22 results on '"SMEULDERS, ARNOLD"'
Search Results
2. Repetition Estimation.
- Author
-
Runia, Tom F. H., Snoek, Cees G. M., and Smeulders, Arnold W. M.
- Subjects
PERIODIC motion ,RELATIVE motion ,ANIMAL behavior ,DEEP learning ,URBAN ecology (Sociology) - Abstract
Visual repetition is ubiquitous in our world. It appears in human activity (sports, cooking), animal behavior (a bee's waggle dance), natural phenomena (leaves in the wind) and in urban environments (flashing lights). Estimating visual repetition from realistic video is challenging as periodic motion is rarely perfectly static and stationary. To better deal with realistic video, we elevate the static and stationary assumptions often made by existing work. Our spatiotemporal filtering approach, established on the theory of periodic motion, effectively handles a wide variety of appearances and requires no learning. Starting from motion in 3D we derive three periodic motion types by decomposition of the motion field into its fundamental components. In addition, three temporal motion continuities emerge from the field's temporal dynamics. For the 2D perception of 3D motion we consider the viewpoint relative to the motion; what follows are 18 cases of recurrent motion perception. To estimate repetition under all circumstances, our theory implies constructing a mixture of differential motion maps: F , ∇ F , ∇ · F and ∇ × F . We temporally convolve the motion maps with wavelet filters to estimate repetitive dynamics. Our method is able to spatially segment repetitive motion directly from the temporal filter responses densely computed over the motion maps. For experimental verification of our claims, we use our novel dataset for repetition estimation, better-reflecting reality with non-static and non-stationary repetitive motion. On the task of repetition counting, we obtain favorable results compared to a deep learning alternative. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
3. Déjà Vu:.
- Author
-
Pintea, Silvia L., van Gemert, Jan C., and Smeulders, Arnold W. M.
- Published
- 2014
- Full Text
- View/download PDF
4. Evaluating Multimedia Features and Fusion for Example-Based Event Detection.
- Author
-
Myers, Gregory K., Snoek, Cees G. M., Nevatia, Ramakant, Nallapati, Ramesh, van Hout, Julien, Pancoast, Stephanie, Sun, Chen, Habibian, Amirhossein, Koelma, Dennis C., van de Sande, Koen E. A., and Smeulders, Arnold W. M.
- Abstract
Multimedia event detection (MED) is a challenging problem because of the heterogeneous content and variable quality found in large collections of Internet videos. To study the value of multimedia features and fusion for representing and learning events from a set of example video clips, we created SESAME, a system for video SEarch with Speed and Accuracy for Multimedia Events. SESAME includes multiple bag-of-words event classifiers based on single data types: low-level visual, motion, and audio features; high-level semantic visual concepts; and automatic speech recognition (ASR). Event detection performance was evaluated for each event classifier. The performance of low-level visual and motion features was improved by the use of difference coding. The accuracy of the visual concepts was nearly as strong as that of the low-level visual features. Experiments with a number of fusion methods for combining the event detection scores from these classifiers revealed that simple fusion methods, such as arithmetic mean, perform as well as or better than other, more complex fusion methods. [ABSTRACT FROM AUTHOR]
- Published
- 2014
- Full Text
- View/download PDF
5. Local Alignments for Fine-Grained Categorization.
- Author
-
Gavves, Efstratios, Fernando, Basura, Snoek, Cees, Smeulders, Arnold, and Tuytelaars, Tinne
- Subjects
DETECTORS ,SOCIAL interaction ,PARAMETERIZATION ,IMAGE segmentation ,GEOMETRY - Abstract
The aim of this paper is fine-grained categorization without human interaction. Different from prior work, which relies on detectors for specific object parts, we propose to localize distinctive details by roughly aligning the objects using just the overall shape. Then, one may proceed to the classification by examining the corresponding regions of the alignments. More specifically, the alignments are used to transfer part annotations from training images to unseen images (supervised alignment), or to blindly yet consistently segment the object in a number of regions (unsupervised alignment). We further argue that for the distinction of sub-classes, distribution-based features like color Fisher vectors are better suited for describing localized appearance of fine-grained categories than popular matching oriented shape-sensitive features, like HOG. They allow capturing the subtle local differences between subclasses, while at the same time being robust to misalignments between distinctive details. We evaluate the local alignments on the CUB-2011 and on the Stanford Dogs datasets, composed of 200 and 120, visually very hard to distinguish bird and dog species. In our experiments we study and show the benefit of the color Fisher vector parameterization, the influence of the alignment partitioning, and the significance of object segmentation on fine-grained categorization. We, furthermore, show that by using object detectors as voters to generate object confidence saliency maps, we arrive at fully unsupervised, yet highly accurate fine-grained categorization. The proposed local alignments set a new state-of-the-art on both the fine-grained birds and dogs datasets, even without any human intervention. What is more, the local alignments reveal what appearance details are most decisive per fine-grained object category. [ABSTRACT FROM AUTHOR]
