Learning to Abstract and Predict Human Actions

by   Romero Morais, et al.

Human activities are naturally structured as hierarchies unrolled over time. For action prediction, temporal relations in event sequences are widely exploited by current methods while their semantic coherence across different levels of abstraction has not been well explored. In this work we model the hierarchical structure of human activities in videos and demonstrate the power of such structure in action prediction. We propose Hierarchical Encoder-Refresher-Anticipator, a multi-level neural machine that can learn the structure of human activities by observing a partial hierarchy of events and roll-out such structure into a future prediction in multiple levels of abstraction. We also introduce a new coarse-to-fine action annotation on the Breakfast Actions videos to create a comprehensive, consistent, and cleanly structured video hierarchical activity dataset. Through our experiments, we examine and rethink the settings and metrics of activity prediction tasks toward unbiased evaluation of prediction systems, and demonstrate the role of hierarchical modeling toward reliable and detailed long-term action forecasting.


page 16

page 17


Classify, predict, detect, anticipate and synthesize: Hierarchical recurrent latent variable models for human activity modeling

Human activity modeling operates on two levels: high-level action modeli...

Learning the Predictability of the Future

We introduce a framework for learning from unlabeled video what is predi...

Intention-Conditioned Long-Term Human Egocentric Action Forecasting @ EGO4D Challenge 2022

To anticipate how a human would act in the future, it is essential to un...

Video Prediction at Multiple Scales with Hierarchical Recurrent Networks

Autonomous systems not only need to understand their current environment...

What Actions are Needed for Understanding Human Actions in Videos?

What is the right way to reason about human activities? What directions ...

Watch-n-Patch: Unsupervised Learning of Actions and Relations

There is a large variation in the activities that humans perform in thei...

Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos

Every moment counts in action recognition. A comprehensive understanding...