相关论文
2016
BOF Image/Video Retrieval Model with Global Feature

Local interest points serve as an elementary building block in many video retrieval algorithms, and most of them exploit the local volume features using a Bag of Features (BOF) representation. Such representation, however, ignores potentially valuable information about the global distribution of interest points. In this paper, we first present an R feature to capture the detailed global geometrical distribution of interest points. Then, we propose a fusion strategy to combine the BOF representation with the global R feature for further improving recognition accuracy. Convincing experimental results on several publicly available datasets demonstrate that the proposed approach outperforms the state-of-the-art approaches in video retrieval.

2011 - Computer Knowledge and Technology
Design of a Desktop Search Engine

Currently the main desktop search engines lack the good user experience,and they can not build index instantly,and they have high resources occupation rate.So the thesis designs a smart,powerful and fast desktop search engine that has the better user experience.It supports the function of re-retrival of search results.Apart from this,it has low resources occupation rate,including cpu,memory and disk.And the thesis designs three types of indexes that ensure the real-time and recall ratio of the desktop search engine.

2006
Make Good Use of the Search Engine in the Reference and Consultation to Increase the Work Efficiency

This paper introduces some relevant background knowledge of the search engine, and puts forward some concrete measures for applying the search engine in library's references and consultations.

2015
Web Accessibility und Search Engine Ranking

Durch die immer weiter zunehmende Internetnutzung gewinnt die Berucksichtigung der Barrierefreiheitsprinzipien bei der Entwicklung von Webseiten stets mehr an Bedeutung. Von unterschiedlichen internationalen Organisationen (z. B. WAI) wurden mittlerweile einige Barrierefreiheitsrichtlinien entwickelt, darunter die aktuellsten WCAG 2.0, die als Grundlage fur Entwickler, aber auch fur Behorden dienen sollen. In mehreren Landern wurden diese Regelungen bereits in die lokale Gesetzgebung implementiert, um Barrierefreiheit in bestimmten Bereichen (z. B. Internetauftritte der Regierungen) zu gewahrleisten. Die aktuelle Forschung zeigt aber, dass in den meisten Bereichen bei der Barrierefreiheit im Internet wesentliches Verbesserungspotential besteht. Die Art und Weise, wie die Suchmaschinen die Internetseiten besuchen, ahnelt der Internetnutzung von Menschen mit Behinderungen, die beispielsweise ein Bildschirmlesegerat verwenden. Zusatzlich bestehen einige Uberschneidungen bei den Suchmaschinenrankingfaktoren und den Barrierefreiheitsprinzipien. Das Ziel der vorliegenden Arbeit besteht darin, den Zusammenhang zwischen dem Barrierefreiheitsniveau und dem Suchmaschinenranking am Beispiel von osterreichischen Regierungsseiten mittels Korrelationsanalyse zu untersuchen. Basierend auf der Literaturanalyse wurde eine positive Korrelation erwartet. Die Ergebnisse haben allerdings gezeigt, dass fur die ausgewahlte Stichprobe zwischen den Variablen keine statistisch signifikante Korrelation nach Spearman vorliegt. Zu den Einschrankungen der Studie zahlen die Grose der Stichprobe sowie die verwendete automatisierte Barrierefreiheitsbewertungsmethodik. Die vorliegende Arbeit soll eine Grundlage fur weitere Forschung in diesem Gebiet bieten und den Nutzen der Berucksichtigung von Barrierefreiheit im Internet fur mehrere Nutzer- und Entwicklergruppen verdeutlichen.

2013 - ICSOC Workshops
A Social Network Based Collaborative Video Story Composition Platform

There is a large number of videos produced and stored in data repositories on a daily basis. Story-telling is a common use-case for using these videos where a user composes a set of videos together to tell a story, either for learning purposes or sharing experiences. For example, a news editor may search and compose story based on video collected from multiple private and public repositories; an instructor may produce teaching materials using a set of publicly available video clips. Existing search engines have limitation on identifying useful video contents for users with different needs [2]. For a user who attempts to compile a story using a variety of videos, there are a few challenges with existing technologies. A search engine often returns a long list of videos that are relevant to the keywords the user enters into the search engine. How the videos in the list are suitable for the story line requires the user’s further investigation and the amount of work involved often overwhelms the user considering the number of videos returned by a search engine. It is often the case that the highly ranked videos are not the most appropriate ones for a story line under composing. In addition, videos are not organized in a structured manner based on the content, which makes identifying videos that match the story topic difficult and time consuming.

