Online Action Detection
18 papers with code • 3 benchmarks • 3 datasets
Online action detection is the task of predicting the action as soon as it happens in a streaming video without access to video frames in the future.
Benchmarks
These leaderboards are used to track progress in Online Action Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
THUMOS14
TVSeries
FineAction
Most implemented papers
Temporal Recurrent Networks for Online Action Detection
xumingze0308/TRN.pytorch
•
•
ICCV 2019
Most work on temporal action detection is formulated as an offline problem, in which the start and end times of actions are determined after the entire video is fully observed.
Long Short-Term Transformer for Online Action Detection
amazon-research/long-short-term-transformer
•
•
NeurIPS 2021
We present Long Short-term TRansformer (LSTR), a temporal modeling algorithm for online action detection, which employs a long- and short-term memory mechanism to model prolonged sequence data.
Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networks
seanmcgovern21/Machine-Learning-CS539
•
•
In this paper, we study the problem of online action detection from streaming skeleton data.
Learning to Discriminate Information for Online Action Detection
For online action detection, in this paper, we propose a novel recurrent unit to explicitly discriminate the information relevant to an ongoing action from others.
A Comprehensive Study on Temporal Modeling for Online Action Detection
wangwen39/Temporal-Modeling-Methods-for-OAD
•
•
Online action detection (OAD) is a practical yet challenging task, which has attracted increasing attention in recent years.
Human Activity Recognition: A Spatio-temporal Image Encoding of 3D Skeleton Data for Online Action Detection
Human activity recognition (HAR) based on skeleton data that can be extracted from videos (Kinect for example) , or provided by a depth camera is a time series classification problem, where handling both spatial and temporal dependencies is a crucial task, in order to achieve a good recognition.
The Instantaneous Accuracy: a Novel Metric for the Problem of Online Human Behaviour Recognition in Untrimmed Videos
The problem of Online Human Behaviour Recognition in untrimmed videos, aka Online Action Detection (OAD), needs to be revisited.
Rethinking Online Action Detection in Untrimmed Videos: A Novel Online Evaluation Protocol
Our results confirm the problems of the previous evaluation protocols, and suggest that an IA-based protocol is more adequate to the online scenario.
Two-Stream AMTnet for Action Detection
gurkirt/AMTNet
•
•
This is achieved by augmenting the previous Action Micro-Tube (AMTnet) action detection framework in three distinct ways: by adding a parallel motion stIn this paper, we propose a new deep neural network architecture for online action detection, termed ream to the original appearance one in AMTnet; (2) in opposition to state-of-the-art action detectors which train appearance and motion streams separately, and use a test time late fusion scheme to fuse RGB and flow cues, by jointly training both streams in an end-to-end fashion and merging RGB and optical flow features at training time; (3) by introducing an online action tube generation algorithm which works at video-level, and in real-time (when exploiting only appearance features).
Temporally smooth online action detection using cycle-consistent future anticipation
Many video understanding tasks work in the offline setting by assuming that the input video is given from the start to the end.
