arXiv：cs.LG· Nahian Rifaat, Felix Morosov, Loutfouz Zaman·· 4 小时前AI 评分32
用深度学习在游戏画面中检测多标签感知 Bug：ResNet-BiLSTM 模型与数据集
Multi-Label Perceptual Bug Detection in Video Games using Deep Learning on Gameplay Footage
AI 导读
研究者提出 ResNet-BiLSTM 深度学习模型，用于在游戏画面中同时检测同一视频帧内的多种感知 Bug，在基准数据集上取得 85.78% 的 F1 分数，优于 Inflated 3D ConvNet 和 3D ResNet 等视频分类模型。
正文
Abstract: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.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.08593 [cs.LG] |
| (or arXiv:2610.08593v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.08593 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Loutfouz Zaman [view email]
[v1]
Tue, 6 Oct 2026 16:01:00 UTC (7,324 KB)
来源：arXiv：cs.LG · arxiv.org