- Published
- 2015
- Full Text
- View/download PDF
6. Color Invariant SURF in Discriminative Object Tracking.
- Author
-
Chu, Dung Manh and Smeulders, Arnold W. M.
- Published
- 2012
- Full Text
- View/download PDF
7. Color Based Tracing in Real-Life Surveillance Data.
- Author
-
Metternich, Michael J., Worring, Marcel, and Smeulders, Arnold W. M.
- Abstract
For post incident investigation a complete reconstruction of an event is needed based on surveillance footage of the crime scene and surrounding areas. Reconstruction of the whereabouts of the people in the incident requires the ability to follow persons within a camera΄s field-of-view (tracking) and between different cameras (tracing). In constrained situations a combination of shape and color information is shown to be best at discriminating between persons. In this paper we focus on person tracing between uncalibrated cameras with non-overlapping field-of-view. In these situations standard image matching techniques perform badly due to large, uncontrolled variations in viewpoint, light source, background and shading. We show that in these unconstrained real-life situations, tracing results are very dependent on the appearance of the subject. [ABSTRACT FROM AUTHOR]
- Published
- 2010
- Full Text
- View/download PDF
8. The University of Amsterdam΄s Concept Detection System at ImageCLEF 2009.
- Author
-
van de Sande, Koen E. A., Gevers, Theo, and Smeulders, Arnold W. M.
- Abstract
Our group within the University of Amsterdam participated in the large-scale visual concept detection task of ImageCLEF 2009. Our experiments focus on increasing the robustness of the individual concept detectors based on the bag-of-words approach, and less on the hierarchical nature of the concept set used. To increase the robustness of individual concept detectors, our experiments emphasize in particular the role of visual sampling, the value of color invariant features, the influence of codebook construction, and the effectiveness of kernel-based learning parameters. The participation in ImageCLEF 2009 has been successful, resulting in the top ranking for the large-scale visual concept detection task in terms of both EER and AUC. For 40 out of 53 individual concepts, we obtain the best performance of all submissions to this task. For the hierarchical evaluation, which considers the whole hierarchy of concepts instead of single detectors, using the concept likelihoods estimated by our detectors directly works better than scaling these likelihoods based on the class priors. [ABSTRACT FROM AUTHOR]
- Published
- 2010
- Full Text
- View/download PDF
9. Kernel Codebooks for Scene Categorization.
- Author
-
van Gemert, Jan C., Geusebroek, Jan-Mark, Veenman, Cor J., and Smeulders, Arnold W. M.
- Abstract
This paper introduces a method for scene categorization by modeling ambiguity in the popular codebook approach. The codebook approach describes an image as a bag of discrete visual codewords, where the frequency distributions of these words are used for image categorization. There are two drawbacks to the traditional codebook model: codeword uncertainty and codeword plausibility. Both of these drawbacks stem from the hard assignment of visual features to a single codeword. We show that allowing a degree of ambiguity in assigning codewords improves categorization performance for three state-of-the-art datasets. [ABSTRACT FROM AUTHOR]
- Published
- 2008
- Full Text
- View/download PDF
10. Semantic Video Indexing.
- Author
-
Snoek, Cees G. M., Worring, Marcel, Geusebroek, Jan-Mark, Koelma, Dennis C., Seinstra, Frank J., and Smeulders, Arnold W. M.
- Abstract
Query-by-keyword is the paradigm on which machine-based text search is still based. Elaborating on the success of text-based search engines, query-by-keyword also gains momentum in multimedia retrieval. For multimedia archives it is hard to achieve access, however, when based on text alone. Multimodal indexing is essential for effective access to video archives. For the automatic detection of specific concepts, the state-of-the-art has produced sophisticated and specialized indexing methods. Other than their textual counterparts, generic methods for semantic indexing in multimedia are neither generally available, nor scalable in their computational needs, nor robust in their performance. As a consequence, semantic access to multimedia archives is still limited. Therefore, there is a case to be made for a new approach to semantic video indexing. [ABSTRACT FROM AUTHOR]
