- document
-
Zhang, T. (author), Ali, Abdallah El (author), Chen, C. (author), Hanjalic, A. (author), Cesar, Pablo (author)Recognizing user emotions while they watch short-form videos anytime and anywhere is essential for facilitating video content customization and personalization. However, most works either classify a single emotion per video stimuli, or are restricted to static, desktop environments. To address this, we propose a correlation-based emotion...journal article 2020
- document
-
Zhan, X. (author), Hanjalic, A. (author), Wang, H. (author)In this paper, we explore how to effectively suppress the diffusion of (mis)information via blocking/removing the temporal contacts between selected node pairs. Information diffusion can be modelled as, e.g., an SI (Susceptible-Infected) spreading process, on a temporal social network: an infected (information possessing) node spreads the...conference paper 2020
- document
-
Wang, Tan (author), Hanjalic, A. (author), Xu, Xing (author), Shen, Heng Tao (author), Yang, Yang (author), Song, Jingkuan (author)A major challenge in matching images and text is that they have intrinsically different data distributions and feature representations. Most existing approaches are based either on embedding or classification, the first one mapping image and text instances into a common embedding space for distance measuring, and the second one regarding...conference paper 2019
- document
-
Manolios, S. (author), Hanjalic, A. (author), Liem, C.C.S. (author)The feld of recommender systems has a lot to gain from the feld of psychology. Indeed, many psychology researchers have investigated relations between models that describe humans and consumption preferences. One example of this is personality, which has been shown to be a valid construct to describe people. As a consequence, personality-based...conference paper 2019
- document
-
Zhan, X. (author), Hanjalic, A. (author), Wang, H. (author)Progress has been made in understanding how temporal network features affect the percentage of nodes reached by an information diffusion process. In this work, we explore further: which node pairs are likely to contribute to the actual diffusion of information, i.e., appear in a diffusion trajectory? How is this likelihood related to the...journal article 2019
- document
-
Kim, Jaehun (author), Urbano, Julián (author), Liem, C.C.S. (author), Hanjalic, A. (author)Inspired by the success of deploying deep learning in the fields of Computer Vision and Natural Language Processing, this learning paradigm has also found its way into the field of Music Information Retrieval. In order to benefit from deep learning in an effective, but also efficient manner, deep transfer learning has become a common approach...journal article 2019
- document
-
Urbano, Julián (author), De Lima, H.A. (author), Hanjalic, A. (author)Statistical significance testing is widely accepted as a means to assess how well a difference in effectiveness reflects an actual difference between systems, as opposed to random noise because of the selection of topics. According to recent surveys on SIGIR, CIKM, ECIR and TOIS papers, the t-test is the most popular choice among IR researchers....conference paper 2019
- document
-
Urbano, Julián (author), De Lima, H.A. (author), Hanjalic, A. (author)In test collection based evaluation of IR systems, score standardization has been proposed to compare systems across collections and minimize the effect of outlier runs on specific topics. The underlying idea is to account for the difficulty of topics, so that systems are scored relative to it. Webber et al. first proposed standardization...conference paper 2019
- document
-
Timoshevskiy, Mikhail V. (author), Pervunin, Konstantin S. (author), Markovich, Dmitriy M. (author), Hanjalic, K. (author)We studied cavitating flow over the suction side of a symmetric 2D foil - a scaled-down model of high-pressure hydroturbine guide vanes (GV) - in different cavitation regimes at several attack angles. High-speed imaging was used to analyze spatial patterns and time dynamics of the gas-vapor cavities, as well as for evaluating the...conference paper 2019
- document
-
Hrebtov, Michael (author), Hanjalic, K. (author)Seasonal variation of air quality in a city with a large river was investigated by means of numerical simulations of air movement and pollutant dispersion over inversion-capped diurnal cycles using a Reynolds-averaged Navier-Stokes (RANS) approach with algebraic turbulent flux model. The study accounts for the effects of urban heat island ...journal article 2019
- document
-
