We present a system that produces sentential descriptions of video: who did what to whom, and where and how they did it. Action class is rendered as a verb, participant objects as noun phrases, properties of those objects as adjectival modifiers in those noun phrases, spatial relations between those participants as prepositional phrases, and characteristics of the event as prepositional-phrase adjuncts and adverbial modifiers. Extracting the information needed to render these linguistic entities requires an approach to event recognition that recovers object tracks, the track-to-role assignments, and changing body posture.

Novel research in the field of Linked Data focuses on the problem of entity summarization. This field addresses the problem of ranking features according to their importance for the task of identifying a particular entity. Next to a more human friendly presentation, these summarizations can play a central role for semantic search engines and semantic recommender systems. In current approaches, it has been tried to apply entity summarization based on patterns that are inherent to the regarded data. The proposed approach of this paper focuses on the movie domain. It utilizes usage data in order to support measuring the similarity between movie entities. Using this similarity it is possible to determine the k-nearest neighbors of an entity. This leads to the idea that features that entities share with their nearest neighbors can be considered as significant or important for these entities. Additionally, we introduce a downgrading factor (similar to TF-IDF) in order to overcome the high number of commonly occurring features. We exemplify the approach based on a movie-ratings dataset that has been linked to Freebase entities.

Logs of the interactions with a search engine show that users often reformulate their queries. Examining these reformulations shows that recommendations that precise the focus of a query are helpful, like those based on expansions of the original queries. But it also shows that queries that express some topical shift with respect to the original query can help user access more rapidly the information they need. We propose a method to identify from the query logs of past users queries that either focus or shift the initial query topic. This method combines various click-based, topic-based and session based ranking strategies and uses supervised learning in order to maximize the semantic similarities between the query and the recommendations, while at the same diversifying them. We evaluate our method using the query/click logs of a Japanese web search engine and we show that the combination of the three methods proposed is significantly better than any of them taken individually.

We present a framework that allows an observer to determine occluded portions of a structure by finding the maximum-likelihood estimate of those occluded portions consistent with visible image evidence and a consistency model. Doing this requires determining which portions of the structure are occluded in the first place. Since each process relies on the other, we determine a solution to both problems in tandem. We extend our framework to determine confidence of one's assessment of which portions of an observed structure are occluded, and the estimate of that occluded structure, by determining the sensitivity of one's assessment to potential new observations. We further extend our framework to determine a robotic action whose execution would allow a new observation that would maximally increase one's confidence.

The common internal structure and algorithmic organization of object detection, detection-based tracking, and event recognition facilitates a general approach to integrating these three components. This supports multidirectional information flow between these components allowing object detection to influence tracking and event recognition and event recognition to influence tracking and object detection. The performance of the combination can exceed the performance of the components in isolation. This can be done with linear asymptotic complexity.

In information retrieval, a fundamental goal is to transform a document into concepts that are representative of its content. The term "representative" is in itself challenging to define, and various tasks require different granularities of concepts. In this paper, we aim to model concepts that are sparse over the vocabulary, and that flexibly adapt their content based on other relevant semantic information such as textual structure or associated image features. We explore a Bayesian nonparametric model based on nested beta processes that allows for inferring an unknown number of strictly sparse concepts. The resulting model provides an inherently different representation of concepts than a standard LDA (or HDP) based topic model, and allows for direct incorporation of semantic features. We demonstrate the utility of this representation on multilingual blog data and the Congressional Record.

Nonnegative matrix factorization (NMF) has become a very popular technique in machine learning because it automatically extracts meaningful features through a sparse and part-based representation. However, NMF has the drawback of being highly ill-posed, that is, there typically exist many different but equivalent factorizations. In this paper, we introduce a completely new way to obtaining more well-posed NMF problems whose solutions are sparser. Our technique is based on the preprocessing of the nonnegative input data matrix, and relies on the theory of M-matrices and the geometric interpretation of NMF. This approach provably leads to optimal and sparse solutions under the separability assumption of Donoho and Stodden (NIPS, 2003), and, for rank-three matrices, makes the number of exact factorizations finite. We illustrate the effectiveness of our technique on several image datasets.

The bioinformatical methods to detect lateral gene transfer events are mainly based on functional coding DNA characteristics. In this paper, we propose the use of DNA traits not depending on protein coding requirements. We introduce several semilocal variables that depend on DNA primary sequence and that reflect thermodynamic as well as physico-chemical magnitudes that are able to tell apart the genome of different organisms. After combining these variables in a neural classificator, we obtain results whose power of resolution go as far as to detect the exchange of genomic material between bacteria that are phylogenetically close.

In general Evolutionary Computation (EC) includes a number of optimization methods inspired by biological mechanisms of evolution. The methods catalogued in this area use the Darwinian principles of life evolution to produce algorithms that returns high quality solutions to hard-to-solve optimization problems. The main strength of EC is precisely that they provide good solutions even if the computational resources (e.g., running time) are limited. Astronomy and Astrophysics are two fields that often require optimizing problems of high complexity or analyzing a huge amount of data and the so-called complete optimization methods are inherently limited by the size of the problem/data. For instance, reliable analysis of large amounts of data is central to modern astrophysics and astronomical sciences in general. EC techniques perform well where other optimization methods are inherently limited (as complete methods applied to NP-hard problems), and in the last ten years, numerous proposals have come up that apply with greater or lesser success methodologies of evolutional computation to common engineering problems. Some of these problems, such as the estimation of non-lineal parameters, the development of automatic learning techniques, the implementation of control systems, or the resolution of multi-objective optimization problems, have had (and have) a special repercussion in the fields. For these reasons EC emerges as a feasible alternative for traditional methods. In this paper, we discuss some promising applications in this direction and a number of recent works in this area; the paper also includes a general description of EC to provide a global perspective to the reader and gives some guidelines of application of EC techniques for future research

Many real-world phenomena can be represented by a spatio-temporal signal: where, when, and how much. Social media is a tantalizing data source for those who wish to monitor such signals. Unlike most prior work, we assume that the target phenomenon is known and we are given a method to count its occurrences in social media. However, counting is plagued by sample bias, incomplete data, and, paradoxically, data scarcity -- issues inadequately addressed by prior work. We formulate signal recovery as a Poisson point process estimation problem. We explicitly incorporate human population bias, time delays and spatial distortions, and spatio-temporal regularization into the model to address the noisy count issues. We present an efficient optimization algorithm and discuss its theoretical properties. We show that our model is more accurate than commonly-used baselines. Finally, we present a case study on wildlife roadkill monitoring, where our model produces qualitatively convincing results.