performance from investing human effort in obtaining annotations, and proposes to build this system as an estimation of the absolute gain in average precision experienced from using human annotations instead of web search.
Flickr distance
168 Citations2008Lei Wu, Xian‐Sheng Hua +3 more
Both subjective user study and objective evaluation show that Flickr distance is more coherent to human perception than Google distance, which makes it a more reasonable distance metric.
Information Processing & ManagementA risk minimization framework for information retrieval
149 Citations2005ChengXiang Zhai, John Lafferty
A probabilistic information retrieval framework in which the retrieval problem is formally treated as a statistical decision problem, and how this framework can unify existing retrieval models and accommodate systematic development of new retrieval models is discussed.
Content-Based Image Annotation Refinement
136 Citations2007Changhu Wang, Jing Feng +2 more
A content-based image annotation refinement (CIAR) algorithm is proposed to re-rank the candidate annotations of images and leverages both corpus information and the content feature of a query image.
IEEE Transactions on Image ProcessingScale-Rotation Invariant Pattern Entropy for Keypoint-Based Near-Duplicate Detection
128 Citations2009Wan‐Lei Zhao, Chong‐Wah Ngo
An algorithm, namely Scale-Rotation invariant Pattern Entropy (SR-PE), is described, for the detection of near-duplicates in large-scale video corpus and the coherency of patterns and the perception of visual similarity are carefully addressed through entropy measure.
Resolving tag ambiguity
125 Citations2008Kilian Q. Weinberger, Malcolm Slaney +1 more
A probabilistic framework is introduced that allows us to find two tags that appear in different contexts but are both likely to co-occur with the original tag set and suggest new tags that disambiguate the original tags.
Image annotation by large-scale content-based image retrieval
115 Citations2006Xirong Li, Le Chen +3 more
Comprehensive evaluation of image annotation on Corel and U. Washington image databases show the effectiveness and efficiency of the proposed approach to solving the automatic image annotation problem in a novel search and mining framework.
IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)Automatic Image Annotation and Retrieval Using Group Sparsity
113 Citations2012Shaoting Zhang, Junzhou Huang +2 more
A group-sparsity-based feature selection algorithm is introduced to leverage both the sparsity and clustering properties of features, and incorporate it into the image annotation task, and keyword similarity is modeled in the annotation framework.
IEEE Transactions on Image ProcessingWeb and Personal Image Annotation by Mining Label Correlation With Relaxed Visual Graph Embedding
113 Citations2011Yi Yang, Fei Wu +4 more
This paper proposes a new inductive algorithm for image annotation by integrating label correlation mining and visual similarity mining into a joint framework and shows that the globally optimal solution of the proposed framework can be obtained by performing generalized eigen-decomposition.
Image retagging
111 Citations2010Dong Liu, Xian‐Sheng Hua +2 more
This paper proposes a social image "retagging" scheme that aims at assigning images with better content descriptors and shows the remarkable performance improvements brought by retagging via two applications, i.e., tag-based search and automatic annotation.
Large-Scale Duplicate Detection for Web Image Search
108 Citations2006Bin Wang, Zhiwei Li +2 more
A novel algorithm is proposed to handle the situation, in which each image is compactly represented by a hash code, and can be both efficient and effective for duplicate detection in Web image search.
Near-duplicate keyframe retrieval by nonrigid image matching
106 Citations2008Jianke Zhu, Steven C. H. Hoi +2 more
A novel and effective Nonrigid Image Matching (NIM) approach to tackle the task of near-duplicate keyframe retrieval from real-world video corpora and promising results show that the proposed method is more effective than other state-of-the-art approaches for near- DUplicateKeyframe retrieval.
IEEE Transactions on Pattern Analysis and Machine IntelligenceA Hybrid Probabilistic Model for Unified Collaborative and Content-Based Image Tagging
98 Citations2010Ning Zhou, William K. Cheung +2 more
A novel hybrid probabilistic model (HPM) which integrates low-level image features and high-level user provided tags to automatically tag images is presented which developed a collaborative filtering method based on nonnegative matrix factorization (NMF) for tackling this data sparsity issue.
