With the rapid development of video Multimodal Large Language Models (MLLMs),
numerous benchmarks have been proposed to assess their video understanding
capability. However, due to the lack of rich events in the videos, these
datasets may suffer from the short-cut bias that the answers can be deduced
from a few frames, without the need to watch the entire video. To address this
issue, we introduce Event-Bench, an event-oriented long video understanding
benchmark built on existing datasets and human annotations. Event-Bench
includes six event-related tasks and 2,190 test instances to comprehensively
evaluate video event understanding ability. Additionally, we propose Video
Instruction Merging~(VIM), a cost-effective method that enhances video MLLMs
using merged, event-intensive video instructions, addressing the scarcity of
human-annotated, event-intensive data. Extensive experiments show that the
best-performing model, GPT-4o, achieves an overall accuracy of 53.33,
significantly outperforming the best open-source model by 41.42%. Leveraging an
effective instruction synthesis method and an adaptive model architecture, VIM
surpasses both state-of-the-art open-source models and GPT-4V on the
Event-Bench. All code, data, and models are publicly available at
this https URL

通过引入基于现有数据集和人类注释的面向事件的长视频理解基准测试集 Event-Bench 以及使用合并的、事件密集型视频指令来增强视频 MLLMs 的低成本方法 VIM，本研究表明 GPT-4o 模型超过了最佳开源模型 41.42％，在 Event-Bench 上表现出 53.33 的整体准确率，优于最先进的开源模型和 GPT-4V。