- Published
- 2007
- Full Text
- View/download PDF
11. Multimedia Analysis by Learning.
- Author
-
Hutchison, David, Kanade, Takeo, Kittler, Josef, Kleinberg, Jon M., Mattern, Friedemann, Mitchell, John C., Naor, Moni, Nierstrasz, Oscar, Rangan, C. Pandu, Steffen, Bernhard, Sudan, Madhu, Terzopoulos, Demetri, Tygar, Doug, Vardi, Moshe Y., Weikum, Gerhard, Sebe, Nicu, Yuncai Liu, Yueting Zhuang, Huang, Thomas S., and Smeulders, Arnold W. M.
- Abstract
In this presentation for the panel at MCAM07, I put forward the transition of modeling the world as was done on a large scale in computer vision before the year 2000, to the current situation where there have been considerable successes with multimedia analysis by learning from the world. We make a plead for the last type of learned features, modeling only the scene accidental conditions and learning the object or object class intrinsic properties. In this paper, in respect to contributions by many others, we illustrate the approach of learning features by papers from our lab at the University of Amsterdam. [ABSTRACT FROM AUTHOR]
- Published
- 2007
- Full Text
- View/download PDF
12. Learned Lexicon-Driven Interactive Video Retrieval.
- Author
-
Sundaram, Hari, Naphade, Milind, Smith, John R., Yong Rui, Cees Snoek, Worring, Marcel, Koelma, Dennis, and Smeulders, Arnold
- Abstract
We combine in this paper automatic learning of a large lexicon of semantic concepts with traditional video retrieval methods into a novel approach to narrow the semantic gap. The core of the proposed solution is formed by the automatic detection of an unprecedented lexicon of 101 concepts. From there, we explore the combination of query-by-concept, query-by-example, query-by-keyword, and user interaction into the MediaMill semantic video search engine. We evaluate the search engine against the 2005 NIST TRECVID video retrieval benchmark, using an international broadcast news archive of 85 hours. Top ranking results show that the lexicon-driven search engine is highly effective for interactive video retrieval. [ABSTRACT FROM AUTHOR]
- Published
- 2006
- Full Text
- View/download PDF
13. Fast Anisotropic Gauss Filtering.
- Author
-
Geusebroek, Jan-Mark, Smeulders, Arnold W. M., and van de Weijer, Joost
- Abstract
We derive the decomposition of the anisotropic Gaussian in a one dimensional Gauss filter in the x-direction followed by a one dimensional filter in a non-orthogonal direction ᵠ. So also the anisotropic Gaussian can be decomposed by dimension. This appears to be extremely efficient from a computing perspective. An implementation scheme for normal convolution and for recursive filtering is proposed. Also directed derivative filters are demonstrated. For the recursive implementation, filtering an 512 × 512 image is performed within 65 msec, independent of the standard deviations and orientation of the filter. Accuracy of the filters is still reasonable when compared to truncation error or recursive approximation error. The anisotropic Gaussian filtering method allows fast calculation of edge and ridge maps, with high spatial and angular accuracy. For tracking applications, the normal anisotropic convolution scheme is more advantageous, with applications in the detection of dashed lines in engineering drawings. The recursive implementation is more attractive in feature detection applications, for instance in affine invariant edge and ridge detection in computer vision. The proposed computational filtering method enables the practical applicability of orientation scale-space analysis. [ABSTRACT FROM AUTHOR]
- Published
- 2002
- Full Text
- View/download PDF
14. Evaluating multimedia features and fusion for example-based event detection.
- Author
-
Myers, Gregory, Nallapati, Ramesh, Hout, Julien, Pancoast, Stephanie, Nevatia, Ramakant, Sun, Chen, Habibian, Amirhossein, Koelma, Dennis, Sande, Koen, Smeulders, Arnold, and Snoek, Cees
- Subjects
DIGITAL media ,STREAMING video & television ,VIDEO excerpts ,PATTERN recognition systems ,SPEECH perception ,AUTOMATIC speech recognition - Abstract
Multimedia event detection (MED) is a challenging problem because of the heterogeneous content and variable quality found in large collections of Internet videos. To study the value of multimedia features and fusion for representing and learning events from a set of example video clips, we created SESAME, a system for video SEarch with Speed and Accuracy for Multimedia Events. SESAME includes multiple bag-of-words event classifiers based on single data types: low-level visual, motion, and audio features; high-level semantic visual concepts; and automatic speech recognition. Event detection performance was evaluated for each event classifier. The performance of low-level visual and motion features was improved by the use of difference coding. The accuracy of the visual concepts was nearly as strong as that of the low-level visual features. Experiments with a number of fusion methods for combining the event detection scores from these classifiers revealed that simple fusion methods, such as arithmetic mean, perform as well as or better than other, more complex fusion methods. SESAME's performance in the 2012 TRECVID MED evaluation was one of the best reported. [ABSTRACT FROM AUTHOR]