2010 - eBusiness & eCommerce eJournal
Real Time Markets vs. Synchronized Markets

I have been suggesting that live video streams should be mandated for all public companies. Simply as a reinforcement to the financial statements. The status quo is that people are taking the rating companies to court. This is further evidence that there is no confidence in the markets. A few years back I set up a web page describing my new standards for accounting. Fundamentally I discussed the definition of REAL TIME MARKETS. In 2009 the term real time refers to SYNCHRONIZED Markets. Real Time should be immediate and responsive valuations in the market to live events in the companies or economies.STOCK PRICE FALLING SCENARIO: COMPANY XYZ TRADES ON THE NYSE:THE DATE: A chilly January Morning in 2010. The Snow is falling but all the employees are hustling to get into work. The siren sounds as the workers punch the clock. Moments later they are at their work stations and the place is humming like a well oiled machine. Everybody is doing their job systematically...FROM HEAD OFFICE IN LONDON At the same time (Its 6 hours later GMT). Management is having a meeting and they pulled up the security cameras for the plant that just came online in the USA. The Meeting is about critiquing the layout of the plant to enhance efficiency. So they are all watching and commenting about different camera angles.At the same time: In Washington DC The SEC is searching through the Video Archives verifying that the assets on the Financial Statements actually exist. They are using the Video Search Engine to quickly go through months worth of footage. They also used The Audio Search Engine to verify and scan for conversations about the issues in the financial statements. In Tokyo an Investment Banker is considering investing in the company as he watches the trucks deliver the products to the shopping mall. The Malls looks full and the stores are making sales so the Japanese investor is excited about making the investment.BACK AT THE PLANT 3 hours later A HUGE SOUND GOES OFF LIKE AN ALARM. There is a fire at the plant. People are screaming and running out the door. The room is filling with smoke. The cameras can't make anything out. The audio is hard to make out without the NATIONAL INSTRUMENT LAB VIEW scanner. However, Its clear THAT THEIR PANIC IS IN THE AIR! Back in LONDON Management maintains their cool. They call both the fire stations and they alert the local management in the MANUFACTURING PLANT USA. They were still watching the action at the manufacturing plant. BACK IN TOKYO The investment banker set his alerts before he logged off and went to bed. Any deviation from the normal sounds of the manufacturing company, he gets alerts in text messages (sms) and email. So now he is awake in the middle of the night checking for the alerts. With one click he is on the video stream of the fire in the MANUFACTURING PLANT. He decides to sell the stock short because their is obviously going to be a delay in the manufacturing process. Which means the products will not make it to the shopping mall in time. The delays will hurt company earnings. In Washington DC. the SEC documents the event. END OF SCENE STOCK PRICE FALLING SCENARIO.

2009 - 2009 IEEE International Conference on Multimedia and Expo
Resource-adaptive multimedia analysis on stream mining systems

Large-scale multimedia semantic concept detection requires realtime identification of a set of concepts in streaming video or large image datasets. The potentially high data volumes of multimedia content, and high complexity associated with individual concept detectors, have hindered the practical deployment of many current solutions. In this paper, we present a summary of our work in building systems and applications for resource adaptive semantic concept detection in multimedia using large-scale distributed stream mining systems. We construct such concept detection applications as a hierarchical topology of individual concept detectors, and deploy them on distributed processing infrastructure. We then focus on dynamically configuring individual concept detectors to meet system imposed resource constraints while minimizing a penalty defined in terms of the misclassification cost. We present multiple centralized and distributed algorithms for this configuration, and describe the implemented application and system. We also verify through simulations that significant improvement in terms of accuracy of classification can be achieved through our approach.

2007 - Computer Engineering and Applications
Research on video retrieval using high-level semantic

Video semantic retrieval is one of the most popular search issue in video retrieval today.Most video retrieval techniques are low-level feature based and no-semantic.These feature are abstract and quite different from the semantic concepts in human thought.To go beyond low-level similarity and access video data content by semantics,how can we bridge the gap between the low-level features and high-level semantics.How can we develop the model of video semantic retrieval.In this paper,semantic video understand,semantic video analysis,semantic video extract are discussed,in order to design a model of semantic video retrieval.

2008 - Zhong xi yi jie he xue bao = Journal of Chinese integrative medicine
Regulation of aromatase P450 expression by puerarin in endometrial cell line RL95-2.

