LocFormer: Enabling Transformers to Perform Temporal Moment Localization on Long Untrimmed Videos With a Feature Sampling Approach.
Cristian Rodriguez OpazoEdison Marrese-TaylorBasura FernandoHiroya TakamuraQi WuPublished in: CoRR (2021)
Keyphrases
- spatio temporal
- temporal information
- spatial and temporal
- temporal domain
- temporal relationships
- video frames
- spatial features
- video database
- feature vectors
- sample size
- motion features
- temporal reasoning
- temporal sequences
- face recognition
- monte carlo
- space time
- temporal databases
- random sampling
- temporal coherence
- feature set
- temporal events