相关论文
2008 - 2008 IEEE International Conference on Multimedia and Expo
A benchmarking system for multipath overlay multimedia streaming

The rapid growth of the Internet multimedia services brings new challenges to how multimedia streams can be delivered to the users over bandwidth-constraint networks. Different strategies that exploit multipath streaming in order to provide better utilization of the Internet resources have been proposed by the research community. However, there exists no metric that allows us to evaluate how close these strategies are to the optimal resource utilization. This paper proposes a static benchmarking system that models the best possible distribution of streams along multiple paths in an overlay network that is shared by several senders and receivers. We have tested it with several different network topologies, and present the test results in this paper.

2023 - International Journal of Modeling and Optimization
Smoke Detection with Ensemble Modeling

This research aims at investigating performance of the ensemble learning method. The ensemble learning brings together various weak learners to create strong learners. Based on this ensemble learning idea, we develop a model for an efficient smoke detection tool. The three schemes of ensemble learning are investigated including bagging, boosting, and stacking. The bagging ensemble algorithm studied in this research is Random Forest and the boosting algorithm is AdaBoost. The stacking ensemble adopts three algorithms, that are Random Forest, AdaBoost, and Logistic Regression. The other learning algorithms adopted for performance comparison include Support Vector Machine, Naïve Bayes, and Decision Tree. The smoke detection data contain 62,630 records and 15 features. The dataset has been separated into training set and test set with a ratio of 75:25. The experimental results reveal that AdaBoost outperforms other learning algorithms when applied to the specific smoke detection application domain.

2023 - Advances in Engineering Technology Research
AI-guided Multi-objective Predicting and Evaluating of SCC Based on Random Forest

Self-compacting concrete (SCC) has unique properties that make it a promising alternative to traditional concrete. However, its prediction and design remain challenging due to the complex interaction of multiple factors. Traditional methods are limited in scope, and often inaccurate. This study presents a multi-objective predicting and evaluating model for SCC using machine learning techniques, particularly random forest algorithm. The model predicts flowability, mechanical property, and durability using nine critical features. The dataset used in this study consisted of 376 samples, and the model achieved high accuracy for predicting all three performance indicators, with R2 values of 0.94 for compressive strength, 0.92 for slump flow, and 0.94 for rapid chloride permeability. The importance analysis results suggest that the weight of binder and sand are the two most critical factors that affect SCC properties. This approach provides a valuable tool for engineers and researchers in the field of concrete science and technology, improving the quality and durability of concrete structures.

2019 - International Journal of Research
Fake News Detection in Facebook Using Machine Learning

This Project comes up with the applications of Random Forest techniques for detecting the 'fake news', that is, misleading news stories that comes from the non-reputable sources. Only by building a model based on a count vectorizer (using word tallies) or a (Term Frequency Inverse Document Frequency) tfidf matrix, (word tallies relative to how often they’re used in other articles in your dataset) can only get you so far. But these models do not consider the important qualities like word ordering and context. It is very possible that two articles that are similar in their word count will be completely different in their meaning. The data science community has responded by taking actions against the problem. There is a Kaggle competition called as the “Fake News Challenge” and Facebook is employing AI to filter fake news stories out of users’ feeds. Combatting the fake news is a classic text classification project with a straight forward proposition. Is it possible for you to build a model that can differentiate between “Real “news and “Fake” news? So a proposed work on assembling a dataset of both fake and real news and employ a Random Forest classifier in order to create a model to classify an article into fake or real based on its words and phrases. The main objective is to detect the fake news, which is a classic text classification problem with a straight forward proposition. It is needed to build a model that can differentiate between “Real” news and “Fake” news.

2008 - 2008 10th International Symposium on Web Site Evolution
Using Semantic clustering to enhance the navigation structure of Web sites

This paper presents an automatic approach based on semantic clustering to enhance the navigation structure of Web sites. The approach extends the navigation structure of a Web site by introducing a set of links that enable the navigation from each page of the site to other pages showing similar or related content. The approach uses Latent Semantic Indexing to compute a dissimilarity measure between the pages of the site and a Graph-Theoretic clustering algorithm to group pages having similar or related content. The additional links connecting each page of the site to the others within the same cluster are dynamically injected into each page by using AJAX code. A prototype of a supporting tool and the results from a case study conducted to assess the feasibility of the approach are also presented.