OBJECTIVE To study the effects of puerarin on the aromatase P450 (P450(arom)) mRNA expression and the effects of low-dose puerarin on transcription factors of the P450(arom) gene (P II) 5'-flanking region. METHODS The effects of puerarin on the P450(arom) mRNA expression were determined by real-time polymerase chain reaction (RT-PCR). The 5'-flanking region was amplified by PCR using human genomic cDNA as a template. By means of the restriction sites and sequence confirmation, the PCR product was cloned into reporter vector. Series of sequential deletion reporter constructs were transiently transfected into RL95-2 cells which were treated with or without puerarin. Luciferase activity was measured by Dual-Luciferase Reporter Assay System and Luminoskan Ascent luminometer. Furthermore, by using web-based search program, the most possible cis-acting elements and transcription factors were evaluated. RESULTS The data demonstrated that low-dose puerarin treatment could decrease P450(arom) expression at mRNA level compared to dimethyl sulphoxide (DMSO) treatment (P<0.01), and puerarin (10(-7)mol/L) had a time-course effect on P450(arom) mRNA expression, which reached the bottom at 12h (P<0.01). Cells transfected with the -763/+8 bp constructs showed decrease in relative luciferase activity after puerarin (10(-7)mol/L) treatment compared to DMSO treatment (P<0.05), indicating an essential regulatory site between -763 bp and -543 bp responsible for the transcription suppression by puerarin. Furthermore, the most possible transcription factors, which turned out to be AP-1(c-jun/c-fos) at -410/-401 bp were also evaluated. The activity of exogenous AP-1 was reduced after 12 hours of puerarin treatment (P<0.05). The inhibition of c-jun mRNA also showed a time-course effect, which bottomed out at 12h in parallel with that of P450(arom) (P<0.01). The protein level of c-jun was also down-regulated by puerarin (10(-7)mol/L) treatment at 12h. CONCLUSION The suppression of P450(arom) expression and activity may be associated with the down-regulation of transcription factor AP-1/c-jun. This partially explains the mechanisms whereby puerarin treats endometriosis.

2011 - International Journal of Computer Applications
A Novel Architecture of a Parallel Web Crawler

ABSTRACT Due to the explosion in the size of the WWW[1,4,5] it becomes essential to make the crawling process parallel. In this paper we present an architecture for a parallel crawler that consists of multiple crawling processes called as C-procs which can run on network of workstations. The proposed crawler is scalable, is resilient against system crashes and other event. The aim of this architecture is to efficiently and effectively crawl the current set of publically indexable web pages so that we can maximize the download rate while minimizing the overhead from parallelization Keywords WWW, Search Engines, Crawlers, Parallel Crawlers. 1. INTRODUCTION The World-Wide Web has undergone explosive, exponential growth. As a consequence, users find themselves unable to browse the ever-changing, distributed hyperlink structure of the web. Furthermore, they are subjected to information overload – information is too abundant . With the increasing number of information resources on the Web, it is often more difficult to locate the resources that are relevant to a given need. Henceforth, Search Engines[2,3] are becoming equally important tool in locating relevant information.

2011 - Online Inf. Rev.
Discovering geographic web services in search engines

Purpose – There is an open discussion in the geographic information community about the use of digital libraries or search engines for the discovery of resources. Some researchers suggest that search engines are a feasible alternative for searching geographic web services based on anecdotal evidence. The purpose of this study is to measure the performance of Bing (formerly Microsoft Live Search), Google and Yahoo! in searching standardised XML documents that describe, identify and locate geographic web services.Design/methodology/approach – The study performed an automated evaluation of three search engines using their application programming interfaces. The queries asked for XML documents describing geographic web services, and documents containing links to those documents. Relevant XML documents linked from the documents found in the search results were also included in the evaluation.Findings – The study reveals that the discovery of geographic web services in search engines does not require the use of...

2015 - Indian journal of science and technology
State of the Art: A Summary of Semantic Image and Video Retrieval Techniques

Our paper comprises of almost maximum used state of the art techniques in video retrieval as a brief summary. As there is developments in all fields, media becomes more popular and so people begun to search videos to know the world happenings visually. This paper gives a review of existed combinational methods, algorithms and techniques. The image retrieval was obtained from multiple lower ranking methods. The survey of many methods leads to an introduction of combination of a best method. The main focus of this survey is focused on video retrieval techniques to identify the underlying factors that affect the performance of the combinational method and to judge the effectiveness to provide efficient semantic video retrieval. Finally we descript a broad discussion about the advantages and drawbacks that have been in state of the art. Due to these reasons semantic video retrieval became a challenging issue in various industries.

1998 - Internet Reference Services Quarterly
Ethnography of novices' first use of Web search engines: affective control in cognitive processing

Abstract Without prior searching instruction, undergraduate novices wrote structured self-reports during their first session on a Web search engine. Users chose their own topics and followed written instructions that prompted them to describe thoughts and feelings during specified stages of the search: pre-search formulation; search statement formulation; search strategy; and evaluation of results. The sentences in the self-reports were numbered and then coded according to their affective or cognitive function. The affective sentences reveal how users set goals and limit the scope of the cognitive operations. Search acts appear to be governed by an affective filter that organizes incoming information and provides criteria for ranking cognitive relevance to search goal. The cognitive sentences reveal a variety of operations in executing searches. Following the search, students made self-ratings on self-confidence as searchers and satisfaction with the search experience, with explanations of their ratings. ...

