Browse > Computer Vision > Zero-Shot Learning > Zero-Shot Action Recognition

Zero-Shot Action Recognition

118 papers with code · Computer Vision
Subtask of Zero-Shot Learning

The zero-shot action recognition aims to recognize unseen/novel action categories by exploiting semantics and seen/known actions

State-of-the-art leaderboards

Trend Dataset Best Method Paper title Paper Code Compare

Latest papers with code

Symbiotic Graph Neural Networks for 3D Skeleton-based Human Action Recognition and Motion Prediction

5 Oct 2019limaosen0/Sym-GNN

For the backbone, we propose multi-branch multi-scale graph convolution networks to extract spatial and temporal features.

SKELETON BASED ACTION RECOGNITION

2
05 Oct 2019

Class Feature Pyramids for Video Explanation

18 Sep 2019alexandrosstergiou/Class_Feature_Visualization_Pyramid

We demonstrate the method on six state-of-the-art 3D convolution neural networks (CNNs) on three action recognition (Kinetics-400, UCF-101, and HMDB-51) and two egocentric action recognition datasets (EPIC-Kitchens and EGTEA Gaze+).

ZERO-SHOT ACTION RECOGNITION

6
18 Sep 2019

Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference Joints

11 Sep 2019carloscaetano/skeleton-images

The proposed representation has the advantage of combining the use of reference joints and a tree structure skeleton.

SKELETON BASED ACTION RECOGNITION

5
11 Sep 2019

Video Representation Learning by Dense Predictive Coding

10 Sep 2019TengdaHan/DPC

The objective of this paper is self-supervised learning of spatio-temporal embeddings from video, suitable for human action recognition.

REPRESENTATION LEARNING ZERO-SHOT ACTION RECOGNITION

70
10 Sep 2019

Human activity recognition from skeleton poses

20 Aug 2019frederico-klein/cad-gas

Human Action Recognition is an important task of Human Robot Interaction as cooperation between robots and humans requires that artificial agents recognise complex cues from the environment.

HUMAN ACTIVITY RECOGNITION ZERO-SHOT ACTION RECOGNITION

0
20 Aug 2019

SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition

30 Jul 2019carloscaetano/skeleton-images

Due to the availability of large-scale skeleton datasets, 3D human action recognition has recently called the attention of computer vision community.

ACTION RECOGNITION IN VIDEOS SKELETON BASED ACTION RECOGNITION

5
30 Jul 2019
67
13 Jun 2019

Skeleton-Based Action Recognition With Directed Graph Neural Networks

CVPR 2019 kenziyuliu/DGNN-PyTorch

The skeleton data have been widely used for the action recognition tasks since they can robustly accommodate dynamic circumstances and complex backgrounds.

GRAPH NEURAL NETWORK SKELETON BASED ACTION RECOGNITION

47
01 Jun 2019

Bayesian Hierarchical Dynamic Model for Human Action Recognition

CVPR 2019 rort1989/HDM

Human action recognition remains as a challenging task partially due to the presence of large variations in the execution of action.

BAYESIAN INFERENCE MULTIMODAL ACTIVITY RECOGNITION SKELETON BASED ACTION RECOGNITION

6
01 Jun 2019

What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention

22 May 2019antoninofurnari/rulstm

Our method is ranked first in the public leaderboard of the EPIC-Kitchens egocentric action anticipation challenge 2019.

OPTICAL FLOW ESTIMATION ZERO-SHOT ACTION RECOGNITION

21
22 May 2019