With Chinese Full-Text Database Journal Net, this paper makes a general analysis over the developing process and current situation of the game industry study which is undertaken with the view of the industry by China...With Chinese Full-Text Database Journal Net, this paper makes a general analysis over the developing process and current situation of the game industry study which is undertaken with the view of the industry by China’s scholars from 1979 to 2013. By means of content analysis approach, this paper takes extensive study covering research projects, topics, methods, theory applied and the shift of study topics.展开更多
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
文摘With Chinese Full-Text Database Journal Net, this paper makes a general analysis over the developing process and current situation of the game industry study which is undertaken with the view of the industry by China’s scholars from 1979 to 2013. By means of content analysis approach, this paper takes extensive study covering research projects, topics, methods, theory applied and the shift of study topics.
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.