2006 - MM '06
Building concept ontology for medical video annotation

Most existing systems for content-based video retrieval (CBVR) are now amenable to support automatic low-level video content analysis and feature extraction, but they have limited effectiveness from a user's perspective. To support semantic video retrieval via keywords, we have proposed a novel framework by incorporating the concept ontology to enable more effective modeling and representation of semantic video concepts. Specifically, this novel framework includes: (a) Using the salient objects to achieve a middle-level understanding of the semantics of video contents; (b) Building a domain dependent concept ontology to enable multi-level modeling and representation of semantic video concepts; (c) Developing a multi-task boosting technique to achieve hierarchical video classifier training for automatic multi-level video annotation. The experimental results in a certain domain of medical education videos are also provided.

1999 - Comput. Networks
Measuring Index Quality Using Random Walks on the Web

Recent research has studied how to measure the size of a search engine, in terms of the number of pages indexed. In this paper, we consider a different measure for search engines, namely the quality of the pages in a search engine index. We provide a simple, effective algorithm for approximating the quality of an index by performing a random walk on the Web, and we use this methodology to compare the index quality of several major search engines.

2009 - MM '09
GRVS: a georeferenced video search engine

An increasing number of recorded videos are being tagged with geographic properties of the camera scenes. This meta-data is of significant use for storing, indexing and searching large collections of videos. By considering video related meta-information, more relevant and precisely delimited search results can be returned. Our system implementation demonstrates a prototype of a georeferenced video search engine (GRVS) that utilizes an estimation model of a camera's viewable scene for efficient video search. For video acquisition, our system provides an automated annotation software that captures videos and their respective field of views (FOV). The acquisition software allows community-driven data contributions to the search engine.

2010 - Comput. Vis. Image Underst.
Learning automatic concept detectors from online video

Concept detection is targeted at automatically labeling video content with semantic concepts appearing in it, like objects, locations, or activities. While concept detectors have become key components in many research prototypes for content-based video retrieval, their practical use is limited by the need for large-scale annotated training sets. To overcome this problem, we propose to train concept detectors on material downloaded from web-based video sharing portals like YouTube, such that training is based on tags given by users during upload, no manual annotation is required, and concept detection can scale up to thousands of concepts. On the downside, web video as training material is a complex domain, and the tags associated with it are weak and unreliable. Consequently, performance loss is to be expected when replacing high-quality state-of-the-art training sets with web video content. This paper presents a concept detection prototype named TubeTagger that utilizes YouTube content for an autonomous training. In quantitative experiments, we compare the performance when training on web video and on standard datasets from the literature. It is demonstrated that concept detection in web video is feasible, and that - when testing on YouTube videos - the YouTube-based detector outperforms the ones trained on standard training sets. By applying the YouTube-based prototype to datasets from the literature, we further demonstrate that: (1) If training annotations on the target domain are available, the resulting detectors significantly outperform the YouTube-based tagger. (2) If no annotations are available, the YouTube-based detector achieves comparable performance to the ones trained on standard datasets (moderate relative performance losses of 11.4% is measured) while offering the advantage of a fully automatic, scalable learning. (3) By enriching conventional training sets with online video material, performance improvements of 11.7% can be achieved when generalizing to domains unseen in training.

2010 - World Wide Web
Clustering Web video search results based on integration of multiple features

The usage of Web video search engines has been growing at an explosive rate. Due to the ambiguity of query terms and duplicate results, a good clustering of video search results is essential to enhance user experience as well as improve retrieval performance. Existing systems that cluster videos only consider the video content itself. This paper presents the first system that clusters Web video search results by fusing the evidences from a variety of information sources besides the video content such as title, tags and description. We propose a novel framework that can integrate multiple features and enable us to adopt existing clustering algorithms. We discuss our careful design of different components of the system and a number of implementation decisions to achieve high effectiveness and efficiency. A thorough user study shows that with an innovative interface showing the clustering output, our system delivers a much better presentation of search results and hence increases the usability of video search engines significantly.

2013 - ICCKE 2013
Creating a novel semantic video search engine through enrichment textual and temporal features of subtitled YouTube media fragments

Semantic video Annotation is an active research zone within the field of multimedia content understanding. With the stable increase of videos published on the famous video sharing platforms such as YouTube, more efforts are spent to automatically annotate these videos. In this paper, we propose a novel framework to annotating subtitled YouTube videos using both textual features such as all of portions extracted from web natural language processors in relation to subtitles, and temporal features such as the duration of the media fragments where particular entities are spotted. We implement SY-VSE (Subtitled YouTube Video Search Engine) as an efficient framework to cruising on the subtitled YouTube videos resident in the Linked Open Data (LOD) cloud. For realizing this purpose, we propose Unifier Module of Natural Language Processing (NLP) Tools Results (UM-NLPTR) for extracting main portions of the 10 NLP web tools from subtitles associated to YouTube videos in order to generate media fragments annotated with resources from the LOD cloud. Then, we propose Unifier Module of Popular API's Results (UM-PAR) containing the seven favorite web APIs to boost results of Named Entities (NE) obtained from UM-NLPTR. We will use dotNetRDF as a powerful and flexible API for working with Resource Description Framework (RDF) and SPARQL in .Net environments.

