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.

Supporting the shared experience of spectators through mobile group media

Abstract: Interesting characteristics of large-scale events are their spatial distribution, their extended duration over days, and the fact that they are set apart from daily life. The increasing pervasiveness of computational media encourages us to investigate such unexplored domains, especially when thinking of applications for spectator groups. Here we report of a field study on two groups of rally spectators who were equipped with multimedia phones, and we present a novel mobile group media application called mGroup that supports groups in creating and sharing experiences. Particularly, we look at the possibilities of and boundary conditions for computer applications posed by our findings on group identity and formation, group awareness and coordination, the meaningful construction of an event experience and its grounding in the event context, the shared context and discourses, protagonism and active spectatorship. Moreover, we aim at providing a new perspective on spectatorship at large scale events, which can make research and development more aware of the socio-cultural dimension.

GANSpace: Discovering Interpretable GAN Controls

Abstract: This paper describes a simple technique to analyze Generative Adversarial Networks (GANs) and create interpretable controls for image synthesis, such as change of viewpoint, aging, lighting, and time of day. We identify important latent directions based on Principal Components Analysis (PCA) applied either in latent space or feature space. Then, we show that a large number of interpretable controls can be defined by layer-wise perturbation along the principal directions. Moreover, we show that BigGAN can be controlled with layer-wise inputs in a StyleGAN-like manner. We show results on different GANs trained on various datasets, and demonstrate good qualitative matches to edit directions found through earlier supervised approaches.

Can eyes reveal interest? Implicit queries from gaze patterns

Abstract: We study a new research problem, where an implicit information retrieval query is inferred from eye movements measured when the user is reading, and used to retrieve new documents. In the training phase, the user's interest is known, and we learn a mapping from how the user looks at a term to the role of the term in the implicit query. Assuming the mapping is universal, that is, the same for all queries in a given domain, we can use it to construct queries even for new topics for which no learning data is available. We constructed a controlled experimental setting to show that when the system has no prior information as to what the user is searching, the eye movements help significantly in the search. This is the case in a proactive search, for instance, where the system monitors the reading behaviour of the user in a new topic. In contrast, during a search or reading session where the set of inspected documents is biased towards being relevant, a stronger strategy is to search for content-wise similar documents than to use the eye movements.

Combining Topic Models and Social Networks for Chat Data Mining

Abstract: Informal chat-room conversations have intrinsically different properties from regular static document collections. Noise, concise expressions and dynamic, changing and interleaving nature of discussions make chat data ill-suited for analysis with an off-the-shelf text mining method. On the other hand, interactive human communication has some implicit features which may be used to enhance the results. In our research we infer social network structures from the chat data by using a few basic heuristics. We then present some preliminary results showing that the inferred social graph may be used to enhance topic identification of a chat room when combined with a state-of-the-art topic and classification models. For validation purposes we then compare the performance effects of using this social information in a topic classification task.

Scalable Optimization of Neighbor Embedding for Visualization

Abstract: Neighbor embedding (NE) methods have found their use in data visualization but are limited in big data analysis tasks due to their O(n2) complexity for n data samples. We demonstrate that the obvious approach of subsampling produces inferior results and propose a generic approximated optimization technique that reduces the NE optimization cost to O(n log n). The technique is based on realizing that in visualization the embedding space is necessarily very low-dimensional (2D or 3D), and hence efficient approximations developed for n-body force calculations can be applied. In gradient-based NE algorithms the gradient for an individual point decomposes into "forces" exerted by the other points. The contributions of close-by points need to be computed individually but far-away points can be approximated by their "center of mass", rapidly computable by applying a recursive decomposition of the visualization space into quadrants. The new algorithm brings a significant speed-up for medium-size data, and brings "big data" within reach of visualization.