Kim, Jaehun (author), Picek, S. (author), Heuser, Annelie (author), Bhasin, Shivam (author), Hanjalic, A. (author)Profiled side-channel analysis based on deep learning, and more precisely Convolutional Neural Networks, is a paradigm showing significant potential. The results, although scarce for now, suggest that such techniques are even able to break cryptographic implementations protected with countermeasures. In this paper, we start by proposing a new...journal article 2019
- document
-
Kim, Jaehun (author), Urbano, Julián (author), Liem, C.C.S. (author), Hanjalic, A. (author)Deep neural networks have frequently been used to directly learn representations useful for a given task from raw input data. In terms of overall performance metrics, machine learning solutions employing deep representations frequently have been reported to greatly outperform those using hand-crafted feature representations. At the same time,...journal article 2019
- document
-
Dulin, V. M. (author), Lobasov, A. S. (author), Chikishev, L. M. (author), Markovich, D. M. (author), Hanjalic, K. (author)We report on a study of the impact of coherent helical vortex structures on the shape of the reaction zone and heat release in swirling methane/air flames in regimes with a vortex breakdown. Three kinds of atmospheric flames are considered, viz., fuel-lean and fuel-rich premixed flames and a partially premixed fuel-rich lifted flame. Based on...journal article 2019
- document
-
Slokom, M. (author), Larson, M.A. (author), Hanjalic, A. (author)Data science challenges allow companies, and other data holders, to collaborate with the wider research community. In the area of recommender systems, the potential of such challenges to move forward the state of the art is limited due to concerns about releasing user interaction data. This paper investigates the potential of privacy...conference paper 2019
- document
-
Song, Jingkuan (author), Guo, Yuyu (author), Gao, Lianli (author), Li, Xuelong (author), Hanjalic, A. (author), Shen, Heng Tao (author)Video captioning, in essential, is a complex natural process, which is affected by various uncertainties stemming from video content, subjective judgment, and so on. In this paper, we build on the recent progress in using encoder-decoder framework for video captioning and address what we find to be a critical deficiency of the existing...journal article 2018
- document
-
Shtork, Sergey I. (author), Litvinov, Ivan V. (author), Gorelikov, Evgeny Y. (author), Mitryakov, Andrey S. (author), Hanjalic, K. (author)The work reports on experimental study of flow and pressure pulsations in draft-tube of a laboratory air model of a Francis hydro-turbine operating over a broad range of regimes corresponding to different combinations of the runner rotation speed and flowrates. The velocity measurements using a computer-automated laser-Doppler anemometer and the...abstract 2018
- document
-
Yang, Yang (author), Zhou, Jie (author), Ai, Jiangbo (author), Bin, Yi (author), Hanjalic, A. (author), Shen, Heng Tao (author)In this paper, we propose a novel approach to video captioning based on adversarial learning and long short-term memory (LSTM). With this solution concept, we aim at compensating for the deficiencies of LSTM-based video captioning methods that generally show potential to effectively handle temporal nature of video data when generating...journal article 2018
- document
-
Yadati, N.K. (author), Larson, M.A. (author), Liem, C.C.S. (author), Hanjalic, A. (author)In this paper, we focus on event detection over the timeline of a music track. Such technology is motivated by the need for innovative applications such as searching, non-linearaccess and recommendation. Event detection over the timeline requires time-code level labels in order to train machine learning dels. We use timed comments from...journal article 2018
- document
-
Liu, L. (author), Qu, B. (author), Chen, Bin (author), Hanjalic, A. (author), Wang, H. (author)Traces of user activities recorded in online social networks open new possibilities to systematically understand the information diffusion process on social networks. From the online social network WeChat, we collected a large number of information cascade trees, each of which tells the spreading trajectory of a message/information such as which...journal article 2018
- document
-
Kim, Jaehun (author), Won, Minz (author), Liem, C.C.S. (author), Hanjalic, A. (author)In this paper, we propose a hybrid Neural Collaborative Filtering (NCF) model trained with a multi-objective function to achieve a music playlist generation system. The proposed approach focuses particularly on the cold-start problem (playlists with no seed tracks) and uses a text encoder employing a Recurrent Neural Network (RNN) to exploit...conference paper 2018