Filters








11 Hits in 1.0 sec

Semi-supervised learning for medical image classification using imbalanced training data [article]

Tri Huynh, Aiden Nibali, Zhen He
2021 arXiv   pre-print
Medical image classification is often challenging for two reasons: a lack of labelled examples due to expensive and time-consuming annotation protocols, and imbalanced class labels due to the relative scarcity of disease-positive individuals in the wider population. Semi-supervised learning (SSL) methods exist for dealing with a lack of labels, but they generally do not address the problem of class imbalance. In this study we propose Adaptive Blended Consistency Loss (ABCL), a drop-in
more » ... t for consistency loss in perturbation-based SSL methods. ABCL counteracts data skew by adaptively mixing the target class distribution of the consistency loss in accordance with class frequency. Our experiments with ABCL reveal improvements to unweighted average recall on two different imbalanced medical image classification datasets when compared with existing consistency losses that are not designed to counteract class imbalance.
arXiv:2108.08956v1 fatcat:bfnu35thhjdzjj7t4wtjdflmoe

Extraction and Classification of Diving Clips from Continuous Video Footage [article]

Aiden Nibali, Zhen He, Stuart Morgan, Daniel Greenwood
2017 arXiv   pre-print
Due to recent advances in technology, the recording and analysis of video data has become an increasingly common component of athlete training programmes. Today it is incredibly easy and affordable to set up a fixed camera and record athletes in a wide range of sports, such as diving, gymnastics, golf, tennis, etc. However, the manual analysis of the obtained footage is a time-consuming task which involves isolating actions of interest and categorizing them using domain-specific knowledge. In
more » ... der to automate this kind of task, three challenging sub-problems are often encountered: 1) temporally cropping events/actions of interest from continuous video; 2) tracking the object of interest; and 3) classifying the events/actions of interest. Most previous work has focused on solving just one of the above sub-problems in isolation. In contrast, this paper provides a complete solution to the overall action monitoring task in the context of a challenging real-world exemplar. Specifically, we address the problem of diving classification. This is a challenging problem since the person (diver) of interest typically occupies fewer than 1% of the pixels in each frame. The model is required to learn the temporal boundaries of a dive, even though other divers and bystanders may be in view. Finally, the model must be sensitive to subtle changes in body pose over a large number of frames to determine the classification code. We provide effective solutions to each of the sub-problems which combine to provide a highly functional solution to the task as a whole. The techniques proposed can be easily generalized to video footage recorded from other sports.
arXiv:1705.09003v1 fatcat:gzk575zigrgwjiripwvnvbvxbi

Numerical Coordinate Regression with Convolutional Neural Networks [article]

Aiden Nibali, Zhen He, Stuart Morgan, Luke Prendergast
2018 arXiv   pre-print
We study deep learning approaches to inferring numerical coordinates for points of interest in an input image. Existing convolutional neural network-based solutions to this problem either take a heatmap matching approach or regress to coordinates with a fully connected output layer. Neither of these approaches is ideal, since the former is not entirely differentiable, and the latter lacks inherent spatial generalization. We propose our differentiable spatial to numerical transform (DSNT) to
more » ... this gap. The DSNT layer adds no trainable parameters, is fully differentiable, and exhibits good spatial generalization. Unlike heatmap matching, DSNT works well with low heatmap resolutions, so it can be dropped in as an output layer for a wide range of existing fully convolutional architectures. Consequently, DSNT offers a better trade-off between inference speed and prediction accuracy compared to existing techniques. When used to replace the popular heatmap matching approach used in almost all state-of-the-art methods for pose estimation, DSNT gives better prediction accuracy for all model architectures tested.
arXiv:1801.07372v2 fatcat:apj6baocjzgghlard5bmj6esvi

Pose is all you need: The pose only group activity recognition system (POGARS) [article]

Haritha Thilakarathne, Aiden Nibali, Zhen He, Stuart Morgan
2021 arXiv   pre-print
We introduce a novel deep learning based group activity recognition approach called the Pose Only Group Activity Recognition System (POGARS), designed to use only tracked poses of people to predict the performed group activity. In contrast to existing approaches for group activity recognition, POGARS uses 1D CNNs to learn spatiotemporal dynamics of individuals involved in a group activity and forgo learning features from pixel data. The proposed model uses a spatial and temporal attention
more » ... ism to infer person-wise importance and multi-task learning for simultaneously performing group and individual action classification. Experimental results confirm that POGARS achieves highly competitive results compared to state-of-the-art methods on a widely used public volleyball dataset despite only using tracked pose as input. Further our experiments show by using pose only as input, POGARS has better generalization capabilities compared to methods that use RGB as input.
arXiv:2108.04186v1 fatcat:egelbg3uw5bfjit7vrtiindi74

3D Human Pose Estimation with 2D Marginal Heatmaps [article]

