Visual tag dictionary
Published 23 October 2009
Meng Wang, Kuiyuan Yang, Xian‐Sheng Hua, Hao Zhang
Citations36
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
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.
Abstract
Visual-word based image representation has shown effectiveness in a wide variety of applications such as categorization, annotation and search. By detecting keypoints in images and treating their patterns as visual words, an image can be represented as a bag of visual words, which is analogous to the bag-of-words representation of text documents. In this paper, we introduce a corpus named visual tag dictionary. Unlike the conventional dictionaries that define terms with textual words, the visual tag dictionary interprets each tag with visual words. The dictionary is constructed in a fully automatic way by exploring the tagged image data on the Internet. With this dictionary, tags and images are connected via visual words and many applications can be thus facilitated. As examples, we empirically demonstrate the effectiveness of the dictionary in tag-based image search, tag ranking and image annotation.
Keywords
Computer Science
International Journal of Computer VisionDistinctive Image Features from Scale-Invariant Keypoints
55,266 Citations2004David Lowe
This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
ACM Transactions on Information SystemsCumulated gain-based evaluation of IR techniques
4,634 Citations2002Kalervo Järvelin, Jaana Kekäläinen
This article proposes several novel measures that compute the cumulative gain the user obtains by examining the retrieval result up to a given ranked position, and test results indicate that the proposed measures credit IR methods for their ability to retrieve highly relevant documents and allow testing of statistical significance of effectiveness differences.
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.
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.
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 TechnologyUnified Video Annotation via Multigraph Learning
441 Citations2009Meng Wang, Xian-Sheng Hua +4 more
This paper shows that various crucial factors in video annotation, including multiple modalities, multiple distance functions, and temporal consistency, all correspond to different relationships among video units, and hence they can be represented by different graphs, and proposes optimized multigraph-based semi-supervised learning (OMG-SSL), which aims to simultaneously tackle these difficulties in a unified scheme.
IEEE Transactions on MultimediaBeyond Distance Measurement: Constructing Neighborhood Similarity for Video Annotation
288 Citations2009Meng Wang, Xian-Sheng Hua +2 more
This work proposes a novel neighborhood similarity measure, which explores the local sample and label distributions and shows that the neighborhood similarity between two samples simultaneously takes into account three characteristics: their distance; the distribution difference of the surrounding samples; and the distribution different of surrounding labels.
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.
Inferring semantic concepts from community-contributed images and noisy tags
208 Citations2009Jinhui Tang, Shuicheng Yan +3 more
This paper proposes a novel sparse graph-based semi-supervised learning approach for harnessing the labeled and unlabeled data simultaneously, and constructs an informative compact concept space with small semantic gap to infer the semantic concepts in this space to bridge the semantic gap.
Columbia University’s Baseline Detectors for 374 LSCOM Semantic Visual Concepts
188 Citations2007Akira Yanagawa, Shih‐Fu Chang
Development of effective concept detectors and systematic evaluation ethods has become an active research topic in recent years and a major video retrieval enchmarking event, NIST TRECVID, has contributed to this emerging area through the rovision of large sets of common data and the organization of common benchmark tasks to form over this data.
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.
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.
A learning-based hybrid tagging and browsing approach for efficient manual image annotation
32 Citations2008Rong Yan, Apostol Natsev +1 more
A learning approach to improve the efficiency of manual image annotation by proposing formal models to characterize the annotation times for two commonly used manual annotation approaches, i.e., tagging and browsing.
Discriminative training of GMM for speaker identification
31 Citations2002Cesar Martín del Alamo, F.J. Caminero Gil +2 more
A novel discriminative training procedure for a Gaussian mixture model (GMM) speaker identification system based on the segmental generalized probabilistic descent (GPD) algorithm formulated to estimate the GMM parameters is described.
VirtualTour
28 Citations2006Feng Jing, Lei Zhang +1 more
The VirtualTour system is an online travel service dedicated on high quality images, which helps travelers plan their trip and a wieldy UI is designed to support several useful features, e.g. query by map, location or path.
Web 2.0 dictionary
13 Citations2008Qingxiong Yang, Xin Chen +1 more
It is demonstrated the effectiveness of the Web 2.0 Dictionary for image/video understanding and retrieval, object categorization, tagging recommendation, etc, in this paper.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIERole of classifiers in multimedia content management
8 Citations2003Milind Naphade, John R. Smith
This paper compares the performance of some popular classifiers for semantic video indexing, one technique for generative modeling and one for discriminant learning and shows how they behave depending on the number of examples that the user is willing to provide to the system.