CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation

TL;DR

CREATE is a comprehensive Chinese short video benchmark with a large dataset, designed to advance research in video retrieval and title generation, integrating multi-modal alignment with a novel model.

Contribution

It introduces the first large-scale Chinese short video retrieval and title generation benchmark, including datasets and a new model for multi-modal alignment.

Findings

Created a 210K labeled dataset for Chinese short videos.

Developed a model combining retrieval and titling tasks.

Facilitated future research in Chinese video applications.

Abstract

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.