CCL24-Eval任务9总结报告:中文图文多模态理解评测

The Chinese Vision-Language Understanding Task aims to evaluate the vision-language modeling and understanding capabilities of Chinese vision-language pre-training models from multiple perspectives. This task includes five sub-tasks: image retrieval, text retrieval, visual question answering, visual grounding, and visual dialogue. The final score is calculated based on the combined results of these five tasks. This paper first introduces the background and motivation of the task, then presents and demonstrates relevant information about this task from aspects including task description, evaluation metrics, submitted results, and participant methods. A total of 11 teams registered to participate in this task. And 3 teams eventually submitted their results.