2013 - TRECVID
The AXES submissions at TRECVID 2013

The AXES project participated in the interactive instance search task (INS), the semantic indexing task (SIN) the multimedia event recounting task (MER), and the multimedia event detection task (MED) for TRECVid 2013. Our interactive INS focused this year on using classifiers trained at query time with positive examples collected from external search engines. Participants in our INS experiments were carried out by students and researchers at Dublin City University. Our best INS runs performed on par with the top ranked INS runs in terms of P@10 and P@30, and around the median in terms of mAP. For SIN, MED and MER, we use systems based on state-of-the-art local low-level descriptors for motion, image, and sound, as well as high-level features to capture speech and text and the visual and audio stream respectively. The low-level descriptors were aggregated by means of Fisher vectors into high-dimensional video-level signatures, the high-level features are aggregated into bag-of-word histograms. Using these features we train linear classifiers, and use early and late-fusion to combine the different features. Our MED system achieved the best score of all submitted runs in the main track, as well as in the ad-hoc track. This paper describes in detail our INS, MER, and MED systems and the results and findings of our experiments.

2007 - ECIR
Classifier Fusion for SVM-Based Multimedia Semantic Indexing

Concept indexing in multimedia libraries is very useful for users searching and browsing but it is a very challenging research problem as well. Combining several modalities, features or concepts is one of the key issues for bridging the gap between signal and semantics. In this paper, we present three fusion schemes inspired from the classical early and late fusion schemes. First, we present a kernel-based fusion scheme which takes advantage of the kernel basis of classifiers such as SVMs. Second, we integrate a new normalization process into the early fusion scheme. Third, we present a contextual late fusion scheme to merge classification scores of several concepts. We conducted experiments in the framework of the official TRECVID'06 evaluation campaign and we obtained significant improvements with the proposed fusion schemes relatively to usual fusion schemes.

2008
Oxford TRECVID 2008 - Notebook paper

The Oxford/IIIT team participated in the high-level feature extraction and interactive search tasks. A vision only approach was used for both tasks, with no use of the text or audio information. For the high-level feature extraction task, we used two different approaches, both based on a combination of visual features. One used a SVM classifier using a linear combination of kernels, the other used a random forest classifier. For both methods, we trained all high-level features using publicly available annotations [24]. The advantage of the random forest classifier is the speed of training and testing. In addition, for thepeople feature, we took a more targeted approach. We used a real-time face detector and an upper body detector, in both cases running on every frame. One run C OXVGG 4 4 was submitted using only Random forest approach for all concepts except two people. It performed best on Dog and hand, and came over the median for all the classes except kitchen and airplane. In the interactive search task, our team came third overall with an mAP of 0.158. The system used was identical to last year with the only change being a source of accurate upper body detections.

1968
OREGON JUNCO FOODS IN CONIFEROUS FORESTS

A food analysis was made from the gizzard contents of 262 Oregon juncos (Junco oreganus) collected in western Oregon from 1954 through 1962. The average annual diet was about half seed and half insect material. Juncos ate the seeds of many plants and also some germinants (sprouting seeds, and seedlings with seed coat on the cotyledons); those of Douglas-fir (Pseudotsuga menziesii), blackberry and raspberry (Rubus spp.) and hawkweed (Hieracium albiflorum) were the most important. A great variety of insects was taken but ants (Formicidae), snout beetles (Curculionidae), ground beetles (Carabidae), and leafhoppers (Cicadellidae) comprised the greatest volume. Douglas-fir seeds and germinants were an important sought-after junco food averaging 12%. They represented a trace in seed failure years, 6% in light seed years, and 32% in moderate to heavy seed years. Hemlock (Tsuga spp.) averaged only 1% of the food, even though it was a consistent seed producer. Seeds of redcedar (Thuja plicata) were not taken. Destruction of Douglasfir seeds and germinants by juncos should be considered when evaluating factors that may hinder regeneration. The authors were Wildlife Research Biologists, Denver Wildlife Research Center, Bureau of Sport Fisheries and Wildlife, U. S. Department of Interior. Their present respective addresses are: Bureau of Sport Fisheries and Wildlife, P. 0. Box 1208, Bend, Oregon 97701; and Rocky Mountain Forest and Range Experiment Station, Forest Service, U. S. Department of Agriculture, P. 0. Box 3313, Laramie, Wyoming 82070. They would like to thank Melva C. Gashwiler for her assistance in collecting the juncos and recording field data. The work of Malcolm H. Zirges, Department of Fisheries and Wildlife student at Oregon State University, who helped to compile the data, is also appreciated. Walter G. Dahms and James W. Barrett. of the Pacific Northwest Forest and Range Experiment Station, and Ann H. Jones and Robert B. Finley, Jr., of the Denver Wildlife Research Center kindly reviewed and edited the manuscript.