2007 - CIVR '07
Towards optimal bag-of-features for object categorization and semantic video retrieval

Bag-of-features (BoF) deriving from local keypoints has recently appeared promising for object and scene classification. Whether BoF can naturally survive the challenges such as reliability and scalability of visual classification, nevertheless, remains uncertain due to various implementation choices. In this paper, we evaluate various factors which govern the performance of BoF. The factors include the choices of detector, kernel, vocabulary size and weighting scheme. We offer some practical insights in how to optimize the performance by choosing good keypoint detector and kernel. For the weighting scheme, we propose a novel soft-weighting method to assess the significance of a visual word to an image. We experimentally show that the proposed soft-weighting scheme can consistently offer better performance than other popular weighting methods. On both PASCAL-2005 and TRECVID-2006 datasets, our BoF setting generates competitive performance compared to the state-of-the-art techniques. We also show that the BoF is highly complementary to global features. By incorporating the BoF with color and texture features, an improvement of 50% is reported on TRECVID-2006 dataset.

The MediaMill TRECVID 2008 Semantic Video Search Engine

Dennis Koelma
|
Xirong Li
|
Masoud Mazloom
|
Koen E. A. van de Sande
|
Arnold W. M. Smeulders
|
Cees Snoek
|
Yu-Gang Jiang
|
Cees G. M. Snoek
|
K. V. D. Sande
|
A. Smeulders
|
Yu-Gang Jiang
|
Xirong Li
|
M. Mazloom
|
D. Koelma

Abstract:In this paper we describe our TRECVID 2008 video retrieval experiments. The MediaMill team participated in three tasks: concept detection, automatic search, and interac- tive search. Rather than continuing to increase the number of concept detectors available for retrieval, our TRECVID 2008 experiments focus on increasing the robustness of a small set of detectors using a bag-of-words approach. To that end, our concept detection experiments emphasize in particular the role of visual sampling, the value of color in- variant features, the influence of codebook construction, and the effectiveness of kernel-based learning parameters. For retrieval, a robust but limited set of concept detectors ne- cessitates the need to rely on as many auxiliary information channels as possible. Therefore, our automatic search ex- periments focus on predicting which information channel to trust given a certain topic, leading to a novel framework for predictive video retrieval. To improve the video retrieval re- sults further, our interactive search experiments investigate the roles of visualizing preview results for a certain browse- dimension and active learning mechanisms that learn to solve complex search topics by analysis from user brows- ing behavior. The 2008 edition of the TRECVID bench- mark has been the most successful MediaMill participation to date, resulting in the top ranking for both concept de- tection and interactive search, and a runner-up ranking for automatic retrieval. Again a lot has been learned during this year’s TRECVID campaign; we highlight the most im- portant lessons at the end of this paper.

参考文献

[1]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[2]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[3]  H. Kuhn.  The Hungarian method for the assignment problem , 1955 .

[4]  M M Astrahan.  SPEECH ANALYSIS BY CLUSTERING, OR THE HYPERPHONEME METHOD , 1970 .

[5]  Gerard Salton,et al.  The SMART Retrieval System—Experiments in Automatic Document Processing , 1971 .

[6]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[7]  Martin F. Porter,et al.  An algorithm for suffix stripping , 1997, Program.

[8]  Michael McGill,et al.  Introduction to Modern Information Retrieval , 1983 .

[9]  Gerard Salton,et al.  Term-Weighting Approaches in Automatic Text Retrieval , 1988, Inf. Process. Manag..

[10]  Gerard Salton,et al.  Improving retrieval performance by relevance feedback , 1997, J. Am. Soc. Inf. Sci..

[11]  Wilson S. Geisler,et al.  Multichannel Texture Analysis Using Localized Spatial Filters , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  T. Landauer,et al.  Indexing by Latent Semantic Analysis , 1990 .

[13]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[14]  Edward A. Fox,et al.  Combination of Multiple Searches , 1993, TREC.

[15]  Yukinobu Taniguchi,et al.  Structured Video Computing , 1994, IEEE MultiMedia.

[16]  Helmut Schmidt,et al.  Probabilistic part-of-speech tagging using decision trees , 1994 .

[17]  Philip Resnik,et al.  Using Information Content to Evaluate Semantic Similarity in a Taxonomy , 1995, IJCAI.

[18]  Philippe Joly,et al.  Efficient automatic analysis of camera work and microsegmentation of video using spatiotemporal images , 1996, Signal Process. Image Commun..

[19]  David L. Sheinberg,et al.  Visual object recognition. , 1996, Annual review of neuroscience.

[20]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Takeo Kanade,et al.  Video OCR: indexing digital news libraries by recognition of superimposed captions , 1999, Multimedia Systems.

[22]  Yihong Gong,et al.  Lessons Learned from Building a Terabyte Digital Video Library , 1999, Computer.

