Cees Snoek

The June issue of IEEE Computer Magazine features an article by myself and Arnold Smeulders titled “Visual-Concept Search Solved?“, which is available for download here. Interpreting the visual signal that enters the brain is an amazingly complex task, deeply rooted in life experience. Approximately half the brain is engaged in assigning a meaning to the incoming image, starting with the categorization of all visual concepts in the scene. Nevertheless, during the past five years, the field of computer vision has made considerable progress. It has done so not on the basis of precise modeling of all encountered objects and scenes—that task would be too complex and exhaustive to execute—but on the basis of combining rich, sensory-invariant descriptions of all patches in the scene into semantic classes learned from a limited number of examples. Research has reached the point where one part of the community suggests visual search is practically solved and progress has only been incremental, while another part argues that current solutions are weak and generalize poorly. We’ve done an experiment to shed light on the issue. Contrary to the widespread belief that visual-search progress is incremental and detectors generalize poorly, our experiment shows that progress has doubled on both counts in just three years. These results suggest that machine understanding of images is within reach.

Credit: PhD comics.

Nikola Tesla, best known for his contributions to electromagnetism, might also be considered as one of the founding fathers of mobile multimedia. This can be concluded from an interview with the New York Times (pictured below), published in Popular Mechanics in 1909. It took a 100 years before his vision became reality, amazing.

Source: http://recombu.com/news/nikola-tesla-predicted-mobile-phones-in-1909_M11683.html

And another CIVR 2010 paper titled: Today’s and Tomorrow’s Retrieval Practice in the Audiovisual Archive by Bouke Huurnink, Cees Snoek, Maarten de Rijke, and Arnold Smeulders is also available online.

Content-based video retrieval is maturing to the point where it can be used in real-world retrieval practices. One such practice is the audiovisual archive, whose users increasingly require fine-grained access to broadcast television content. We investigate to what extent content-based video retrieval methods can improve search in the audiovisual archive. In particular, we propose an evaluation methodology tailored to the specific needs and circumstances of the audiovisual archive, which are typically missed by existing evaluation initiatives. We utilize logged searches and content purchases from an existing audiovisual archive to create realistic query sets and relevance judgments. To reflect the retrieval practice of both the archive and the video retrieval community as closely as possible, our experiments with three video search engines incorporate archive-created catalog entries as well as state-of-the-art multimedia content analysis results. We find that incorporating content-based video retrieval into the archive’s practice results in significant performance increases for shot retrieval and for retrieving entire television programs. Our experiments also indicate that individual content-based retrieval methods yield approximately equal performance gains. We conclude that the time has come for audiovisual archives to start accommodating content-based video retrieval methods into their daily practice.

The resources developed as part of the system evaluation methodology for users of the audiovisual archive are available from http://ilps.science.uva.nl/resources/avarchive

The CIVR 2010 paper entitled Unsupervised Multi-Feature Tag Relevance Learning for Social Image Retrieval by Xirong Li, Cees Snoek, and Marcel Worring is available online. The work extends upon our tag-relevance approach. Interpreting the relevance of a user-contributed tag with respect to the visual content of an image is an emerging problem in social image retrieval. In the literature this problem is tackled by analyzing the correlation between tags and images represented by specific visual features. Unfortunately, no single feature represents the visual content completely, e.g., global features are suitable for capturing the gist of scenes, while local features are better for depicting objects. To solve the problem of learning tag relevance given multiple features, we introduce in this paper two simple and effective methods: one is based on the classical Borda Count and the other is a method we name UniformTagger. Both methods combine the output of many tag relevance learners driven by diverse features in an unsupervised, rather than supervised, manner. Experiments on 3.5 million social-tagged images and two test sets verify our proposal. Using learned tag relevance as updated tag frequency for social image retrieval, both Borda Count and UniformTagger outperform retrieval without tag relevance learning and retrieval with single-feature tag relevance learning. Moreover, the two unsupervised methods are comparable to a state-of-the-art supervised alternative, but without the need of any training data.

A preprint of the paper Comparing Compact Codebooks for Visual Categorization by Jan van Gemert, Cor Veenman, Arnold Smeulders, Jan-Mark Geusebroek, and myself is available online now. In the face of current large-scale video libraries, the practical applicability of content-based indexing algorithms is constrained by their efficiency. To this end, this paper compares various visual-based concept categorization techniques for efficient large-scale video indexing. In visual categorization, the popular codebook model has shown excellent categorization performance. The codebook model represents continuous visual features by discrete prototypes predefined in a vocabulary. The vocabulary size has a major impact on categorization efficiency, where a more compact vocabulary is more efficient. However, smaller vocabularies typically score lower on classification performance than larger vocabularies. This paper compares four approaches to achieve a compact codebook vocabulary while retaining categorization performance. For these four methods, we investigate the trade-off between codebook compactness and categorization performance. We evaluate the methods on more than 200 hours of challenging video data with as many as 101 semantic concepts. The results allow us to create a taxonomy of the four methods based on their efficiency and categorization performance. The paper will appear in the forthcoming special issue on Image and Video Retrieval Evaluation of Computer Vision and Image Understanding.