Tag refinement by regularized LDA
92 Citations2009Hao Xu, Jingdong Wang +2 more
A novel graphical model, regularized Latent Dirichlet Allocation (rLDA), is presented, which facilitates the topic modeling by exploiting both the statistics of tags and visual affinities of images in the corpus.
ARISTA - image search to annotation on billions of web photos
90 Citations2010Xinjing Wang, Lei Zhang +3 more
The Arista project is introduced, which aims to build a practical image annotation engine targeting at popular concepts in the real world, and is particularly interested in understanding how many image concepts can be addressed by the data-driven annotation approach and how good the performance is.
IGroup
86 Citations2006Jing Feng, Changhu Wang +4 more
IGroup, an efficient and effective algorithm that organizes Web image search results into clusters based on a key phrases extraction algorithm originally proposed for clustering general Web search results is proposed.
Spirittagger
85 Citations2008Emily Moxley, Jim Kleban +1 more
Experiments on a data set consisting of over 100,000 Flickr photos in Los Angeles and Southern California show that the geographically relevant tag suggestion tool provides a significant improvement in precision-recall performance over baseline image-based similarity suggestion.
Diversifying the image retrieval results
84 Citations2006Kai Song, Yonghong Tian +2 more
A re-ranking method based on topic richness analysis is proposed to enrich topic coverage in retrieval results and a quantitative criterion called diversity scores (DS) is proposed in order to evaluate the improvement.
Bipartite graph reinforcement model for web image annotation
84 Citations2007Xiaoguang Rui, Mingjing Li +3 more
A bipartite graph reinforcement model (BGRM) is proposed for web image annotation, where a set of candidate annotations is extracted from its surrounding text and other textual information in the hosting web page to include more potentially relevant annotations.
Jointly optimising relevance and diversity in image retrieval
75 Citations2009Thomas Deselaers, Tobias Gass +2 more
A method to jointly optimise the relevance and the diversity of the results in image retrieval using techniques inspired by dynamic programming algorithms and it is observed that the diverse results are more attractive to an average user.
IEEE Transactions on MultimediaGPS Estimation for Places of Interest From Social Users' Uploaded Photos
73 Citations2013Jing Li, Xueming Qian +3 more
An unsupervised image GPS location estimation approach with hierarchical global feature clustering and local feature refinement and the effectiveness of the proposed hierarchical structure and inverted file structure is demonstrated.
IEEE Transactions on MultimediaImage Retagging Using Collaborative Tag Propagation
72 Citations2011Dong Liu, Shuicheng Yan +2 more
The proposed image retagging scheme is formulated as a multiple graph-based multi-label learning problem, which simultaneously explores the visual content of the images, semantic correlation of the tags as well as the prior information provided by users.
SheepDog
65 Citations2008Hongming Chen, Ming-Hsiu Chang +4 more
A system named SheepDog is proposed to automatically add photos into appropriate groups and recommend suitable tags for users on Flickr, adopting concept detection to predict relevant concepts of a photo and probing into the issue about training data collection for concept classification.
Image clustering based on a shared nearest neighbors approach for tagged collections
63 Citations2008Pierre-Alain Moëllic, Jean‐Emmanuel Haugeard +1 more
A new method for extracting meaningful and representative clusters based on a shared nearest neighbors (SNN) approach that treats both content-based features and textual descriptions (tags) and some experimental results show that this approach extracts representative information of an image set.
NeurocomputingTagging photos using users' vocabularies
61 Citations2013Xueming Qian, Xiaoxiao Liu +3 more
A personalized photo tagging approach by using users' own vocabularies that can recommend users preferred tags for their newly uploaded photos based on the history information in their social communities by modeling users' tagging habit is proposed.
Information Storage and RetrievalA searching procedure for information retrieval
58 Citations1964William Goffman
A search procedure for an information retrieval system is developed whereby the answer to a question is obtained by maximizing an evaluation function of the system's output in terms of the probability of relevance.
