Player Experience Extraction from Gameplay Video
This addresses a barrier for researchers, developers, and hobbyists by enabling game log extraction from video, though it is incremental as it builds on existing transfer learning methods.
The paper tackled the problem of extracting game event sequences from gameplay video without needing game engine access, presenting two CNN-based transfer learning approaches that outperformed random forest and other baselines in Super Mario Bros., Mega Man, and Skyrim.
The ability to extract the sequence of game events for a given player's play-through has traditionally required access to the game's engine or source code. This serves as a barrier to researchers, developers, and hobbyists who might otherwise benefit from these game logs. In this paper we present two approaches to derive game logs from game video via convolutional neural networks and transfer learning. We evaluate the approaches in a Super Mario Bros. clone, Mega Man and Skyrim. Our results demonstrate our approach outperforms random forest and other transfer baselines.