@inproceedings{wentaolu2026ICSE-bug-frame,
 abstract = {Modern game studios deliver new builds and patches at a rapid pace, generating thousands of bug reports, many of which embed gameplay videos. To verify and triage these bug reports, developers must watch the submitted videos. This manual review is labour-intensive, slow, and hard to scale. In this paper, we introduce an automated pipeline that reduces each video to a single frame that best matches the reported bug description, giving developers instant visual evidence that pinpoints the bug. Our pipeline begins with FFmpeg for keyframe extraction, reducing each video to a median of just 1.9\% of its original frames while still capturing bug moments in 98.79\% of cases. These keyframes are then evaluated by a multimodal large language model (GPT-4o) with visual and text capabilities, which ranks them based on how well they match the textual bug description and selects the most representative frame. We evaluated this approach using real-world developer-submitted gameplay videos and JIRA bug reports from a popular First-Person Shooter (FPS) game. The pipeline achieves an overall F1 score of 0.79 and Success of 0.89 for the top-1 retrieved frame. Performance is highest for the Lighting \& Shadow (F1 = 0.94), Physics \& Collision (0.86), and UI \& HUD (0.83) bug categories, and lowest for Animation \& VFX (0.51). By replacing video viewing with an immediately informative image, our pipeline supports the visual confirmation step of the bug triaging process, offering practical benefits to quality assurance (QA) teams and developers across the game industry.},
 accepted = {2025-11-30},
 author = {Wentao Lu and Alexander Senchenko and Abram Hindle and Cor-Paul Bezemer},
 authors = {Wentao Lu, Alexander Senchenko, Abram Hindle, Cor-Paul Bezemer},
 booktitle = {IEEE/ACM 48th International Conference on Software Engineering: Software Engineering in Practice},
 code = {wentaolu2026ICSE-bug-frame},
 date = {2025-11-30},
 funding = {MITACS Accelerate, NSERC Discovery},
 location = {Rio De Janeiro, Brazil},
 pagerange = {200--211},
 pages = {200--211},
 rate = {61/162},
 role = {Co-Author},
 title = {Automated Bug Frame Retrieval from Gameplay Videos Using Multimodal Large Language Models},
 type = {inproceedings},
 url = {http://softwareprocess.ca/pubs/wentaolu2026ICSE-bug-frame.pdf},
 venue = {IEEE/ACM 48th International Conference on Software Engineering: Software Engineering in Practice},
 year = {2026}
}