DeepAI AI Chat
Log In Sign Up

Predicting Action Tubes

by   Gurkirt Singh, et al.
Oxford Brookes University

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.


page 1

page 3

page 8

page 9


Action Anticipation By Predicting Future Dynamic Images

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

Temporally smooth online action detection using cycle-consistent future anticipation

Many video understanding tasks work in the offline setting by assuming t...

Is attention to bounding boxes all you need for pedestrian action prediction?

The human driver is no longer the only one concerned with the complexity...

Untrimmed Action Anticipation

Egocentric action anticipation consists in predicting a future action th...

Real Time Monocular Vehicle Velocity Estimation using Synthetic Data

Vision is one of the primary sensing modalities in autonomous driving. I...

Learning to Anticipate Egocentric Actions by Imagination

Anticipating actions before they are executed is crucial for a wide rang...

Action Concept Grounding Network for Semantically-Consistent Video Generation

Recent works in self-supervised video prediction have mainly focused on ...