arXiv subjects

Tom Gedeon

Publications and source records attributed to Tom Gedeon.

84 records · Page 5Linked to original sources

arXiv2020

A Token-wise CNN-based Method for Sentence Compression

Sentence compression is a Natural Language Processing (NLP) task aimed at shortening original sentences and preserving their key information. Its applications can benefit many fields e.g. one can build tools for language education. However, current methods are largely based on Recurrent Neural Network (RNN) models which suffer from poor processing speed. To address this issue, in this paper, we propose a token-wise Convolutional Neural Network, a CNN-based model along with pre-trained Bidirectional Encoder Representations from Transformers (BERT) features for deletion-based sentence compression. We also compare our model with RNN-based models and fine-tuned BERT. Although one of the RNN-based models outperforms marginally other models given the same input, our CNN-based model was ten times faster than the RNN-based approach.

cs.CL↗

arXiv2020

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

Mutual information is widely applied to learn latent representations of observations, whilst its implication in classification neural networks remain to be better explained. 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. Through experiments on synthetic and real datasets, we show that softmax cross-entropy can estimate mutual information approximately. When applied to image classification, this relation helps approximate the point-wise mutual information between an input image and a label without modifying the network structure. To this end, we propose infoCAM, informative class activation map, which highlights regions of the input image that are the most relevant to a given label based on differences in information. The activation map helps localise the target object in an input image. Through experiments on the semi-supervised object localisation task with two real-world datasets, we evaluate the effectiveness of our information-theoretic approach.

cs.LG↗

arXiv2020

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

Three-dimensional face reconstruction is one of the popular applications in computer vision. However, even state-of-the-art models still require frontal face as inputs, which restricts its usage scenarios in the wild. A similar dilemma also happens in face recognition. New research designed to recover the frontal face from a single side-pose facial image has emerged. The state-of-the-art in this area is the Face-Transformation generative adversarial network, which is based on the CycleGAN. This inspired our research which explores the performance of two models from pixel transformation in frontal facial synthesis, Pix2Pix and CycleGAN. We conducted the experiments on five different loss functions on Pix2Pix to improve its performance, then followed by proposing a new network Pairwise-GAN in frontal facial synthesis. Pairwise-GAN uses two parallel U-Nets as the generator and PatchGAN as the discriminator. The detailed hyper-parameters are also discussed. Based on the quantitative measurement by face similarity comparison, our results showed that Pix2Pix with L1 loss, gradient difference loss, and identity loss results in 2.72% of improvement at average similarity compared to the default Pix2Pix model. Additionally, the performance of Pairwise-GAN is 5.4% better than the CycleGAN and 9.1% than the Pix2Pix at average similarity.

cs.CV↗

arXiv2020

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

People can manipulate emotion expressions when interacting with others. For example, acted anger can be expressed when stimuli is not genuinely angry with an aim to manipulate the observer. In this paper, we aim to examine if the veracity of anger can be recognized with observers' pupillary data with computational approaches. We use Genetic-based Feature Selection (GFS) methods to select time-series pupillary features of of observers who observe acted and genuine anger of the video stimuli. We then use the selected features to train a simple fully connected neural work and a two-stream neural network. Our results show that the two-stream architecture is able to achieve a promising recognition result with an accuracy of 93.58% when the pupillary responses from both eyes are available. It also shows that genetic algorithm based feature selection method can effectively improve the classification accuracy by 3.07%. We hope our work could help daily research such as human machine interaction and psychology studies that require emotion recognition .

cs.CV↗

arXiv2020

Simulating Content Consistent Vehicle Datasets with Attribute Descent

This paper uses a graphic engine to simulate a large amount of training data with free annotations. Between synthetic and real data, there is a two-level domain gap, i.e., content level and appearance level. While the latter has been widely studied, we focus on reducing the content gap in attributes like illumination and viewpoint. To reduce the problem complexity, we choose a smaller and more controllable application, vehicle re-identification (re-ID). We introduce a large-scale synthetic dataset VehicleX. Created in Unity, it contains 1,362 vehicles of various 3D models with fully editable attributes. We propose an attribute descent approach to let VehicleX approximate the attributes in real-world datasets. Specifically, we manipulate each attribute in VehicleX, aiming to minimize the discrepancy between VehicleX and real data in terms of the Fréchet Inception Distance (FID). This attribute descent algorithm allows content domain adaptation (DA) orthogonal to existing appearance DA methods. We mix the optimized VehicleX data with real-world vehicle re-ID datasets, and observe consistent improvement. With the augmented datasets, we report competitive accuracy. We make the dataset, engine and our codes available at https://github.com/yorkeyao/VehicleX.

cs.CV↗

arXiv2020

Emotion Recognition Through Observer's Physiological Signals

Emotion recognition based on physiological signals is a hot topic and has a wide range of applications, like safe driving, health care and creating a secure society. This paper introduces a physiological dataset PAFEW, which is obtained using movie clips from the Acted Facial Expressions in the Wild (AFEW) dataset as stimuli. To establish a baseline, we use the electrodermal activity (EDA) signals in this dataset and extract 6 features from each signal series corresponding to each movie clip to recognize 7 emotions, i.e., Anger, Disgust, Fear, Happy, Surprise, Sad and Neutral. Overall, 24 observers participated in our collection of the training set, including 19 observers who participated in only one session watching 80 videos from 7 classes and 5 observers who participated multiple times and watched all the videos. All videos were presented in an order balanced fashion. Leave-one-observer-out was employed in this classification task. We report the classification accuracy of our baseline, a three-layer network, on this initial training set while training with signals from all participants, only single participants and only multiple participants. We also investigate the recognition accuracy of grouping the dataset by arousal or valence, which achieves 68.66% and 72.72% separately. Finally, we provide a two-step network. The first step is to classify the features into high/low arousal or positive/negative valence by a network. Then the arousal/valence middle output of the first step is concatenated with feature sets as input of the second step for emotion recognition. We found that adding arousal or valence information can help to improve the classification accuracy. In addition, the information of positive/negative valence boosts the classification accuracy to a higher degree on this dataset.