2012 - ICCCI
Ant Colony Decision Forest Meta-ensemble

This paper is devoted to the study of an extension of Ant Colony Decision Tree (ACDT) approach to Random Forests (RF) --- an arisen meta-ensemble technique called Ant Colony Decision Forest (ACDF). To the best of our knowledge this is the first time that Ant Colony Optimization is being applied as an ensemble method in data mining tasks. Meta-ensemble ACDF as a hybrid RF and ACO based algorithm is evolved and experimentally shown high accuracy and good effectiveness of this technique motivate us to further development.

2006
Foraging, roosting and survival of Natterer's bats, Myotis nattereri, in a commercial coniferous plantation

I studied Natterer's bats in Tentsmuir Forest, a 9143-hectare commercial coniferous plantation on the NE coast of Fife, Scotland that has been planted predominantly with Scots and Corsican pine. Two maternity colonies of approximately 111 & 68 adult females regularly use bat boxes within the forest as summer and maternity roosts. The foraging ecology, roost dynamics, population structure and survival rates of the Natterer's bats present were determined in this study by radio tracking and banding. The two colonies occupied home ranges of 4.43 & 6.46 km with densities of approximately 25 & 10 adult females per km . Individual bats had a mean foraging home range of 0.47 km that contained 1-3 core foraging areas, which did not overlap with the core areas of other individual bats. Adult female Natterer's bats preferentially foraged in stands of mature Corsican pines and around water bodies; grazing meadows and arable land adjacent to the forest were avoided. They also foraged extensively in mature Scots pine, the predominant habitat. However, it was underused relative to its availability. Out of a set of five different bat box types, the bats preferentially chose old square wooden and round wood crete boxes to use as summer and maternity roosts. I found that the bats also roosted in a specific type of natural cavity in double-Ieadered Corsican pines that has not been recorded before. Bats changed roost sites every 2.5 days on average.

2019 - Computer methods and programs in biomedicine
A comparative study on feature selection for a risk prediction model for colorectal cancer

BACKGROUND AND OBJECTIVE Risk prediction models aim at identifying people at higher risk of developing a target disease. Feature selection is particularly important to improve the prediction model performance avoiding overfitting and to identify the leading cancer risk (and protective) factors. Assessing the stability of feature selection/ranking algorithms becomes an important issue when the aim is to analyze the features with more prediction power. METHODS This work is focused on colorectal cancer, assessing several feature ranking algorithms in terms of performance for a set of risk prediction models (Neural Networks, Support Vector Machines (SVM), Logistic Regression, k-Nearest Neighbors and Boosted Trees). Additionally, their robustness is evaluated following a conventional approach with scalar stability metrics and a visual approach proposed in this work to study both similarity among feature ranking techniques as well as their individual stability. A comparative analysis is carried out between the most relevant features found out in this study and features provided by the experts according to the state-of-the-art knowledge. RESULTS The two best performance results in terms of Area Under the ROC Curve (AUC) are achieved with a SVM classifier using the top-41 features selected by the SVM wrapper approach (AUC=0.693) and Logistic Regression with the top-40 features selected by the Pearson (AUC=0.689). Experiments showed that performing feature selection contributes to classification performance with a 3.9% and 1.9% improvement in AUC for the SVM and Logistic Regression classifier, respectively, with respect to the results using the full feature set. The visual approach proposed in this work allows to see that the Neural Network-based wrapper ranking is the most unstable while the Random Forest is the most stable. CONCLUSIONS This study demonstrates that stability and model performance should be studied jointly as Random Forest turned out to be the most stable algorithm but outperformed by others in terms of model performance while SVM wrapper and the Pearson correlation coefficient are moderately stable while achieving good model performance.

