A computer vision approach through Open AI’s CLIP, a model capable of predicting text-image pairs, is used to create an AI agent for Dixit, a game which requires creative linking between images and text. This paper c...A computer vision approach through Open AI’s CLIP, a model capable of predicting text-image pairs, is used to create an AI agent for Dixit, a game which requires creative linking between images and text. This paper calculates baseline accuracies for both the ability to match the correct image to a hint and the ability to match up with human preferences. A dataset created by previous work on Dixit is used for testing. CLIP is utilized through the comparison of a hint to multiple images, and previous hints, achieving a final accuracy of 0.5011 which surpasses previous results.展开更多
In this study, we conduct research to estimate the elements of fun in card games. Previously, we tried to estimate the elements of fun by conducting a questionnaire to players, but the results were not good. Therefore...In this study, we conduct research to estimate the elements of fun in card games. Previously, we tried to estimate the elements of fun by conducting a questionnaire to players, but the results were not good. Therefore, we propose an analysis using the player’s biological information to make a more accurate estimation. Specifically, we try to elucidate the elements of fun by having a player who is playing a game wear a smart watch, and measuring and analyzing the heart rate of that player. This paper conducts an experiment to determine whether our intended data can be collected. As a result, it was found that there is a response to the heart rate in a specific scene, and there is a possibility that the intended data can be collected. We plan to conduct larger experiments in the future.展开更多
文摘A computer vision approach through Open AI’s CLIP, a model capable of predicting text-image pairs, is used to create an AI agent for Dixit, a game which requires creative linking between images and text. This paper calculates baseline accuracies for both the ability to match the correct image to a hint and the ability to match up with human preferences. A dataset created by previous work on Dixit is used for testing. CLIP is utilized through the comparison of a hint to multiple images, and previous hints, achieving a final accuracy of 0.5011 which surpasses previous results.
文摘In this study, we conduct research to estimate the elements of fun in card games. Previously, we tried to estimate the elements of fun by conducting a questionnaire to players, but the results were not good. Therefore, we propose an analysis using the player’s biological information to make a more accurate estimation. Specifically, we try to elucidate the elements of fun by having a player who is playing a game wear a smart watch, and measuring and analyzing the heart rate of that player. This paper conducts an experiment to determine whether our intended data can be collected. As a result, it was found that there is a response to the heart rate in a specific scene, and there is a possibility that the intended data can be collected. We plan to conduct larger experiments in the future.