Aiden Nibali, Zhen He, Stuart Morgan, Luke Prendergast
2018 arXiv   pre-print
Automatically determining three-dimensional human pose from monocular RGB image data is a challenging problem. The two-dimensional nature of the input results in intrinsic ambiguities which make inferring depth particularly difficult. Recently, researchers have demonstrated that the flexible statistical modelling capabilities of deep neural networks are sufficient to make such inferences with reasonable accuracy. However, many of these models use coordinate output techniques which are
more » ... ensive, not differentiable, and/or do not spatially generalise well. We propose improvements to 3D coordinate prediction which avoid the aforementioned undesirable traits by predicting 2D marginal heatmaps under an augmented soft-argmax scheme. Our resulting model, MargiPose, produces visually coherent heatmaps whilst maintaining differentiability. We are also able to achieve state-of-the-art accuracy on publicly available 3D human pose estimation data.
arXiv:1806.01484v2 fatcat:d5nlhqqk6vglze2lfavq5rbvwq

Trajic: An Effective Compression System for Trajectory Data

Aiden Nibali, Zhen He
2015 IEEE Transactions on Knowledge and Data Engineering  
Delta compression achieves lossless compression by storing the difference between successive data points • Aiden Nibali and Zhen He are with the Department of Computer Science and Computer Engineering,  ... 
doi:10.1109/tkde.2015.2436932 fatcat:adxn6iov65f7naftlfevgbvsvy

Extraction and Classification of Diving Clips from Continuous Video Footage

Aiden Nibali, Zhen He, Stuart Morgan, Daniel Greenwood
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
Due to recent advances in technology, the recording and analysis of video data has become an increasingly common component of athlete training programmes. Today it is incredibly easy and affordable to set up a fixed camera and record athletes in a wide range of sports, such as diving, gymnastics, golf, tennis, etc. However, the manual analysis of the obtained footage is a time-consuming task which involves isolating actions of interest and categorizing them using domain-specific knowledge. In
more » ... der to automate this kind of task, three challenging sub-problems are often encountered: 1) temporally cropping events/actions of interest from continuous video; 2) tracking the object of interest; and 3) classifying the events/actions of interest. Most previous work has focused on solving just one of the above sub-problems in isolation. In contrast, this paper provides a complete solution to the overall action monitoring task in the context of a challenging real-world exemplar. Specifically, we address the problem of diving classification. This is a challenging problem since the person (diver) of interest typically occupies fewer than 1% of the pixels in each frame. The model is required to learn the temporal boundaries of a dive, even though other divers and bystanders may be in view. Finally, the model must be sensitive to subtle changes in body pose over a large number of frames to determine the classification code. We provide effective solutions to each of the sub-problems which combine to provide a highly functional solution to the task as a whole. The techniques proposed can be easily generalized to video footage recorded from other sports.
doi:10.1109/cvprw.2017.18 dblp:conf/cvpr/NibaliHMG17 fatcat:2tjy23yqzrfbjeihr3ylqs6iha

A Survey on Destination Prediction Using Trajectory Data Mining Technique

Banupriya C S
2016 International Journal Of Engineering And Computer Science  
LITERARY SURVEY Aiden Nibali and Zhen He [1] proposed the Trajic process for compressing the vast amount of the trajectory data.  ... 
doi:10.18535/ijecs/v5i12.67 fatcat:lzg2mq6fdnfstj3ll4s76a35je

Benign and Malignant Classification Model of Pulmonary Nodules Based on Residual Neural Network

Zhenzhe Lin, Guitang Wang, Qinshen Fu, Guozhen Wang
2019 Proceedings of the 2019 International Conference on Big Data, Electronics and Communication Engineering (BDECE 2019)   unpublished
Aiden Nibali et al. [2] put forward a residual network to classify lung cancers using CT images, obtaining an accuracy rate of 89.9%.  ... 
doi:10.2991/acsr.k.191223.038 fatcat:h4bhfwpij5fu5la77drmroluna

BAPose: Bottom-Up Pose Estimation with Disentangled Waterfall Representations [article]

Bruno Artacho, Andreas Savakis
2021 arXiv   pre-print
In European Conference [29] Aiden Nibali, Zhen He, Stuart Morgan, and Luke Prender- on Computer Vision, pages 527–544.  ... 
arXiv:2112.10716v1 fatcat:oqnfato4qrd5jfjm35wu4ipupi

Orientation Keypoints for 6D Human Pose Estimation [article]

Martin Fisch, Ronald Clark
2021 arXiv   pre-print
In The IEEE International [46] Aiden Nibali, Zhen He, Stuart Morgan, and Luke Prendergast. 3d Conference on Computer Vision (ICCV), October 2019.  ... 
arXiv:2009.04930v2 fatcat:bjahcsglunasxdahyitwouwanq