PLAN-B: Predicting Likely Alternative Next Best Sequences for Action Prediction

by   Dan Scarafoni, et al.

Action prediction focuses on anticipating actions before they happen. Recent works leverage probabilistic approaches to describe future uncertainties and sample future actions. However, these methods cannot easily find all alternative predictions, which are essential given the inherent unpredictability of the future, and current evaluation protocols do not measure a system's ability to find such alternatives. We re-examine action prediction in terms of its ability to predict not only the top predictions, but also top alternatives with the accuracy@k metric. In addition, we propose Choice F1: a metric inspired by F1 score which evaluates a prediction system's ability to find all plausible futures while keeping only the most probable ones. To evaluate this problem, we present a novel method, Predicting the Likely Alternative Next Best, or PLAN-B, for action prediction which automatically finds the set of most likely alternative futures. PLAN-B consists of two novel components: (i) a Choice Table which ensures that all possible futures are found, and (ii) a "Collaborative" RNN system which combines both action sequence and feature information. We demonstrate that our system outperforms state-of-the-art results on benchmark datasets.



page 9


Action Anticipation By Predicting Future Dynamic Images

Human action-anticipation methods predict what is the future action by o...

Predicting the Future: A Jointly Learnt Model for Action Anticipation

Inspired by human neurological structures for action anticipation, we pr...

Predicting Responses to a Robot's Future Motion using Generative Recurrent Neural Networks

Robotic navigation through crowds or herds requires the ability to both ...

RegFlow: Probabilistic Flow-based Regression for Future Prediction

Predicting future states or actions of a given system remains a fundamen...

TTPP: Temporal Transformer with Progressive Prediction for Efficient Action Anticipation

Video action anticipation aims to predict future action categories from ...

Encouraging LSTMs to Anticipate Actions Very Early

In contrast to the widely studied problem of recognizing an action given...

Towards Streaming Egocentric Action Anticipation

Egocentric action anticipation is the task of predicting the future acti...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.