[23]  Marcel Worring,et al.  Content-Based Image Retrieval at the End of the Early Years , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  Robert P. W. Duin,et al.  PRTools - Version 3.0 - A Matlab Toolbox for Pattern Recognition , 2000 .

[25]  Anil K. Jain,et al.  Statistical Pattern Recognition: A Review , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Peter M. A. Sloot,et al.  The distributed ASCI Supercomputer project , 2000, OPSR.

[27]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[28]  P. Bartlett,et al.  Probabilities for SV Machines , 2000 .

[29]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[30]  Anil K. Jain,et al.  Image classification for content-based indexing , 2001, IEEE Trans. Image Process..

[31]  Arnold W. M. Smeulders,et al.  Color Invariance , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[32]  Cees G. M. Snoek.  The authoring metaphor to machine understanding of multimedia , 2001 .

[33]  Edward Y. Chang,et al.  Support vector machine active learning for image retrieval , 2001, MULTIMEDIA '01.

[34]  Djoerd Hiemstra,et al.  Lazy Users and Automatic Video Retrieval Tools in (the) Lowlands , 2001, TREC.

[35]  Cor J. Veenman,et al.  Resolving Motion Correspondence for Densely Moving Points , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[36]  Jean-Luc Gauvain,et al.  The LIMSI Broadcast News transcription system , 2002, Speech Commun..

[37]  Georges Quénot,et al.  CLIPS at TREC 11: Experiments in Video Retrieval , 2002, TREC.

[38]  Erik F. Tjong Kim Sang,et al.  Memory-Based Shallow Parsing , 2002, J. Mach. Learn. Res..

[39]  M. Tarr,et al.  Visual Object Recognition , 1996, ISTCS.

[40]  Marcel Worring,et al.  Interactive Search Using Indexing, Filtering, Browsing and Ranking , 2003, TRECVID.

[41]  Thomas S. Huang,et al.  Relevance feedback in image retrieval: A comprehensive review , 2003, Multimedia Systems.

[42]  Andrew Zisserman,et al.  Video Google: a text retrieval approach to object matching in videos , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[43]  Harriet J. Nock,et al.  Discriminative model fusion for semantic concept detection and annotation in video , 2003, ACM Multimedia.

[44]  Ching-Yung Lin,et al.  Video Collaborative Annotation Forum: Establishing Ground-Truth Labels on Large Multimedia Datasets , 2003, TRECVID.

[45]  Jianping Fan,et al.  ClassView: hierarchical video shot classification, indexing, and accessing , 2004, IEEE Transactions on Multimedia.

[46]  Takeo Kanade,et al.  Object Detection Using the Statistics of Parts , 2004, International Journal of Computer Vision.

[47]  Ted Pedersen,et al.  WordNet::Similarity - Measuring the Relatedness of Concepts , 2004, NAACL.

[48]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[49]  Yi Wu,et al.  Ontology-based multi-classification learning for video concept detection , 2004, 2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763).

[50]  CHENGXIANG ZHAI,et al.  A study of smoothing methods for language models applied to information retrieval , 2004, TOIS.

[51]  Dirk P. Kroese,et al.  The Cross-Entropy Method: A Unified Approach to Combinatorial Optimization, Monte-Carlo Simulation and Machine Learning , 2004 .

[52]  Cordelia Schmid,et al.  Scale & Affine Invariant Interest Point Detectors , 2004, International Journal of Computer Vision.

[53]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[54]  Jitendra Malik,et al.  Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons , 2001, International Journal of Computer Vision.

[55]  Daniel P. Huttenlocher,et al.  Efficient Graph-Based Image Segmentation , 2004, International Journal of Computer Vision.

[56]  Christian Petersohn.  Fraunhofer HHI at TRECVID 2004: Shot Boundary Detection System , 2004, TRECVID.

[57]  Milind R. Naphade.  On supervision and statistical learning for semantic multimedia analysis , 2004, J. Vis. Commun. Image Represent..

[58]  Dirk P. Kroese,et al.  The Cross Entropy Method: A Unified Approach To Combinatorial Optimization, Monte-carlo Simulation (Information Science and Statistics) , 2004 .

[59]  Marcel Worring,et al.  Multimodal Video Indexing : A Review of the State-ofthe-art , 2001 .

[60]  Leonidas J. Guibas,et al.  The Earth Mover's Distance as a Metric for Image Retrieval , 2000, International Journal of Computer Vision.

[61]  Bernt Schiele,et al.  Natural Scene Retrieval Based on a Semantic Modeling Step , 2004, CIVR.

[62]  Marcel Worring,et al.  The MediaMill TRECVID 2004 Semantic Viedo Search Engine , 2004, TRECVID.

[63]  Milind R. Naphade,et al.  Learning the semantics of multimedia queries and concepts from a small number of examples , 2005, MULTIMEDIA '05.

