Predicting Action Tubes

TL;DR

This paper introduces TPnet, a real-time method for predicting entire action tubes in videos, including unobserved segments, by jointly forecasting past, present, and future bounding boxes and actions.

Contribution

The paper presents a novel Tube Prediction network (TPnet) that predicts complete action tubes in real-time, improving detection and enabling prediction of unobserved video segments.

Findings

TPnet improves state-of-the-art detection performance.

TPnet accurately predicts unobserved action segments.

The method operates effectively in real-time.

Abstract

In this work, we present a method to predict an entire `action tube' (a set of temporally linked bounding boxes) in a trimmed video just by observing a smaller subset of it. Predicting where an action is going to take place in the near future is essential to many computer vision based applications such as autonomous driving or surgical robotics. Importantly, it has to be done in real-time and in an online fashion. We propose a Tube Prediction network (TPnet) which jointly predicts the past, present and future bounding boxes along with their action classification scores. At test time TPnet is used in a (temporal) sliding window setting, and its predictions are put into a tube estimation framework to construct/predict the video long action tubes not only for the observed part of the video but also for the unobserved part. Additionally, the proposed action tube predictor helps in completing action tubes for unobserved segments of the video. We quantitatively demonstrate the latter ability, and the fact that TPnet improves state-of-the-art detection performance, on one of the standard action detection benchmarks - J-HMDB-21 dataset.