一句话：提出半监督聚类工具 SemCluster，利用深度图像理解融合文本与截图语义，以减少众包测试报告重复。
众包移动应用测试因开放性导致大量重复报告。已有方法提取测试报告的文本特征，结合浅层图像分析，进行无监督聚类以识别重复报告，但忽略了文本描述与截图之间的语义关联，造成聚类结果不理想、去重精度较低。针对此问题，本文提出 SemCluster，一种半监督聚类工具，引入深度图像理解来建模文本与截图的语义连接，从而提升众包测试报告聚类与去重效果。摘要未给出具体实验数据，但该工具旨在弥合文本描述与视觉信息间的语义鸿沟，解决现有方法因语义缺失而导致的聚类与去重不准确问题。
Due to the openness of crowdsourced testing, mobile app crowdsourced testing has been subject to duplicate reports. The previous research methods extract the textual features of the crowdsourced test reports, combine with shallow image analysis, and perform unsupervised clustering on the crowdsourced test reports to clarify the duplication of crowdsourced test reports and solve the problem. However, these methods ignore the semantic connection between textual descriptions and screenshots, making the clustering results unsatisfactory and the deduplication effect less accurate.
DOI 原文 ·
@inproceedings{paperbot7101,
title = {SemCluster: a semi-supervised clustering tool for crowdsourced test reports with deep image understanding},
author = {Mingzhe Du and Shengcheng Yu and Chunrong Fang and Tongyu Li and Heyuan Zhang and Zhenyu Chen},
booktitle = {FSE},
year = {2022},
doi = {10.1145/3540250.3558933}
}