2013 - Remote Sensing of Environment
Properties of Endogenous Post-Stratified Estimation using remote sensing data

article i nfo Endogenous post-stratification Forest inventory analysis Landsat ETM+ Random Forest Improved precision Post-stratification is commonly used to improve the precision of survey estimates. In traditional post- stratification methods, the stratification variable must be known at the population level. When suitable covari- ates are available at the population level, an alternative approach consists of fitting a model on the covariates, making predictions for the population and then stratifying on these predicted values. This method is called En- dogenous Post-Stratification Estimation (EPSE) and it is well suited for applications using remote sensing data. In this article, we investigate the performance of EPSE in a realistic setting using data from the United States For- est Service Forest Inventory Analysis and Landsat Enhanced Thematic Mapper Plus. This article has three specific objectives: first, to evaluate the statistical properties of EPSE when using linear regression, spline regression, and the machine learning tool Random Forest to predict tree canopy cover using remote sensing and Geographic In- formation System data; second, to investigate the effect on the EPSE variance estimator using estimated stratum boundaries instead of fixed stratum boundaries; and third, to investigate the effect on the EPSE variance estima- tor when optimizing the stratum boundaries to minimize the variance estimate. The main findings of this article are that the EPSE variance estimator performs well using Random Forests, but can underestimate the true vari- ance if an optimization isperformed on the stratum boundaries in an attempt to minimize the variance estimate. This result supports the use of the EPSE estimator using remote sensing data in cases where there is no optimi- zation on the variance estimator.

2011
Dynamic signal segmentation for activity recognition

Activity recognition is an essential task in many ambient assisted living applications. Activities are commonly recognized using data streams from onbody sensors such as accelerometers. An important subtask in activity recognition is signal segmentation: a procedure for dividing the data into intervals. These intervals are then used as instances for machine learning. We present a novel signal segmentation method, which utilizes a segmentation scheme based on dynamic signal partitioning. To validate the method, experimental results including 6 activities and 4 transitions between activities from 11 subjects are presented. Using a Random forest algorithm, an accuracy of 97.5% was achieved with dynamic signal segmentation method, 94.8% accuracy with non-overlapping and 95.3% with overlapping sliding window method.

2015 - 2015 IEEE Winter Conference on Applications of Computer Vision
Multi-shot Re-identification with Random-Projection-Based Random Forests

Human re-identification remains one of the fundamental, difficult problems in video surveillance and analysis. Current metric learning algorithms mainly focus on finding an optimized vector space such that observations of the same person in this space have a smaller distance than observations of two different people. In this paper, we propose a novel metric learning approach to the human reidentification problem, with an emphasis on the multi-shot scenario. First, we perform dimensionality reduction on image feature vectors through random projection. Next, a random forest is trained based on pair wise constraints in the projected subspace. This procedure repeats with a number of random projection bases, so that a series of random forests are trained in various feature subspaces. Finally, we select personalized random forests for each subject using their multi-shot appearances. We evaluate the performance of our algorithm on three benchmark datasets.

2013 - 2013 IEEE 14th International Conference on Information Reuse & Integration (IRI)
Interpreting random forest models using a feature contribution method

Model interpretation is one of the key aspects of the model evaluation process. The explanation of the relationship between model variables and outputs is easy for statistical models, such as linear regressions, thanks to the availability of model parameters and their statistical significance. For “black box” models, such as random forest, this information is hidden inside the model structure. This work presents an approach for computing feature contributions for random forest classification models. It allows for the determination of the influence of each variable on the model prediction for an individual instance. Interpretation of feature contributions for two UCI benchmark datasets shows the potential of the proposed methodology. The robustness of results is demonstrated through an extensive analysis of feature contributions calculated for a large number of generated random forest models.

2004 - EMNLP
Random Forests in Language Modelin

In this paper, we explore the use of Random Forests (RFs) (Amit and Geman, 1997; Breiman, 2001) in language modeling, the problem of predicting the next word based on words already seen before. The goal in this work is to develop a new language modeling approach based on randomly grown Decision Trees (DTs) and apply it to automatic speech recognition. We study our RF approach in the context of -gram type language modeling. Unlike regular -gram language models, RF language models have the potential to generalize well to unseen data, even when a complicated history is used. We show that our RF language models are superior to regular -gram language models in reducing both the perplexity (PPL) and word error rate (WER) in a large vocabulary speech recognition system.

2014 - NeuroImage
Lesion segmentation from multimodal MRI using random forest following ischemic stroke

