隐藏字幕
计算机科学
水准点(测量)
任务(项目管理)
人工智能
判决
自然语言处理
情报检索
机器学习
语音识别
图像(数学)
管理
大地测量学
经济
地理
作者
Haoran Chen,Jianmin Li,Simone Frintrop,Xiaolin Hu
标识
DOI:10.1016/j.cviu.2022.103581
摘要
Video captioning automatically generates short descriptions of the video content, usually in form of a single sentence. Many methods have been proposed for solving this task. A large dataset called MSR Video to Text (MSR-VTT) is often used as the benchmark dataset for testing the performance of the methods. However, we found that the human annotations, i.e., the descriptions of video contents in the dataset are quite noisy, e.g., there are many duplicate captions and many captions contain grammatical problems. These problems may pose difficulties to video captioning models for learning underlying patterns. We cleaned the MSR-VTT annotations by removing these problems, then tested several typical video captioning models on the cleaned dataset. Experimental results showed that data cleaning boosted the performances of the models measured by popular quantitative metrics. We recruited subjects to evaluate the results of a model trained on the original and cleaned datasets. The human behavior experiment demonstrated that trained on the cleaned dataset, the model generated captions that were more coherent and more relevant to the contents of the video clips.
科研通智能强力驱动
Strongly Powered by AbleSci AI