Search papers, labs, and topics across Lattice.
This paper addresses the challenge of multi-label perceptual bug detection in video games by proposing a ResNet-BiLSTM deep learning model, outperforming established 3D convolutional architectures like I3D and 3D ResNet with an F1 score of 85.78% on a novel, large-scale dataset. The research highlights the critical role of temporal dependency modeling for accurate video-based bug identification, offering a significant advancement over existing methods that struggle with multiple bug types simultaneously. This work aims to substantially reduce manual testing costs and improve quality assurance in game development.
A novel ResNet-BiLSTM model achieves 85.78% F1 for multi-label perceptual bug detection in video games, proving temporal modeling is key for identifying diverse visual glitches.
Traditional approaches for automated bug detection in video games, such as manual testing, can be beneficial for the improvement of quality assurance, but they can be expensive and time-consuming. The scarce number of tools available to detect multiple perceptual bugs in the same video frame introduces detection challenges for automated bug detection tools in real-world scenarios. We propose a deep learning model for multi-label perceptual bug detection and compare it against video classification models such as Inflated 3D ConvNet and 3D ResNet. Our proposed model, ResNet-BiLSTM, achieved an F1 score of 85.78% on the benchmark dataset. Our results demonstrated that temporal dependency modelling is beneficial for accurate video-based bug detection. We believe this work with multi-label perceptual bug detection on gameplay videos will help save resources spent on manual testing workloads in video games. Furthermore, we introduce a new dataset with multi-label perceptual bugs in this work. The dataset contains 77,969 video clips across different genres of games with approximately 1.2 million frames, containing combinations from 5 classes of bugs in the same video frame.