Understanding structure-function relationships in the brain after stroke is reliant not only on the accurate anatomical delineation of the focal ischemic lesion, but also on previous infarcts, remote changes and the presence of white matter hyperintensities. The robust definition of primary stroke boundaries and secondary brain lesions will have significant impact on investigation of brain-behavior relationships and lesion volume correlations with clinical measures after stroke. Here we present an automated approach to identify chronic ischemic infarcts in addition to other white matter pathologies, that may be used to aid the development of post-stroke management strategies. Our approach uses Bayesian-Markov Random Field (MRF) classification to segment probable lesion volumes present on fluid attenuated inversion recovery (FLAIR) MRI. Thereafter, a random forest classification of the information from multimodal (T1-weighted, T2-weighted, FLAIR, and apparent diffusion coefficient (ADC)) MRI images and other context-aware features (within the probable lesion areas) was used to extract areas with high likelihood of being classified as lesions. The final segmentation of the lesion was obtained by thresholding the random forest probabilistic maps. The accuracy of the automated lesion delineation method was assessed in a total of 36 patients (24 male, 12 female, mean age: 64.57±14.23yrs) at 3months after stroke onset and compared with manually segmented lesion volumes by an expert. Accuracy assessment of the automated lesion identification method was performed using the commonly used evaluation metrics. The mean sensitivity of segmentation was measured to be 0.53±0.13 with a mean positive predictive value of 0.75±0.18. The mean lesion volume difference was observed to be 32.32%±21.643% with a high Pearson's correlation of r=0.76 (p<0.0001). The lesion overlap accuracy was measured in terms of Dice similarity coefficient with a mean of 0.60±0.12, while the contour accuracy was observed with a mean surface distance of 3.06mm±3.17mm. The results signify that our method was successful in identifying most of the lesion areas in FLAIR with a low false positive rate.

2012
COMPARISON OF MACHINE LEARNING ALGORITHMS RANDOM FOREST, ARTIFICIAL NEURAL NETWORK AND SUPPORT VECTOR MACHINE TO MAXIMUM LIKELIHOOD FOR SUPERVISED CROP TYPE CLASSIFICATION

The classification and recognition of agricultural crop types is an important application of remote sensing. New machine learning algorithms have emerged in the last years, but so far, few studies only have compared their performance and usability. Therefore, we compared three different state-of-the-art machine learning classifiers, namely Support Vector Machine (SVM), Artificial Neural Network (ANN) and Random Forest (RF) as well as the traditional classification method Maximum Likelihood (ML) among each other. For this purpose we classified a dataset of more than 500 crop fields located in the Canadian Prairies with a stratified randomized sampling approach. Up to four multi-spectral RapidEye images from the 2009 growing season were used. We compared the mean overall classification accuracies as well as standard deviations. Furthermore, the classification accuracy of single crops was analysed. Support Vector Machine classifiers using radial basis function or polynomial kernels exhibited superior results to ANN and RF in terms of overall accuracy and robustness, while ML exhibited inferior accuracies and higher variability. Grassland exhibited the best results for early-season mono-temporal analysis. With a multi-temporal approach, the highest accuracies were achieved for Rapeseed and Field Peas. Other crops, such as Wheat, Flax and Lentils were also successfully classified. The user’s and producer’s accuracies were higher than 85 %.

2015 - Remote. Sens.
On the Importance of Training Data Sample Selection in Random Forest Image Classification: A Case Study in Peatland Ecosystem Mapping

Random Forest (RF) is a widely used algorithm for classification of remotely sensed data. Through a case study in peatland classification using LiDAR derivatives, we present an analysis of the effects of input data characteristics on RF classifications (including RF out-of-bag error, independent classification accuracy and class proportion error). Training data selection and specific input variables (i.e., image channels) have a large impact on the overall accuracy of the image classification. High-dimension datasets should be reduced so that only uncorrelated important variables are used in classifications. Despite the fact that RF is an ensemble approach, independent error assessments should be used to evaluate RF results, and iterative classifications are recommended to assess the stability of predicted classes. Results are also shown to be highly sensitive to the size of the training data set. In addition to being as large as possible, the training data sets used in RF classification should also be (a) randomly distributed or created in a manner that allows for the class proportions of the training data to be representative of actual class proportions in the landscape; and (b) should have minimal spatial autocorrelation to improve classification results and to mitigate inflated estimates of RF out-of-bag classification accuracy.

ITI-CERTH participation to TRECVID 2015

Yiannis Kompatsiaris
|
Anastasios Dimou
|
Vasileios Mezaris
|
Anastasia Moumtzidou
|
Stefanos Vrochidis
|
Nikolaos Gkalelis

Abstract:This paper provides an overview of the tasks submitted to TRECVID 2011 by ITI-CERTH. ITICERTH participated in the Known-item search (KIS) as well as in the Semantic Indexing (SIN) and the Event Detection in Internet Multimedia (MED) tasks. In the SIN task, techniques are developed, which combine motion information with existing well-performing descriptors such as SURF, Random Forests and Bag-of-Words for shot representation. In the MED task, the trained concept detectors of the SIN task are used to represent video sources with model vector sequences, then a dimensionality reduction method is used to derive a discriminant subspace for recognizing events, and, nally, SVMbased event classiers are used to detect the underlying video events. The KIS search task is performed by employing VERGE, which is an interactive retrieval application combining retrieval functionalities in various modalities and exploiting implicit user feedback.