IEEE Transactions on Image ProcessingImage Annotation by Input&#x2013;Output Structural Grouping Sparsity
47 Citations2012Yahong Han, Fei Wu +2 more
The proposed structured feature selection by structural grouping sparsity can be used not only to select group-of-features but also to conduct within-group selection and leads to a quite interpretable model for image understanding.
Multimedia SystemsScalable search-based image annotation
45 Citations2008Changhu Wang, Feng Jing +2 more
A search-based image annotation algorithm that is analogous to information retrieval that shows the effectiveness and efficiency of the proposed algorithm but also the advantage of image retrieval using annotation results over that using visual features.
IEEE Transactions on MultimediaTag Tagging: Towards More Descriptive Keywords of Image Content
43 Citations2011Kuiyuan Yang, Xian‐Sheng Hua +2 more
An automatic scheme called tag tagging to supplement semantic image descriptions by associating a group of property tags with each existing tag, which enables much more precise image search especially when certain tag properties are included in the query.
Image tag clarity
40 Citations2009Aixin Sun, Sourav S. Bhowmick
Evaluated on a large real-world dataset containing more than 269K images and their associated tags, it is shown that NITC score can effectively identify the visual-representative tags from all tags contributed by users.
Diversifying image search with user generated content
40 Citations2008Roelof van Zwol, Vanessa Murdock +2 more
A retrieval model which provides diverse results as a property of the model itself, rather than in a post-retrieval step is presented, and it is shown that it is possible to minimize the trade-offs between precision and diversity.
Pattern RecognitionCross-media retrieval using query dependent search methods
39 Citations2010Yi Yang, Fei Wu +3 more
This work constructs an MMD semi-semantic graph (MMDSSG) by jointly analyzing the heterogeneous multimedia data and proposes different learning methods of relevance feedback (RF) to improve the performance of cross-media retrieval.
Annotating images by harnessing worldwide user-tagged photos
38 Citations2009Xirong Li, Cees G. M. Snoek +1 more
A joint-modality tag relevance estimation method which efficiently addresses both textual and visual clues in a search-based framework to tackle the unreliability and sparsity of user tagging.
Visual tag dictionary
36 Citations2009Meng Wang, Kuiyuan Yang +2 more
A corpus named visual tag dictionary is introduced, which interprets each tag with visual words and is constructed in a fully automatic way by exploring the tagged image data on the Internet.
Detection of non-identical duplicate consumer photographs
33 Citations2004Alejandro Jaimes, Shih‐Fu Chang +1 more
A novel framework that automatically distinguishes between non-identical duplicate and very similar non-duplicate images is introduced and a novel and extensive image duplicate database is presented.
On the sampling of web images for learning visual concept classifiers
32 Citations2010Shiai Zhu, Gang Wang +2 more
The impact of exploiting the tagged images towards concept learning is studied, investigating the issue of how the quality of pseudo training images affects concept detection performance, and a simple approach is proposed, named semantic field, for predicting the relevance between a target concept and the tag list associated with the images.
Object Categorization Using Hierarchical Wavelet Packet Texture Descriptors
30 Citations2009Xueming Qian, Guizhong Liu +4 more
Experimental results show that object categorization performances of the proposed texture descriptors are better than that of Gabor texture descriptor and as good as that of PHOG shape descriptor.
ACM Transactions on Multimedia Computing Communications and ApplicationsIn-video product annotation with web information mining
30 Citations2012Guangda Li, Meng Wang +3 more
This article presents a novel solution to the annotation of specific products in videos by mining information from the Web by simultaneously leveraging Amazon and Google image search engine.
Retagging social images based on visual and semantic consistency
24 Citations2010Dong Liu, Xian‐Sheng Hua +2 more
This paper proposes a social image ``retagging'' scheme that aims at assigning images with better content descriptors that is formulated as an optimization framework based on the consistency between ``visual similarity'' and ``semantic similarity'' in social images.
Tagging over time
23 Citations2007Ritendra Datta, Dhiraj Joshi +2 more
It is observed that the addition of this meta-learning layer produces much improved results that outperform best-known results, and the T/T approach produces progressively better annotation with time, significantly outperforming the black-box as well as the static form of the meta-learner, on real-world data.
