Helsinki Institute for Information Technology

About: Helsinki Institute for Information Technology is a facility organization based out in Espoo, Finland. It is known for research contribution in the topics: Population & Bayesian network. The organization has 630 authors who have published 1962 publications receiving 63426 citations.

Focused multi-task learning in a Gaussian process framework

Abstract: Multi-task learning, learning of a set of tasks together, can improve performance in the individual learning tasks. Gaussian process models have been applied to learning a set of tasks on different data sets, by constructing joint priors for functions underlying the tasks. In these previous Gaussian process models, the setting has been symmetric in the sense that all the tasks have been assumed to be equally important, whereas in settings such as transfer learning the goal is asymmetric, to enhance performance in a target task given the other tasks. We propose a focused Gaussian process model which introduces an "explaining away" model for each of the additional tasks to model their non-related variation, in order to focus the transfer to the task-of-interest. This focusing helps reduce the key problem of negative transfer, which may cause performance to even decrease if the tasks are not related closely enough. In experiments, our model improves performance compared to single-task learning, symmetric multi-task learning using hierarchical Dirichlet processes, transfer learning based on predictive structure learning, and symmetric multi-task learning with Gaussian processes.

Syxaw: Data Synchronization Middleware for the Mobile Web

Abstract: In this paper, we present a middleware for synchronization of opaque and structured data in a mobile and resource-constrained environment. The presented Syxaw (Synchronizer with XML-awareness) system distinguishes itself from related proposals in that it interoperates transparently with resources on the World Wide Web, and by exhibiting a model of synchronization that is both easy to understand and well suited for weak devices in a mobile and ubiquitous environment. We demonstrate the feasibility of the proposed system by considering several usage scenarios, including working on the Web and collaborative XML editing. We consider system performance on a mobile wireless device, and examine the impact of different optimization techniques to the performance. According to our analysis, Web interoperability suggests that the data share model be kept simple and conservative, and that moving functionality onto the client is advantageous. We find that the techniques of operation bundling and concurrent use of network downlink and uplink improve network utilization, but that achieving full bandwidth usage with a weak client is challenging in practice.

VSD2014: A dataset for violent scenes detection in hollywood movies and web videos

Abstract: In this paper, we introduce a violent scenes and violence-related concept detection dataset named VSD2014 It contains annotations as well as auditory and visual features of Hollywood movies and user-generated footage shared on the web The dataset is the result of a joint annotation endeavor of different research institutions and responds to the real-world use case of parental guidance in selecting appropriate content for children The dataset has been validated during the Violent Scenes Detection (VSD) task at the MediaEval benchmarking initiative for multimedia evaluation

Checksum gestures: continuous gestures as an out-of-band channel for secure pairing

Abstract: We propose the use of a single continuous gesture as a novel, intuitive, and efficient mechanism to authenticate a secure communication channel. Our approach builds on a novel algorithm for encoding (at least 20-bits) authentication information as a single continuous gesture, referred to as a checksum gesture. By asking the user to perform the generated gesture, a secure channel can be authenticated. Results from a controlled user experiment (N = 13 participants, 1022 trials) demonstrate the feasibility of our technique, showing over 90% success rate in establishing a secure communication channel despite relying on complex gesture patterns. The authentication times of our method are over three-folds faster than with previous gesture-based solutions. The average execution time of a gesture is 5:7 seconds in our study, which is comparable to the input time of conventional text input based PIN authentication. Our approach is particularly well-suited for scenarios involving wearable devices that lack conventional input capabilities, e.g., pairing a smartwatch with an interactive display.

Dense Subset Sum may be the hardest

Abstract: The SUBSET SUM problem asks whether a given set of n positive integers contains a subset of elements that sum up to a given target t. It is an outstanding open question whether the O^*(2^{n/2})-time algorithm for SUBSET SUM by Horowitz and Sahni [J. ACM 1974] can be beaten in the worst-case setting by a "truly faster", O^*(2^{(0.5-delta)*n})-time algorithm, with some constant delta > 0. Continuing an earlier work [STACS 2015], we study SUBSET SUM parameterized by the maximum bin size beta, defined as the largest number of subsets of the n input integers that yield the same sum. For every epsilon > 0 we give a truly faster algorithm for instances with beta = 2^{0.661n}. Consequently, we also obtain a characterization in terms of the popular density parameter n/log_2(t): if all instances of density at least 1.003 admit a truly faster algorithm, then so does every instance. This goes against the current intuition that instances of density 1 are the hardest, and therefore is a step toward answering the open question in the affirmative. Our results stem from a novel combinatorial analysis of mixings of earlier algorithms for SUBSET SUM and a study of an extremal question in additive combinatorics connected to the problem of Uniquely Decodable Code Pairs in information theory.