Search Results for author: Tom Gedeon

Found 39 papers, 17 papers with code

Optimizing Camera Configurations for Multi-View Pedestrian Detection

no code implementations4 Dec 2023 Yunzhong Hou, Xingjian Leng, Tom Gedeon, Liang Zheng

Jointly considering multiple camera views (multi-view) is very effective for pedestrian detection under occlusion.

Pedestrian Detection

Adaptive Multi-head Contrastive Learning

no code implementations9 Oct 2023 Lei Wang, Piotr Koniusz, Tom Gedeon, Liang Zheng

As such, enforcing a high similarity for positive pairs and a low similarity for negative pairs may not always be achievable, and in the case of some pairs, forcing so may be detrimental to the performance.

Contrastive Learning

Training with Product Digital Twins for AutoRetail Checkout

1 code implementation18 Aug 2023 Yue Yao, Xinyu Tian, Zheng Tang, Sujit Biswas, Huan Lei, Tom Gedeon, Liang Zheng

Because the digital twins individually mimic user bias, the resulting DT training set better reflects the characteristics of the target scenario and allows us to train more effective product detection and tracking models.

Pavlok-Nudge: A Feedback Mechanism for Atomic Behaviour Modification with Snoring Usecase

no code implementations10 May 2023 Shreya Ghosh, Rakibul Hasan, Pradyumna Agrawal, Zhixi Cai, Susannah Soon, Abhinav Dhall, Tom Gedeon

To this end, we design a user interface to generate an automatic feedback mechanism that integrates Pavlok and a deep learning based model to detect certain behaviours via an integrated user interface i. e. mobile or desktop application.

Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization

1 code implementation3 May 2023 Zhixi Cai, Shreya Ghosh, Abhinav Dhall, Tom Gedeon, Kalin Stefanov, Munawar Hayat

The proposed baseline method, Boundary Aware Temporal Forgery Detection (BA-TFD), is a 3D Convolutional Neural Network-based architecture which effectively captures multimodal manipulations.

Binary Classification DeepFake Detection +2

Large-scale Training Data Search for Object Re-identification

1 code implementation CVPR 2023 Yue Yao, Huan Lei, Tom Gedeon, Liang Zheng

We consider a scenario where we have access to the target domain, but cannot afford on-the-fly training data annotation, and instead would like to construct an alternative training set from a large-scale data pool such that a competitive model can be obtained.


A Bag-of-Prototypes Representation for Dataset-Level Applications

no code implementations CVPR 2023 Weijie Tu, Weijian Deng, Tom Gedeon, Liang Zheng

The former measures how suitable a training set is for a target domain, while the latter studies how challenging a test set is for a learned model.

Deep transfer learning for image classification: a survey

no code implementations20 May 2022 Jo Plested, Tom Gedeon

We show that under this new taxonomy, many of the applications where transfer learning has been shown to be ineffective or even hinder performance are to be expected when taking into account the source and target datasets and the techniques used.

Classification Image Classification +1

Attribute Descent: Simulating Object-Centric Datasets on the Content Level and Beyond

2 code implementations28 Feb 2022 Yue Yao, Liang Zheng, Xiaodong Yang, Milind Napthade, Tom Gedeon

This article aims to use graphic engines to simulate a large number of training data that have free annotations and possibly strongly resemble to real-world data.

Data Augmentation Image Classification

How to Synthesize a Large-Scale and Trainable Micro-Expression Dataset?

1 code implementation3 Dec 2021 Yuchi Liu, Zhongdao Wang, Tom Gedeon, Liang Zheng

To this end, we develop a protocol to automatically synthesize large scale MiE training data that allow us to train improved recognition models for real-world test data.

Face Generation Micro-Expression Recognition

Feature Selection on Thermal-stress Dataset

no code implementations8 Sep 2021 Xuyang Shen, Jo Plested, Tom Gedeon

These findings are likely to improve the accuracy of current stress recognition systems.

feature selection

Exploring Biases and Prejudice of Facial Synthesis via Semantic Latent Space

no code implementations23 Aug 2021 Xuyang Shen, Jo Plested, Sabrina Caldwell, Tom Gedeon

Varying the proportions of male and female faces in the training data can have a substantial effect on behavior on the test data: we found that the seemingly obvious choice of 50:50 proportions was not the best for this dataset to reduce biased behavior on female faces, which was 71% unbiased as compared to our top unbiased rate of 84%.

Neural Network Classifier as Mutual Information Evaluator

no code implementations19 Jun 2021 Zhenyue Qin, Dongwoo Kim, Tom Gedeon

We give a new view of neural network classifiers with softmax and cross-entropy as mutual information evaluators.

Disentangling Noise from Images: A Flow-Based Image Denoising Neural Network

1 code implementation11 May 2021 Yang Liu, Saeed Anwar, Zhenyue Qin, Pan Ji, Sabrina Caldwell, Tom Gedeon

The prevalent convolutional neural network (CNN) based image denoising methods extract features of images to restore the clean ground truth, achieving high denoising accuracy.

