Anticipation and next action forecasting in video: an end-to-end model with memory
This work addresses the problem of predicting future actions in videos for applications like surveillance or robotics, but it appears incremental as it builds on existing methods by adding memory components.
The paper tackles action anticipation and forecasting in videos by proposing an end-to-end network with memory to capture contextual signs from the past, resulting in significant improvements in forecasting performance as shown in experiments on action sequence datasets.
Action anticipation and forecasting in videos do not require a hat-trick, as far as there are signs in the context to foresee how actions are going to be deployed. Capturing these signs is hard because the context includes the past. We propose an end-to-end network for action anticipation and forecasting with memory, to both anticipate the current action and foresee the next one. Experiments on action sequence datasets show excellent results indicating that training on histories with a dynamic memory can significantly improve forecasting performance.