F$^3$Set: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos
This addresses the problem of detecting subtle, rapid events in videos for video analytics and multi-modal LLMs, but is incremental as it builds on existing temporal action understanding methods.
The paper tackles the challenge of analyzing Fast, Frequent, and Fine-grained (F³) events in videos by introducing F³Set, a benchmark dataset with over 1,000 event types and precise timestamps, and reveals that existing methods struggle on it while their proposed F³ED method achieves superior performance.
Analyzing Fast, Frequent, and Fine-grained (F$^3$) events presents a significant challenge in video analytics and multi-modal LLMs. Current methods struggle to identify events that satisfy all the F$^3$ criteria with high accuracy due to challenges such as motion blur and subtle visual discrepancies. To advance research in video understanding, we introduce F$^3$Set, a benchmark that consists of video datasets for precise F$^3$ event detection. Datasets in F$^3$Set are characterized by their extensive scale and comprehensive detail, usually encompassing over 1,000 event types with precise timestamps and supporting multi-level granularity. Currently, F$^3$Set contains several sports datasets, and this framework may be extended to other applications as well. We evaluated popular temporal action understanding methods on F$^3$Set, revealing substantial challenges for existing techniques. Additionally, we propose a new method, F$^3$ED, for F$^3$ event detections, achieving superior performance. The dataset, model, and benchmark code are available at https://github.com/F3Set/F3Set.