CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation
This provides a new benchmark for video titling and retrieval in Chinese short videos, addressing a domain-specific gap but likely incremental in methodology.
The authors tackled the lack of a proper benchmark for video titling in Chinese short videos by creating CREATE, a large-scale dataset with 210K labeled videos, 3M/10M pre-training datasets, and 537K manually annotated titles. They also proposed ALWIG, a model combining video retrieval and titling tasks, though no specific performance numbers are provided.
Previous works of video captioning aim to objectively describe the video's actual content, which lacks subjective and attractive expression, limiting its practical application scenarios. Video titling is intended to achieve this goal, but there is a lack of a proper benchmark. In this paper, we propose to CREATE, the first large-scale Chinese shoRt vidEo retrievAl and Title gEneration benchmark, to facilitate research and application in video titling and video retrieval in Chinese. CREATE consists of a high-quality labeled 210K dataset and two large-scale 3M/10M pre-training datasets, covering 51 categories, 50K+ tags, 537K manually annotated titles and captions, and 10M+ short videos. Based on CREATE, we propose a novel model ALWIG which combines video retrieval and video titling tasks to achieve the purpose of multi-modal ALignment WIth Generation with the help of video tags and a GPT pre-trained model. CREATE opens new directions for facilitating future research and applications on video titling and video retrieval in the field of Chinese short videos.