JTJun Tanabe

Jun Tanabe

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jun Tanabe has a total of 6 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Adaptive Background Music According to the Player’s Arousal for DareFightingICE

    by Jun Tanabe, Ibrahim Khan, Thai Van Nguyen, Chollakorn Nimpattanavong, Ruck Thawonmas

    This paper presents a system that adapts the background music of a fighting game according to the player’s arousal. The system uses a model to estimate the player’s arousal based on events in the game and accordingly changes the pitch, tempo, and volume of the music. The system does not use AI music generation or arrangement but modifies existing music in real time. We experiment to evaluate the impact of different arousal durations on the player’s immersion and music preference. The results show that a duration of 10 seconds is the most suitable for fighting games, as it increases the immersion and matches the music with the game situation.

  • Open Access

    Minecraft Video Aesthetics Quality Assessment Model

    by Ryosuke Hasegawa, Ruck Thawonmas, Jun Tanabe, Lian Yu

    We propose the Minecraft Video Aesthetic Quality Assessment Model (MCVQA), a tool designed to assess the aesthetic quality of Minecraft videos (MC videos) comprehensively. We explain the meticulous processes, including creating purpose-built datasets, implementing sophisticated feature extraction techniques, and fine-tuning model hyperparameters. We validate MCVQA’s efficacy through a two-step approach: accuracy validation and an information recommendation system. In conclusion, first, using the datasets created in this study, an impressive 63.6% alignment was observed between the "best" shot types assigned by the user and the model’s predictions. Subsequently, the usefulness of MCVQA as a recommendation system was validated, and a remarkable accuracy of 58.3% was confirmed.