[64]  Marcel Worring,et al.  Multimedia event-based video indexing using time intervals , 2005, IEEE Transactions on Multimedia.

[65]  Christopher D. Manning,et al.  Incorporating Non-local Information into Information Extraction Systems by Gibbs Sampling , 2005, ACL.

[66]  Cordelia Schmid,et al.  A Comparison of Affine Region Detectors , 2005, International Journal of Computer Vision.

[67]  Cees G. M. Snoek,et al.  Early versus late fusion in semantic video analysis , 2005, MULTIMEDIA '05.

[68]  Antonio Torralba,et al.  Describing Visual Scenes using Transformed Dirichlet Processes , 2005, NIPS.

[69]  Cordelia Schmid,et al.  A performance evaluation of local descriptors , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[70]  Pietro Perona,et al.  A Bayesian hierarchical model for learning natural scene categories , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[71]  Djoerd Hiemstra,et al.  An Integrated Approach to Text and Image Retrieval- The Lowlands Team at Trecvid 2005 , 2005, TRECVID.

[72]  G. P. Nguyen,et al.  The MediaMill TRECVID 2005 Semantic Video Search Engine (Draft Version). , 2005 .

[73]  Joost van de Weijer,et al.  Edge and corner detection by photometric quasi-invariants , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[74]  Frédéric Jurie,et al.  Creating efficient codebooks for visual recognition , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[75]  Marcel Worring,et al.  User transparent parallel processing of the 2004 NIST TRECVID data set , 2005, 19th IEEE International Parallel and Distributed Processing Symposium.

[76]  Arnold W. M. Smeulders,et al.  Color texture measurement and segmentation , 2005, Signal Process..

[77]  B. Huurnink.  Autoseek towards a Fully Automated Video Search System Acknowledgements , 2005 .

[78]  Luc Van Gool,et al.  Modeling scenes with local descriptors and latent aspects , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[79]  G. P. Nguyen,et al.  Similarity Based Visualization of Image Collections , 2005 .

[80]  Marcel Worring,et al.  On the surplus value of semantic video analysis beyond the key frame , 2005, 2005 IEEE International Conference on Multimedia and Expo.

[81]  Joshua R. Smith,et al.  A Web-based System for Collaborative Annotation of Large Image and Video Collections , 2005 .

[82]  Joost van de Weijer,et al.  Boosting saliency in color image features , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[83]  Shih-Fu Chang,et al.  Visual Cue Cluster Construction via Information Bottleneck Principle and Kernel Density Estimation , 2005, CIVR.

[84]  Arnold W. M. Smeulders,et al.  c ○ 2005 Springer Science + Business Media, Inc. Manufactured in The Netherlands. A Six-Stimulus Theory for Stochastic Texture , 2002 .

[85]  Marcel Worring,et al.  Learning rich semantics from news video archives by style analysis , 2006, TOMCCAP.

[86]  Paul Over,et al.  Evaluation campaigns and TRECVid , 2006, MIR '06.

[87]  Jan-Mark Geusebroek,et al.  Compact Object Descriptors from Local Colour Invariant Histograms , 2006, BMVC.

[88]  Cordelia Schmid,et al.  Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study , 2006, CVPR Workshops.

[89]  Thorsten Joachims,et al.  Training linear SVMs in linear time , 2006, KDD '06.

[90]  Marcel Worring,et al.  The Semantic Pathfinder: Using an Authoring Metaphor for Generic Multimedia Indexing , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[91]  Lih-Yuan Deng,et al.  The Cross-Entropy Method: A Unified Approach to Combinatorial Optimization, Monte-Carlo Simulation, and Machine Learning , 2006, Technometrics.

[92]  Cor J. Veenman,et al.  Robust Scene Categorization by Learning Image Statistics in Context , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[93]  Marcel Worring,et al.  The challenge problem for automated detection of 101 semantic concepts in multimedia , 2006, MM '06.

[94]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[95]  John R. Smith,et al.  Large-scale concept ontology for multimedia , 2006, IEEE MultiMedia.

[96]  Marcel Worring,et al.  Browsing News Video using Semantic Threads , 2006 .

[97]  Gunnar Rätsch,et al.  Large Scale Multiple Kernel Learning , 2006, J. Mach. Learn. Res..

[98]  Cordelia Schmid,et al.  Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[99]  Cor J. Veenman,et al.  The influence of cross-validation on video classification performance , 2006, MM '06.

[100]  Cordelia Schmid,et al.  Coloring Local Feature Extraction , 2006, ECCV.

[101]  K. V. D. Sande,et al.  Coloring Concept Detection in Video Using Interest Regions Coloring Concept Detection in Video Using Interest Regions Specialization: Multimedia and Intelligent Systems , 2007 .

[102]  Marcel Worring,et al.  Query on demand video browsing , 2007, ACM Multimedia.