cs.HC↗

arXiv2019

Predicting Group Cohesiveness in Images

The cohesiveness of a group is an essential indicator of the emotional state, structure and success of a group of people. 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. In order to identify the visual cues (attributes) for cohesion, we conducted a user survey. Image analysis is performed at a group-level via a multi-task convolutional neural network. For analyzing the contribution of facial expressions of the group members for predicting the Group Cohesion Score (GCS), a capsule network is explored. We add GCS to the Group Affect database and propose the `GAF-Cohesion database'. The proposed model performs well on the database and is able to achieve near human-level performance in predicting a group's cohesion score. It is interesting to note that group cohesion as an attribute, when jointly trained for group-level emotion prediction, helps in increasing the performance for the later task. This suggests that group-level emotion and cohesion are correlated.

cs.CV↗

arXiv2018

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

Eye movement patterns reflect human latent internal cognitive activities. We aim to discover eye movement patterns during face recognition under different cognitions of information concealing. These cognitions include the degrees of face familiarity and deception or not, namely telling the truth when observing familiar and unfamiliar faces, and deceiving in front of familiar faces. We apply Hidden Markov models with Gaussian emission to generalize regions and trajectories of eye fixation points under the above three conditions. Our results show that both eye movement patterns and eye gaze regions become significantly different during deception compared with truth-telling. We show the feasibility of detecting deception and further cognitive activity classification using eye movement patterns.

cs.HC↗

arXiv2018

EmotiW 2018: Audio-Video, Student Engagement and Group-Level Affect Prediction

This paper details the sixth Emotion Recognition in the Wild (EmotiW) challenge. EmotiW 2018 is a grand challenge in the ACM International Conference on Multimodal Interaction 2018, Colorado, USA. The challenge aims at providing a common platform to researchers working in the affective computing community to benchmark their algorithms on `in the wild' data. This year EmotiW contains three sub-challenges: a) Audio-video based emotion recognition; b) Student engagement prediction; and c) Group-level emotion recognition. The databases, protocols and baselines are discussed in detail.

cs.CV↗

arXiv2018

Neural Networks Assist Crowd Predictions in Discerning the Veracity of Emotional Expressions

Crowd predictions have demonstrated powerful performance in predicting future events. We aim to understand crowd prediction efficacy in ascertaining the veracity of human emotional expressions. We discover that collective discernment can increase the accuracy of detecting emotion veracity from 63%, which is the average individual performance, to 80%. Constraining data to best performers can further increase the result up to 92%. Neural networks can achieve an accuracy to 99.69% by aggregating participants' answers. That is, assigning positive and negative weights to high and low human predictors, respectively. Furthermore, neural networks that are trained with one emotion data can also produce high accuracies on discerning the veracity of other emotion types: our crowdsourced transfer of emotion learning is novel. We find that our neural networks do not require a large number of participants, particularly, 30 randomly selected, to achieve high accuracy predictions, better than any individual participant. Our proposed method of assembling peoples' predictions with neural networks can provide insights for applications such as fake news prevention and lie detection.

cs.HC↗

arXiv2018

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

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. We study its behavior under classical genetic algorithms. Unlike what we seem to observe in nature, the emergence of modularity is highly conditional and dependent, for example, on the eagerness of search. In nature, modular solutions generally dominate populations, whereas in this domain, modularity, when it emerges, is a relatively rare variant. Emergence of modularity depends heavily on random fluctuations in the fitness function, with a randomly varied but unchanging fitness function, modularity evolved far more rarely. Interestingly, high-fitness non-modular solutions could frequently be converted into even-higher-fitness modular solutions by manually removing all inter-module edges. Despite careful exploration, we do not yet have a full explanation of why the genetic algorithm was unable to find these better solutions.

cs.NE↗

arXiv2016

Risk and Ambiguity in Information Seeking: Eye Gaze Patterns Reveal Contextual Behaviour in Dealing with Uncertainty

Information foraging connects optimal foraging theory in ecology with how humans search for information. The theory suggests that, following an information scent, the information seeker must optimize the tradeoff between exploration by repeated steps in the search space vs. exploitation, using the resources encountered. We conjecture that this tradeoff characterizes how a user deals with uncertainty and its two aspects, risk and ambiguity in economic theory. Risk is related to the perceived quality of the actually visited patch of information, and can be reduced by exploiting and understanding the patch to a better extent. Ambiguity, on the other hand, is the opportunity cost of having higher quality patches elsewhere in the search space. The aforementioned tradeoff depends on many attributes, including traits of the user: at the two extreme ends of the spectrum, analytic and wholistic searchers employ entirely different strategies. The former type focuses on exploitation first, interspersed with bouts of exploration, whereas the latter type prefers to explore the search space first and consume later. Based on an eye-tracking study of experts' interactions with novel search interfaces in the biomedical domain, we demonstrate that perceived risk shifts the balance between exploration and exploitation in either type of users, tilting it against vs. in favour of ambiguity minimization. Since the pattern of behaviour in information foraging is quintessentially sequential, risk and ambiguity minimization cannot happen simultaneously, leading to a fundamental limit on how good such a tradeoff can be. This in turn connects information seeking with the emergent field of quantum decision theory.

cs.IR↗