Technical Report: Temporal Aggregate Representations
This is an incremental technical report that addresses video understanding challenges for researchers in computer vision.
The authors extended their previous work on long-term video understanding by conducting additional experiments with their multi-granular temporal aggregation framework on new tasks and the EPIC-KITCHENS-100 dataset, but no specific results or numbers are reported.
This technical report extends our work presented in [9] with more experiments. In [9], we tackle long-term video understanding, which requires reasoning from current and past or future observations and raises several fundamental questions. How should temporal or sequential relationships be modelled? What temporal extent of information and context needs to be processed? At what temporal scale should they be derived? [9] addresses these questions with a flexible multi-granular temporal aggregation framework. In this report, we conduct further experiments with this framework on different tasks and a new dataset, EPIC-KITCHENS-100.