A preprint of the paper Evaluating Color Descriptors for Object and Scene Recognition by Koen van de Sande, Theo Gevers, and myself is available online now. In this paper we study visual descriptors, which are an important prerequisite to access visual information on the level of objects and scene types. So far, intensity-based descriptors have been widely used for feature extraction at salient points. To increase illumination invariance and discriminative power, color descriptors have been proposed. Because many different descriptors exist, a structured overview is required of color invariant descriptors in the context of image category recognition. Therefore, this paper studies the invariance properties and the distinctiveness of color descriptors in a structured way. The analytical invariance properties of color descriptors are explored, using a taxonomy based on invariance properties with respect to photometric transformations, and tested experimentally using a dataset with known illumination conditions. In addition, the distinctiveness of color descriptors is assessed experimentally using two benchmarks, one from the image domain and one from the video domain. From the theoretical and experimental results, it can be derived that invariance to light intensity changes and light color changes affects category recognition. The results reveal further that, for light intensity shifts, the usefulness of invariance is category-specific. Overall, when choosing a single descriptor and no prior knowledge about the dataset and object and scene categories is available, the OpponentSIFT is recommended. Furthermore, a combined set of color descriptors outperforms intensity-based SIFT and improves category recognition by 8% on the PASCAL VOC 2007 and by 7% on the Mediamill Challenge. The paper appears in IEEE Transactions on Pattern Analysis and Machine Intelligence, the software is available on www.colordescriptors.com.

Sconto Prescrizione Di Farmaci. Farmacia Canadese Legale. Farmaci Più Economici Online. È Possibile Ottenere Prezzi Accessibili All’interno Della Farmacia Da Casa Tua Qui their explanation Apertamente! Con Uno Sconto Meraviglioso. Ordina Rapidamente La Spedizione E La Consegna Se Hai Pagato Con Carta Di Credito.

The paper on Concept-Based Video Retrieval by myself and Marcel Worring has appeared in Foundations and Trends® in Information Retrieval. In this paper, we review 300 references on video retrieval, indicating when text-only solutions are unsatisfactory and showing the promising alternatives which are in majority concept-based. Therefore, central to our discussion is the notion of a semantic concept: an objective linguistic description of an observable entity. Specifically, we present our view on how its automated detection, selection under uncertainty, and interactive usage might solve the major scientific problem for video retrieval: the semantic gap. To bridge the gap, we lay down the anatomy of a concept-based video search engine. We present a component-wise decomposition of such an interdisciplinary multimedia system, covering influences from information retrieval, computer vision, machine learning, and human-computer interaction. For each of the components we review state-of-the-art solutions in the literature, each having different characteristics and merits. Because of these differences, we cannot understand the progress in video retrieval without serious evaluation efforts such as carried out in the NIST TRECVID benchmark. We discuss its data, tasks, results, and the many derived community initiatives in creating annotations and baselines for repeatable experiments. We conclude with our perspective on future challenges and opportunities. The paper is available for download now.

Livraison Dans Le Monde Entier. Pharmacie Sur Internet. Anonymat Complet. Vous Pourriez Devenir Vrai à Marseille Depuis Votre Résidence En Dessous De hop over to here Ouvertement. Et Bénéficiez D’une Livraison Totalement Gratuite. Où Trouver La Meilleure Offre, Demandez-vous, Je Me Contente Des Tarifs De Ce Détaillant Et Je Vous Recommande.

Although the Mexican flu can still influence the final conference dates, the forhtcoming paper for ICME 2009 in Cancun by Arjan Setz and myself, entitled “Can Social Tagged Images Aid Concept-Based Video Search?” is available online now. This paper seeks to unravel whether commonly available social tagged images can be exploited as a training resource for concept-based video search. Since social tags are known to be ambiguous, overly personalized, and often error prone, we place special emphasis on the role of disambiguation. We present a systematic experimental study that evaluates concept detectors based on social tagged images, and their disambiguated versions, in three application scenarios: within-domain, cross-domain, and together with an interacting user. The results indicate that social tagged images can aid concept-based video search indeed, especially after disambiguation and when used in an interactive video retrieval setting. These results open-up interesting avenues for future research.