VidEvent: A Large Dataset for Understanding Dynamic Evolution of Events in Videos
This addresses the problem of video event understanding for AI researchers, offering a new dataset to support algorithm development, though it is incremental as it builds on existing data collection efforts.
The paper tackles the challenge of understanding complex events in videos by introducing VidEvent, a large-scale dataset with over 23,000 labeled events from movie recaps, and provides baseline models to benchmark future research.
Despite the significant impact of visual events on human cognition, understanding events in videos remains a challenging task for AI due to their complex structures, semantic hierarchies, and dynamic evolution. To address this, we propose the task of video event understanding that extracts event scripts and makes predictions with these scripts from videos. To support this task, we introduce VidEvent, a large-scale dataset containing over 23,000 well-labeled events, featuring detailed event structures, broad hierarchies, and logical relations extracted from movie recap videos. The dataset was created through a meticulous annotation process, ensuring high-quality and reliable event data. We also provide comprehensive baseline models offering detailed descriptions of their architecture and performance metrics. These models serve as benchmarks for future research, facilitating comparisons and improvements. Our analysis of VidEvent and the baseline models highlights the dataset's potential to advance video event understanding and encourages the exploration of innovative algorithms and models. The dataset and related resources are publicly available at www.videvent.top.