Human action recognition in drone videos using a few aerial training examples
Waqas Sultani,Mubarak Shah +1 more
TLDR
In this article, a disjoint multitask learning framework was proposed to combine real and game data in an alternating fashion to obtain an improved action classifier for aerial action recognition.About:
This article is published in Computer Vision and Image Understanding.The article was published on 2021-05-01 and is currently open access. It has received 16 citations till now.read more
Citations
More filters
Journal ArticleDOI
A Systematic Review on Data Scarcity Problem in Deep Learning: Solution and Applications
TL;DR: The purpose of this study focuses on various data augmentation techniques that can be used to further improve the accuracy of a neural network by augmenting available data.
Journal ArticleDOI
Human Activity Classification Using the 3DCNN Architecture
TL;DR: The experimental results show that the optimized proposed 3DCNN provides better results than neural network architectures for motion, static and hybrid features, and the experimental results on the UCF YouTube Action dataset demonstrate the effectiveness of the proposed3DCNN for recognition of human activity.
Journal ArticleDOI
Automated Parts-Based Model for Recognizing Human-Object Interactions from Aerial Imagery with Fully Convolutional Network
Yazeed Yasin Ghadi,Manahil Waheed,Tamara Al Shloul,Suliman A. Alsuhibany,Ahmad Jalal,Jeon-Su Park +5 more
TL;DR: This article proposes a novel parts-based model for recognizing complex human–object interactions in videos and images captured using ground and aerial cameras using a fully convolutional network (FCN).
Journal ArticleDOI
Detecting Human Actions in Drone Images Using YoloV5 and Stochastic Gradient Boosting
TL;DR: This work explores low-resource methods for ML (machine learning)-based action recognition using a previously collected real-world dataset (the “Okutama-Action” dataset) and investigates a combination of object recognition and classifier techniques to support single-image action identification.
Book ChapterDOI
FAR: Fourier Aerial Video Recognition
TL;DR: In this article , Fourier object disentanglement is used to separate out the human agent from the background in the frequency domain to characterize the extent of temporal change of spatial pixels, and exploits convolution-multiplication properties of Fourier transform.
References
More filters
Journal ArticleDOI
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
Book ChapterDOI
SSD: Single Shot MultiBox Detector
Wei Liu,Dragomir Anguelov,Dumitru Erhan,Christian Szegedy,Scott Reed,Cheng-Yang Fu,Alexander C. Berg +6 more
TL;DR: The approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location, which makes SSD easy to train and straightforward to integrate into systems that require a detection component.
Posted Content
Conditional Generative Adversarial Nets
Mehdi Mirza,Simon Osindero +1 more
TL;DR: The conditional version of generative adversarial nets is introduced, which can be constructed by simply feeding the data, y, to the generator and discriminator, and it is shown that this model can generate MNIST digits conditioned on class labels.
Proceedings ArticleDOI
Learning Spatiotemporal Features with 3D Convolutional Networks
TL;DR: The learned features, namely C3D (Convolutional 3D), with a simple linear classifier outperform state-of-the-art methods on 4 different benchmarks and are comparable with current best methods on the other 2 benchmarks.
Proceedings Article
Wasserstein Generative Adversarial Networks
TL;DR: This work introduces a new algorithm named WGAN, an alternative to traditional GAN training that can improve the stability of learning, get rid of problems like mode collapse, and provide meaningful learning curves useful for debugging and hyperparameter searches.
Related Papers (5)
Human Action Recognition in Drone Videos using a Few Aerial Training Examples
Waqas Sultani,Mubarak Shah +1 more