We propose to model relative attributes that capture the relationships between images and objects in terms of human-nameable visual properties. For example, the models can capture that animal A is 'furrier' than animal B, or image X is 'brighter' than image B. Given training data stating how object/scene categories relate according to different attributes, we learn a ranking function per attribute. The learned ranking functions predict the relative strength of each property in novel images. We show how these relative attribute predictions enable a variety of novel applications, including zero-shot learning from relative comparisons, automatic image description, image search with interactive feedback, and active learning of discriminative classifiers. We overview results demonstrating these applications with images of faces and natural scenes. Overall, we find that relative attributes enhance the precision of communication between humans and computer vision algorithms, providing the richer language needed to fluidly "teach" a system about visual concepts.

Constraint programming has become an important technology for solving hard combinatorial problems in a diverse range of application domains. It has its roots in artificial intelligence, mathematical programming, op- erations research, and programming languages. This paper gives a perspective on where constraint programming is today, and discusses a number of opportunities and challenges that could provide focus for the research community into the future.

Complexity of voting manipulation is a prominent research topic in computational social choice. The voting manipulation literature usually assumes that the manipulator is only concerned with improving the outcome of the election from her perspective. However, in practice, the manipulator may also be reluctant to lie, i.e., she may have a preference for submitting a vote that does not deviate too much from her true ranking of the candidates. In this paper, we study the complexity of finding a manipulative vote that achieves the manipulator's goal yet is as close as possible to her true preference order. We analyze this problem for three natural notions of closeness, namely, swap distance, footrule distance, and maximum displacement distance, and a variety of voting rules, such as scoring rules, Bucklin, Copeland, and Maximin. For all three distances, we obtain polynomial-time algorithms for all scoring rules and Bucklin and hardness results for Copeland and Maximin.

A central component in many applications is the underlying data management layer. In Data-Web applications, the central component of this layer is the triple store. It is thus evident that finding the most adequate store for the application to develop is of crucial importance for individual projects as well as for data integration on the Data Web in general. In this paper, we propose a generic benchmark creation procedure for SPARQL, which we apply to the DBpedia knowledge base. In contrast to previous approaches, our benchmark is based on queries that were actually issued by humans and applications against existing RDF data not resembling a relational schema. In addition, our approach does not only take the query string but also the features of the queries into consideration during the benchmark generation process. Our generic procedure for benchmark creation is based on query-log mining, SPARQL feature analysis and clustering. After presenting the method underlying our benchmark generation algorithm, we use the generated benchmark to compare the popular triple store implementations Virtuoso, Sesame, Jena-TDB, and BigOWLIM.

I provide a personal view of some of the major research challenges in the area of combinatorial search. These include solving and playing games with chance, hidden information, and multiple players, optimally solving larger instances of well-known single-agent toy problems, applying search techniques to more realistic problem domains, analyzing the time complexity of heuristic search algorithms, and capitalizing on advances in computing hardware, such as very large external memories and multi-core processors.

The currently dominant approach to domain-independent planning is planning as heuristic search, with most successful planning heuristics being based on solutions to delete-relaxed versions of planning problems, in which the negative effects of actions are ignored. We introduce a principled, flexible, and practical technique for augmenting delete-relaxed tasks with a limited amount of delete information, by introducing special fluents that explicitly represent conjunctions of fluents in the original planning task. Differently from previous work, conditional effects are used to limit the growth of the task to be linear in the number of such conjunctions, making its use for obtaining heuristic functions feasible. The resulting heuristics are empirically evaluated, and shown to be some- times much more informative than standard delete-relaxation heuristics.

This paper provides a broad overview of the situation in the area of Parallel Search with a specific focus on Parallel SAT Solving. A set of challenges to researchers is presented which, we believe, must be met to ensure the practical applicability of Parallel SAT Solvers in the future. All these challenges are described informally, but put into perspective with related research results, and a (subjective) grading of difficulty for each of them is provided.

Goal recognition in digital games involves inferring players’ goals from observed sequences of low-level player actions. Goal recognition models support player-adaptive digital games, which dynamically augment game events in response to player choices for a range of applications, including entertainment, training, and education. However, digital games pose significant challenges for goal recognition, such as exploratory actions and ill-defined goals. This paper presents a goal recognition framework based on Markov logic networks (MLNs). The model’s parameters are directly learned from a corpus that was collected from player interactions with a non-linear educational game. An empirical evaluation demonstrates that the MLN goal recognition framework accurately predicts players’ goals in a game environment with exploratory actions and ill-defined goals.

The multiagent systems community has adopted game theory as a framework for the design of systems of multiple self-interested agents. For this to be effective, efficient algorithms must be designed to compute the solutions that game theory prescribes. In this paper, I summarize some of the state of the art on this topic, focusing particularly on how this line of work has contributed to several highly visible deployed security applications, developed at the University of Southern California.

Hybrid automata networks (HAN) are a powerful formalism to model complex embedded systems. In this paper, we survey the recent advances in the application of Satisfiability Modulo Theories (SMT) to the analysis of HAN. SMT can be seen as an extended form of Boolean satisfiability (SAT), where literals are interpreted with respect to a background theory (e.g. linear arithmetic). HAN can be symbolically represented by means of SMT formulae, and analyzed by generalizing to the case of SMT the traditional model checking algorithms based on SAT.