参考文献

[1]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[2]  Yiannis Kompatsiaris,et al.  Video event recounting using mixture subclass discriminant analysis , 2013, 2013 IEEE International Conference on Image Processing.

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

[4]  Yiannis Kompatsiaris,et al.  Activity detection using Sequential Statistical Boundary Detection (SSBD) , 2016, Comput. Vis. Image Underst..

[5]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[6]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Yiannis Kompatsiaris,et al.  Mixture Subclass Discriminant Analysis , 2011, IEEE Signal Processing Letters.

[8]  Vasileios Mezaris,et al.  Video event detection using generalized subclass discriminant analysis and linear support vector machines , 2014, ICMR.

[9]  Ebroul Izquierdo,et al.  Knowledge Space of Semantic Inference for Automatic Annotation and retrieval of Multimedia Content - K-Space , 2006, SAMT.

[10]  Koen E. A. van de Sande,et al.  Evaluating Color Descriptors for Object and Scene Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[12]  Yiannis Kompatsiaris,et al.  Mixture Subclass Discriminant Analysis Link to Restricted Gaussian Model and Other Generalizations , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[13]  Zhi-Hua Zhou,et al.  ML-KNN: A lazy learning approach to multi-label learning , 2007, Pattern Recognit..

[14]  David Nistér,et al.  Scalable Recognition with a Vocabulary Tree , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[15]  Cordelia Schmid,et al.  Aggregating local descriptors into a compact image representation , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[16]  Hari Kalva,et al.  Accuracy and stability improvement of tomography video signatures , 2010, 2010 IEEE International Conference on Multimedia and Expo.

[17]  Christof Monz,et al.  The QMUL system description for IWSLT 2010 , 2010, IWSLT.

[18]  Antonin Guttman,et al.  R-trees: a dynamic index structure for spatial searching , 1984, SIGMOD '84.

[19]  Nicholas W. D. Evans,et al.  ALIZE/spkdet: a state-of-the-art open source software for speaker recognition , 2008, Odyssey.

[20]  Arnold W. M. Smeulders,et al.  Real-Time Visual Concept Classification , 2010, IEEE Transactions on Multimedia.

[21]  Ioannis Patras,et al.  A Study on the Use of a Binary Local Descriptor and Color Extensions of Local Descriptors for Video Concept Detection , 2015, MMM.

[22]  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).

[23]  Mannes Poel,et al.  Multimedia Semantic Syndication for Enhanced News Services (MESH) , 2006 .

[24]  George Karypis,et al.  A Comparison of Document Clustering Techniques , 2000 .

[25]  Yiannis Kompatsiaris,et al.  The COST292 experimental framework for TRECVID 2007 , 2007, TRECVID.

[26]  Ioannis Patras,et al.  Cascade of classifiers based on binary, non-binary and deep convolutional network descriptors for video concept detection , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[27]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[28]  Yiannis Kompatsiaris,et al.  Improving event detection using related videos and relevance degree support vector machines , 2013, MM '13.

[29]  Gerald Friedland,et al.  Acoustic super models for large scale video event detection , 2011, J-MRE '11.

[30]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[31]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[32]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[33]  Yiannis Kompatsiaris,et al.  Video Tomographs and a Base Detector Selection Strategy for Improving Large-Scale Video Concept Detection , 2014, IEEE Transactions on Circuits and Systems for Video Technology.

[34]  Thomas Hofmann,et al.  Probabilistic Latent Semantic Analysis , 1999, UAI.

[35]  Yiannis Kompatsiaris,et al.  Linear Subclass Support Vector Machines , 2012, IEEE Signal Processing Letters.

[36]  Cordelia Schmid,et al.  Aggregating Local Image Descriptors into Compact Codes , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  Yiannis Kompatsiaris,et al.  COST292 experimental framework for TRECVID2008 , 2008, TRECVID.

[38]  Jean-Luc Gauvain,et al.  Modeling northern and southern varieties of dutch for STT , 2009, INTERSPEECH.

[39]  Yiannis Kompatsiaris,et al.  High-level event detection system based on discriminant visual concepts , 2011, ICMR '11.