Disentanglement Image Denoising

Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition

1 code implementation4 May 2021 Zhenyue Qin, Yang Liu, Pan Ji, Dongwoo Kim, Lei Wang, Bob McKay, Saeed Anwar, Tom Gedeon

Recent skeleton-based action recognition methods extract features from 3D joint coordinates as spatial-temporal cues, using these representations in a graph neural network for feature fusion to boost recognition performance.

Action Recognition Skeleton Based Action Recognition

S2FGAN: Semantically Aware Interactive Sketch-to-Face Translation

1 code implementation30 Nov 2020 Yan Yang, Md Zakir Hossain, Tom Gedeon, Shafin Rahman

Instead of constraining the translation process by using a reference image, the users can command the model to retouch the generated images by involving the semantic information in the generation process.

Image Generation Image Manipulation +1

Disguising Personal Identity Information in EEG Signals

1 code implementation18 Oct 2020 Shiya Liu, Yue Yao, Chaoyue Xing, Tom Gedeon

The personal identity information in original EEGs are transformed into disguised ones with a CycleGANbased EEG disguising model.

EEG Electroencephalogram (EEG)

Analogical and Relational Reasoning with Spiking Neural Networks

no code implementations14 Oct 2020 Rollin Omari, R. I. McKay, Tom Gedeon

To illustrate this, we first investigate the performance of our networks with supervised learning, then with unsupervised learning.

Relational Reasoning

RealSmileNet: A Deep End-To-End Network for Spontaneous and Posed Smile Recognition

no code implementations7 Oct 2020 Yan Yang, Md Zakir Hossain, Tom Gedeon, Shafin Rahman

Smiles play a vital role in the understanding of social interactions within different communities, and reveal the physical state of mind of people in both real and deceptive ways.

Feature Engineering Smile Recognition

A Token-wise CNN-based Method for Sentence Compression

no code implementations23 Sep 2020 Weiwei Hou, Hanna Suominen, Piotr Koniusz, Sabrina Caldwell, Tom Gedeon

Sentence compression is a Natural Language Processing (NLP) task aimed at shortening original sentences and preserving their key information.

Sentence Compression

Pairwise-GAN: Pose-based View Synthesis through Pair-Wise Training

1 code implementation13 Sep 2020 Xuyang Shen, Jo Plested, Yue Yao, Tom Gedeon

This inspired our research which explores the performance of two models from pixel transformation in frontal facial synthesis, Pix2Pix and CycleGAN.

Face Reconstruction Novel View Synthesis

Are Deep Neural Architectures Losing Information? Invertibility Is Indispensable

1 code implementation7 Sep 2020 Yang Liu, Zhenyue Qin, Saeed Anwar, Sabrina Caldwell, Tom Gedeon

Identifying the information lossless condition for deep neural architectures is important, because tasks such as image restoration require keep the detailed information of the input data as much as possible.

Image Denoising Image Inpainting +1

A Genetic Feature Selection Based Two-stream Neural Network for Anger Veracity Recognition

no code implementations6 Sep 2020 Chaoxing Huang, Xuanying Zhu, Tom Gedeon

For example, acted anger can be expressed when stimuli is not genuinely angry with an aim to manipulate the observer.

Emotion Recognition feature selection +2

Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator

1 code implementation25 Nov 2019 Zhenyue Qin, Dongwoo Kim, Tom Gedeon

We show that optimising the parameters of classification neural networks with softmax cross-entropy is equivalent to maximising the mutual information between inputs and labels under the balanced data assumption.

Classification Fine-Grained Image Classification +2

Predicting Group Cohesiveness in Images

no code implementations31 Dec 2018 Shreya Ghosh, Abhinav Dhall, Nicu Sebe, Tom Gedeon

We study the factors that influence the perception of group-level cohesion and propose methods for estimating the human-perceived cohesion on the group cohesiveness scale.

Your Eyes Say You're Lying: An Eye Movement Pattern Analysis for Face Familiarity and Deceptive Cognition

no code implementations8 Nov 2018 Jiaxu Zuo, Tom Gedeon, Zhenyue Qin

Eye movement patterns reflect human latent internal cognitive activities.

Human-Computer Interaction

Why don't the modules dominate - Investigating the Structure of a Well-Known Modularity-Inducing Problem Domain

no code implementations11 Jul 2018 Zhenyue Qin, Robert McKay, Tom Gedeon

Wagner's modularity inducing problem domain is a key contribution to the study of the evolution of modularity, including both evolutionary theory and evolutionary computation.

EPUTION at SemEval-2018 Task 2: Emoji Prediction with User Adaption

no code implementations SEMEVAL 2018 Liyuan Zhou, Qiongkai Xu, Hanna Suominen, Tom Gedeon

This paper describes our approach, called EPUTION, for the open trial of the SemEval- 2018 Task 2, Multilingual Emoji Prediction.

General Classification Task 2 +4

Cannot find the paper you are looking for? You can Submit a new open access paper.