Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal Grounding

Understand

Existing Video Temporal Grounding (VTG) models excel in accuracy but often overlook open-world challenges posed by open-vocabulary queries and untrimmed videos.

• This leads to unreliable predictions for noisy, corrupted, and out-of-distribution data.
• Adapting VTG models to dynamically estimate uncertainties based on user input can address this issue.
• To this end, we introduce SRAM, a robust network module that benefits from a two-stage cross-modal alignment task.