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

[41]  Tao Mei,et al.  Online video recommendation based on multimodal fusion and relevance feedback , 2007, CIVR '07.

[42]  Marcel Worring,et al.  MediaTable: Interactive Categorization of Multimedia Collections , 2010, IEEE Computer Graphics and Applications.

[43]  Siddharth Patwardhan,et al.  Incorporating Dictionary and Corpus Information into a Context Vector Measure of Semantic Relatednes , 2003 .

[44]  GeversTheo,et al.  Evaluating Color Descriptors for Object and Scene Recognition , 2010 .

[45]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

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

[47]  Thomas G. Dietterich.  Multiple Classifier Systems , 2000, Lecture Notes in Computer Science.

[48]  Yiannis Kompatsiaris,et al.  MESH participation to TRECVID2008 HLFE , 2008, TRECVID.

[49]  Yiannis Kompatsiaris,et al.  ITI-CERTH participation in TRECVID 2018 , 2017, TRECVID.

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

[51]  Michael G. Strintzis,et al.  A framework for the efficient segmentation of large-format color images , 2002, Proceedings. International Conference on Image Processing.

[52]  Yiannis Kompatsiaris,et al.  On the use of feature tracks for dynamic concept detection in video , 2010, 2010 IEEE International Conference on Image Processing.

[53]  Paul Over,et al.  High-level feature detection from video in TRECVid: a 5-year retrospective of achievements , 2009 .

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

[55]  Heikki Mannila,et al.  Random projection in dimensionality reduction: applications to image and text data , 2001, KDD '01.

[56]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[57]  Sergio Escalera,et al.  On the Decoding Process in Ternary Error-Correcting Output Codes , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[58]  Yiannis Kompatsiaris,et al.  High-level event detection in video exploiting discriminant concepts , 2011, 2011 9th International Workshop on Content-Based Multimedia Indexing (CBMI).

[59]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[60]  Sergio Escalera,et al.  Subclass Problem-Dependent Design for Error-Correcting Output Codes , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[61]  Georges Quénot,et al.  Re-ranking by local re-scoring for video indexing and retrieval , 2011, CIKM '11.

[62]  Yiannis Kompatsiaris,et al.  On the Use of Visual Soft Semantics for Video Temporal Decomposition to Scenes , 2010, 2010 IEEE Fourth International Conference on Semantic Computing.

[63]  Cordelia Schmid,et al.  Learning realistic human actions from movies , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[64]  Yiannis Kompatsiaris,et al.  Automatic event-based indexing of multimedia content using a joint content-event model , 2010, EiMM '10.

[65]  Ioannis Patras,et al.  Learning to detect video events from zero or very few video examples , 2015, Image Vis. Comput..

[66]  Yiannis Kompatsiaris,et al.  Gradual transition detection using color coherence and other criteria in a video shot meta-segmentation framework , 2008, 2008 15th IEEE International Conference on Image Processing.

[67]  Boon-Lock Yeo,et al.  Segmentation of Video by Clustering and Graph Analysis , 1998, Comput. Vis. Image Underst..

[68]  Michael G. Strintzis,et al.  Still Image Segmentation Tools For Object-Based Multimedia Applications , 2004, Int. J. Pattern Recognit. Artif. Intell..

[69]  Xudong Jiang,et al.  Eigenfeature Regularization and Extraction in Face Recognition , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[70]  Emily Gallup Fayen,et al.  Guidelines for the construction, format, and management of monolingual controlled vocabularies : A revision of ANSI/NISO Z39.19 for the 21st century , 2007 .

[71]  Cor J. Veenman,et al.  Visual Word Ambiguity , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[73]  Ioannis Patras,et al.  Local Features and a Two-Layer Stacking Architecture for Semantic Concept Detection in Video , 2015, IEEE Transactions on Emerging Topics in Computing.

[74]  Andrew Zisserman,et al.  Image Classification using Random Forests and Ferns , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[75]  G. McLachlan,et al.  The EM algorithm and extensions , 1996 .

[76]  Andrew Zisserman,et al.  The devil is in the details: an evaluation of recent feature encoding methods , 2011, BMVC.

[77]  I. Jolliffe.  Principal Component Analysis , 2002 .

[78]  Yiannis Kompatsiaris,et al.  ITI-CERTH participation to TRECVID 2009 HLFE and Search , 2009, TRECVID.

[79]  Aleix M. Martínez,et al.  Subclass discriminant analysis , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[80]  Gary R. Bradski,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.