- Published
- 2014
- Full Text
- View/download PDF
15. Identifying distributed and overlapping clusters of hemodynamic synchrony in fMRI data sets.
- Author
-
Ghebreab, Sennay and Smeulders, Arnold W. M.
- Subjects
- *
DISTRIBUTED cognition , *HEMODYNAMICS , *MAGNETIC resonance imaging , *SIGNAL processing , *PRINCIPAL components analysis , *BRAIN function localization - Abstract
Natural sensory stimuli elicit complex brain responses that manifest in fMRI as widely distributed and overlapping clusters of hemodynamic responses. We propose a statistical signal processing method for finding synchronous hemodynamic activity that directly or transiently reflects information about the experimental condition. When applied to fMRI data, the method searches for voxels with activation patterns exhibiting high coherence and simultaneously high variance across brain scans. The crux of the method is functional principal component analysis (fPCA) of activation patterns stored in a two-dimensional data matrix, with rows and columns representing voxels and scans, respectively. Without external information, fPCA is performed directly on this data matrix. Otherwise, the data matrix is first transformed to highlight a specific source of variation, enabling fully or partially supervised fPCA with a single parameter determining the degree of supervision. We evaluated our method on a public benchmark of fMRI scans of subjects viewing natural movies. Our method turns out to be very suitable for flexibly uncovering distributed and overlapping hemodynamic patterns that distinguish well between experimental conditions or cognitive states. [ABSTRACT FROM AUTHOR]
- Published
- 2011
- Full Text
- View/download PDF
16. Robust Tracking Using Foreground-Background Texture Discrimination.
- Author
-
Nguyen, Hieu T. and Smeulders, Arnold W. M.
- Subjects
- *
COMPUTER vision , *IMAGE processing , *PATTERN recognition systems , *IMAGING systems , *LIGHTING - Abstract
This paper conceives of tracking as the developing distinction of a foreground against the background. In this manner, fast changes in the object or background appearance can be dealt with. When modelling the target alone (and not its distinction from the background), changes of lighting or changes of viewpoint can invalidate the internal target model. As the main contribution, we propose a new model for the detection of the target using foreground/background texture discrimination. The background is represented as a set of texture patterns. During tracking, the algorithm maintains a set of discriminant functions each distinguishing one pattern in the object region from background patterns in the neighborhood of the object. The idea is to train the foreground/background discrimination dynamically, that is while the tracking develops. In our case, the discriminant functions are efficiently trained online using a differential version of Linear Discriminant Analysis (LDA). Object detection is performed by maximizing the sum of all discriminant functions. The method employs two complementary sources of information: it searches for the image region similar to the target object, and simultaneously it seeks to avoid background patterns seen before. The detection result is therefore less sensitive to sudden changes in the appearance of the object than in methods relying solely on similarity to the target. The experiments show robust performance under severe changes of viewpoint or abrupt changes of lighting. [ABSTRACT FROM AUTHOR]
- Published
- 2006
- Full Text
- View/download PDF
17. A Six-Stimulus Theory for Stochastic Texture.
- Author
-
Geusenroek, Jan-Mark and Smeulders, Arnold W. M.
- Subjects
- *
IMAGE processing , *COLORIMETRY , *TEXTURE (Art) , *COLORIMETRIC analysis , *COMPUTER graphics , *IMAGE quality in imaging systems , *IMAGING systems , *COMPUTER vision - Abstract
We report a six-stimulus basis for stochastic texture perception. Fragmentation of the scene by a chaotic process causes the spatial scene statistics to conform to a Weibull-distribution. The parameters of the Weibull distribution characterize the spatial structure of uniform stochastic textures of many different origins completely. In this paper, we report the perceptual significance of the Weibull parameters. We demonstrate the parameters to be sensitive to orthogonal variations in the imaging conditions, specifically to the illumination conditions, camera magnification and resolving power, and the texture orientation. Apparently, the Weibull parameters form a six-stimulus basis for stochastic texture description. The results indicate that texture perception can be approached like the experimental science of colorimetry. [ABSTRACT FROM AUTHOR]
- Published
- 2005
- Full Text
- View/download PDF
18. The Amsterdam Library of Object Images.
- Author
-
Geusebroek, Jan-Mark, Burghouts, Gertjan J., and Smeulders, Arnold W.M.