Lecture notes in computer scienceGPS Estimation from Users’ Photos
22 Citations2013Jing Li, Xueming Qian +3 more
A GPS location estimation approach is proposed for an uploaded image, its GPS information is estimated by both hierarchical global feature classification and local feature refinement to guarantee the accuracy and computational cost.
Effective music tagging through advanced statistical modeling
21 Citations2010Jialie Shen, Wang Meng +3 more
A novel system called MMTagger is introduced that effectively integrates both multimodal and temporal information in the representation of music signal and seamlessly combines Multiple Gaussian Mixture Models (GMMs) and Support Vector Machine (SVM) into a single framework.
Visual summarization of landmarks via viewpoint modeling
20 Citations2012Yao Xue, Xueming Qian
This paper describes an approach for visually summarizing a landmark by recommending images with diverse viewpoints by using a 4-D viewpoint vector, which describes viewpoint in horizontal, vertical, scale and orientation aspects.
Beyond tag relevance
19 Citations2010Songhe Feng, Congyan Lang +1 more
This paper presents an integrated framework for tag saliency ranking which combines both visual attention model and multi-instance learning algorithm to investigate the saliencyranking order information of tags with respect to the given image.
Finding representative and diverse community contributed images to create visual summaries of geographic areas
19 Citations2011Stevan Rudinac, Alan Hanjalić +1 more
An automatic approach that uses community-contributed images to create representative and diverse visual summaries of specific geographic areas using a multimodal graph and introduces an edge-weighting mechanism for the fusion of heterogeneous modalities.
Generating representative images for landmark by discovering high frequency shooting locations from community-contributed photos
17 Citations2013Shuhui Jiang, Xueming Qian +3 more
This work is the first attempt to generate representative images by high frequency shooting locations mining by discovering high frequency Shooting locations from geo-tagged community-contributed photos.
Finding near-duplicate images on the web using fingerprints
16 Citations2008Srinitish Srinivasan, Neela Sawant
A fast, accurate and highly scalable image fingerprinting technique suited for near-duplicate detection at the web-scale, which is faster than fast approximate near-neighbor searches like LSH.
Lecture notes in computer scienceGeneric and Spatial Approaches to Image Search Results Diversification
14 Citations2009Monica Lestari Paramita, Jiayu Tang +1 more
A generic diversity and two novel spatial diversity algorithms for (image) search result diversification found to be promising and to achieve good geographical diversity while not significantly reducing precision are proposed.
Multi-graph similarity reinforcement for image annotation refinement
12 Citations2008Jimin Jia, Nenghai Yu +2 more
LCMKL
8 Citations2013Qing Li, Yun Gu +1 more
This paper proposes a novel approach called latent-community and multi-kernel learning (LCMKL), which outperforms other state-of-the-art approaches on NUS-WIDE database.
Tag filtering based on similar compatible principle
7 Citations2012Xueming Qian, Xian‐Sheng Hua +1 more
A similar compatible principle based tag filtering approach is proposed that determines the ranks of user annotated tags by maximizing the compatible value of changing the labels of the tags from irrelevant to relevant at each step.
Graph-cut based tag enrichment
6 Citations2011Xueming Qian, Xian‐Sheng Hua
Experiments on Flickr dataset demonstrate the effectiveness of the proposedGraph cut based tag enrichment approach, which builds a graph for each image with its initial tags.
Lecture notes in computer scienceRepresentativeness and Diversity in Photos via Crowd-Sourced Media Analysis
4 Citations2014Anca-Livia Radu, Julian Stöttinger +3 more
A hybrid, two step, machine and human automated media analysis approach to improve retrieval relevance by selecting a small number of representative and diverse images from a noisy set of candidate images (e.g. Internet media).
HAL (Le Centre pour la Communication Scientifique Directe)Creating visual summaries for geographic regions
4 Citations2009Adrian Popescu, Ioannis Kanellos
…