[81]  Evgeniy Gabrilovich,et al.  Computing Semantic Relatedness Using Wikipedia-based Explicit Semantic Analysis , 2007, IJCAI.

[82]  Cordelia Schmid,et al.  Action recognition by dense trajectories , 2011, CVPR 2011.

[83]  Ioannis Patras,et al.  Ordering of Visual Descriptors in a Classifier Cascade Towards Improved Video Concept Detection , 2016, MMM.

[84]  Cordelia Schmid,et al.  Action Recognition with Improved Trajectories , 2013, 2013 IEEE International Conference on Computer Vision.

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

[86]  John R. Smith,et al.  Multimedia semantic indexing using model vectors , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[87]  Vasileios Mezaris,et al.  GPU Accelerated Generalised Subclass Discriminant Analysis for Event and Concept Detection in Video , 2015, ACM Multimedia.

[88]  Andrew Zisserman,et al.  Multiple queries for large scale specific object retrieval , 2012, BMVC.

[89]  Dennis Koelma,et al.  The MediaMill TRECVID 2008 Semantic Video Search Engine , 2008, TRECVID.

[90]  Yiannis Kompatsiaris,et al.  K-Space at TRECvid 2006 , 2006, TRECVID.

[91]  Georges Quénot,et al.  TRECVID 2015 - An Overview of the Goals, Tasks, Data, Evaluation Mechanisms and Metrics , 2011, TRECVID.

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

[93]  Yiannis Kompatsiaris,et al.  A Comparative Study on the Use of Multi-label Classification Techniques for Concept-Based Video Indexing and Annotation , 2014, MMM.

[94]  Paul W. Munro,et al.  Improving Committee Diagnosis with Resampling Techniques , 1995, NIPS.

[95]  Li Xu,et al.  Hierarchical Saliency Detection , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[96]  Yiannis Kompatsiaris,et al.  Temporal Video Segmentation to Scenes Using High-Level Audiovisual Features , 2011, IEEE Transactions on Circuits and Systems for Video Technology.

[97]  Fengxi Song,et al.  Feature Selection Based on Linear Discriminant Analysis , 2010, 2010 International Conference on Intelligent System Design and Engineering Application.

[98]  Gang Hua,et al.  Semantic Model Vectors for Complex Video Event Recognition , 2012, IEEE Transactions on Multimedia.

引用
Concise Preservation by combining Managed Forgetting and Contextualized Remembering Fact Sheet Project information Project description Digital
2013
Multimodal Fusion: Combining Visual and Textual Cues for Concept Detection in Video
Multimedia Data Mining and Analytics
2015
Large-scale video event classification using dynamic temporal pyramid matching of visual semantics
2013 IEEE International Conference on Image Processing
2013
ITI-CERTH participation in TRECVID 2018
TRECVID
2017
MULTISENSOR: Development of multimedia content integration technologies for journalism, media monitoring and international exporting decision support
2015 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)
2015
A multimedia interactive search engine based on graph-based and non-linear multimodal fusion
2016 14th International Workshop on Content-Based Multimedia Indexing (CBMI)
2016
Query and Keyframe Representations for Ad-hoc Video Search
ICMR
2017
VERGE: A Multimodal Interactive Video Search Engine
MMM
2015
VERGE: An Interactive Search Engine for Browsing Video Collections
MMM
2014
VERGE in VBS 2017
MMM
2017
Local Invariant Feature Tracks for high-level video feature extraction
11th International Workshop on Image Analysis for Multimedia Interactive Services WIAMIS 10
2010
Dual Encoding for Zero-Example Video Retrieval
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
2018
Hybrid Space Learning for Language-based Video Retrieval
ArXiv
2020
MULTISENSOR Mining and Understanding of multilinguaL contenT for Intelligent Sentiment Enriched coNtext and Social Oriented inteRpretation FP 7-610411 D 2 . 2 Basic techniques for speech recognition , text analysis and concept detection
2014
Tree-Augmented Cross-Modal Encoding for Complex-Query Video Retrieval
SIGIR
2020
The MULTISENSOR Project - Development of Multimedia Content Integration Technologies for Journalism, Media Monitoring and International Exporting Decision Support
MMDA@ECAI
2016
Event modelling and recognition in video
2013
SEA: Sentence Encoder Assembly for Video Retrieval by Textual Queries
IEEE Transactions on Multimedia
2020
Event-based media processing and analysis: A survey of the literature
Image Vis. Comput.
2016
Migration-Related Semantic Concepts for the Retrieval of Relevant Video Content
2020