- Subjects
IMAGING systems ,SENSORY stimulation ,THREE-dimensional imaging ,IMAGE processing ,PATTERN recognition systems ,COMPUTER vision - Abstract
We present the ALOI collection of 1,000 objects recorded under various imaging circumstances. In order to capture the sensory variation in object recordings, we systematically varied viewing angle, illumination angle, and illumination color for each object, and additionally captured wide-baseline stereo images. We recorded over a hundred images of each object, yielding a total of 110,250 images for the collection. These images are made publicly available for scientific research purposes. [ABSTRACT FROM AUTHOR]
- Published
- 2005
- Full Text
- View/download PDF
19. Filter Image Browsing: Interactive Image Retrieval by Using Database Overviews.
- Author
-
Vendrig, Jeroen, Worring, Marcl, and Smeulders, Arnold
- Abstract
Human-computer interaction is a decisive factor in effective content-based access to large image repositories. In current image retrieval systems the user refines his query by selecting example images from a relevance ranking. Since the top ranked images are all similar, user feedback often results in rearrangement of the presented images only. For better incorporation of user interaction in the retrieval process, we have developed the Filter Image Browsing method. It also uses feedback through image selection. However, it is based on differences between images rather than similarities. Filter Image Browsing presents overviews of relevant parts of the database to users. Through interaction users then zoom in on parts of the image collection. By repeatedly limiting the information space, the user quickly ends up with a small amount of relevant images. The method can easily be extended for the retrieval of multimedia objects. For evaluation of the Filter Image Browsing retrieval concept, a user simulation is applied to a pictorial database containing 10,000 images acquired from the World Wide Web by a search robot. The simulation incorporates uncertainty in the definition of the information need by users. Results show Filter Image Browsing outperforms plain interactive similarity ranking in required effort from the user. Also, the method produces predictable results for retrieval sessions, so that the user quickly knows if a successful session is possible at all. Furthermore, the simulations show the overview techniques are suited for applications such as hand-held devices where screen space is limited. [ABSTRACT FROM AUTHOR]
- Published
- 2001
- Full Text
- View/download PDF
20. A Minimum Cost Approach for Segmenting Networks of Lines.
- Author
-
Geusebroek, Jan-Mark, Smeulders, Arnold, and Geerts, Hugo
- Abstract
The extraction and interpretation of networks of lines from images yields important organizational information of the network under consideration. In this paper, a one-parameter algorithm for the extraction of line networks from images is presented. The parameter indicates the extracted saliency level from a hierarchical graph. Input for the algorithm is the domain specific knowledge of interconnection points. Graph morphological tools are used to extract the minimum cost graph which best segments the network. We give an extensive error analysis for the general case of line extraction. Our method is shown to be robust against gaps in lines, and against spurious vertices at lines, which we consider as the most prominent source of error in line detection. The method indicates detection confidence, thereby supporting error proof interpretation of the network functionality. The method is demonstrated to be applicable on a broad variety of line networks, including dashed lines. Hence, the proposed method yields a major step towards general line tracking algorithms. [ABSTRACT FROM AUTHOR]
- Published
- 2001
- Full Text
- View/download PDF
21. Content based internet access to paper documents.
- Author
-
Worring, Marcel and Smeulders, Arnold W.M.
- Abstract
When archives of paper documents are to be accessed via the Internet, the implicit hypertext structure of the original documents should be employed. In this paper we study the different hypertext structures one encounters in a document. Methods for analyzing paper documents to find these structures are presented. The structures also form the basis for the presentation of the content of the document to the user. Results are presented. [ABSTRACT FROM AUTHOR]
- Published
- 1999
- Full Text
- View/download PDF
22. Guest Editorial.
- Author
-
Smeulders, Arnold W.M., Huang, Thomas S., and Gevers, Theo
- Subjects
- *
INFORMATION retrieval , *IMAGE processing , *IMAGE retrieval , *COMPUTER vision , *INFORMATION services - Abstract
Focuses on the impact of the development in hardware, storage, connectivity and sensor technology to the introduction of large image repositories. Efficacy of man and machine interaction; Challenges of the computer vision in content-based retrieval; Citation of the essential components of image retrieval systems.
- Published
- 2004
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.