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

TL;DR

This paper introduces PLAN-B, a novel method for predicting multiple plausible future action sequences, emphasizing the importance of identifying all likely alternatives and proposing new evaluation metrics.

Contribution

The paper presents PLAN-B, a new approach with a Choice Table and collaborative RNN to find all likely future actions, improving over existing methods.

Findings

Outperforms state-of-the-art on benchmark datasets

Effectively finds all plausible future actions

Introduces new evaluation metrics for alternative prediction

Abstract

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.