[103]  Marcel Worring,et al.  A Learned Lexicon-Driven Paradigm for Interactive Video Retrieval , 2007, IEEE Transactions on Multimedia.

[104]  Marcel Worring,et al.  Multi Thread Video Browsing , 2007 .

[105]  Dong Wang,et al.  Video diver: generic video indexing with diverse features , 2007, MIR '07.

[106]  Sheng Tang,et al.  TRECVID 2007 High-Level Feature Extraction By MCG-ICT-CAS , 2007, TRECVID.

[107]  Maarten de Rijke,et al.  The value of stories for speech-based video search , 2007, CIVR '07.

[108]  Jiawei Han,et al.  Efficient Kernel Discriminant Analysis via Spectral Regression , 2007, Seventh IEEE International Conference on Data Mining (ICDM 2007).

[109]  Franciska de Jong,et al.  Annotation of Heterogeneous Multimedia Content Using Automatic Speech Recognition , 2007, SAMT.

[110]  Hsuan-Tien Lin,et al.  A note on Platt’s probabilistic outputs for support vector machines , 2007, Machine Learning.

[111]  Xie Kanglin.  Lucene Search Engine , 2007 .

[112]  Maarten de Rijke,et al.  Exploiting redundancy in cross-channel video retrieval , 2007, MIR '07.

[113]  Marcel Worring,et al.  Adding Semantics to Detectors for Video Retrieval , 2007, IEEE Transactions on Multimedia.

[114]  Cordelia Schmid,et al.  Learning Object Representations for Visual Object Class Recognition , 2007, ICCV 2007.

[115]  Marcel Worring,et al.  Balancing thread based navigation for targeted video search , 2008, CIVR '08.

[116]  M. de Rijke,et al.  UvA-DARE ( Digital Academic Repository ) The MediaMill TRECVID 2008 semantic video search engine , 2008 .

[117]  Apostol Natsev,et al.  Web-based information content and its application to concept-based video retrieval , 2008, CIVR '08.

[118]  Jieping Ye,et al.  Multi-class Discriminant Kernel Learning via Convex Programming , 2008, J. Mach. Learn. Res..

[119]  Meng Wang,et al.  MSRA atT TRECVID 2008: High-Level Feature Extraction and Automatic Search , 2008, TRECVID.

[120]  Stéphane Ayache,et al.  Video Corpus Annotation Using Active Learning , 2008, ECIR.

[121]  Subhransu Maji,et al.  Classification using intersection kernel support vector machines is efficient , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[122]  Koen E. A. van de Sande,et al.  Evaluation of color descriptors for object and scene recognition , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[123]  Andrew Zisserman,et al.  Efficient Visual Search for Objects in Videos , 2008, Proceedings of the IEEE.

[124]  Cor J. Veenman,et al.  Kernel Codebooks for Scene Categorization , 2008, ECCV.

[125]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[126]  Katja Hofmann,et al.  Assessing concept selection for video retrieval , 2008, MIR '08.

引用
Ensemble Learning with LDA Topic Models for Visual Concept Detection
2012
A Multimodal Scheme for Program Segmentation and Representation in Broadcast Video Streams
IEEE Transactions on Multimedia
2008
Smart Video Browsing with Augmented Navigation Bars
MMM
2013
Semantic concept-based query expansion and re-ranking for multimedia retrieval
ACM Multimedia
2007
Fisher Kernel Temporal Variation-based Relevance Feedback for video retrieval
Comput. Vis. Image Underst.
2016
Vocabulary Expansion Using Word Vectors for Video Semantic Indexing
ACM Multimedia
2015
A reranking approach for context-based concept fusion in video indexing and retrieval
CIVR '07
2007
n-gram Models for Video Semantic Indexing
ACM Multimedia
2014
A Selective Weighted Late Fusion for Visual Concept Recognition
ECCV Workshops
2012
Query by Example by Extracting Inductive Query Definitions Using Rough Set Theory
2012
Fusion in Computer Vision
Advances in Computer Vision and Pattern Recognition
2014
A Novel Method for Spoken Text Feature Extraction in Semantic Video Retrieval
PCM
2006
Covering the Space of Tilts. Application to Affine Invariant Image Comparison
SIAM J. Imaging Sci.
2018
A Fast and Accurate Video Semantic-Indexing System Using Fast MAP Adaptation and GMM Supervectors
IEEE Transactions on Multimedia
2012
Extreme video retrieval: joint maximization of human and computer performance
MM '06
2006
A System That Learns to Tag Videos by Watching Youtube
ICVS
2008
Video browsing interfaces and applications: a review
2010
Zhejiang University at TRECVID 2006
TRECVID
2006
PKU_ICST at TRECVID 2018: Instance Search Task
TRECVID
2013
Memory recall based video search: Finding videos you have seen before based on your memory
TOMCCAP
2014