Mihalis A. Nicolaou

Cyprus Institute

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Stefanos Zafeiriou

Imperial College London

Yannis Panagakis

National and Kapodistrian University of Athens

Maja Pantić

Imperial College London

James Oldfield

Queen Mary University of London

Charles Ringer

University of York

Hatice Güneş

University of Cambridge

Ioannis Patras

Queen Mary University of London

Markos Georgopoulos

Synthesia (Czechia)

Björn W. Schuller

Technical University of Munich

Irene Kotsia

Digital Catapult

Cooperative Institutions

Imperial College London

Cyprus Institute

National and Kapodistrian University of Athens

Universidade Federal do Rio de Janeiro

University of California, San Diego

National Technical University of Athens

Goldsmiths University of London

Massachusetts Institute of Technology

Queen Mary University of London

Aristotle University of Thessaloniki

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Streaming Behaviour: Live Streaming as a Paradigm for Multi-view Analysis of Emotional and Social Signals

Mihalis A. Nicolaou Charles Ringer

Live Streaming

Source

Cite

Citations (3)

Facial Affect “In-the-Wild”: A Survey and a New Database

Stefanos Zafeiriou Athanasios Papaioannou Irene Kotsia Mihalis A. Nicolaou Guoying Zhao

Well-established databases and benchmarks have been developed in the past 20 years for automatic facial behaviour analysis. Nevertheless, for some important problems regarding analysis of facial behaviour, such as (a) estimation of affect in a continuous dimensional space (e.g., valence and arousal) in videos displaying spontaneous facial behaviour and (b) detection of the activated facial muscles (i.e., facial action unit detection), to the best of our knowledge, well-established in-the-wild databases and benchmarks do not exist. That is, the majority of the publicly available corpora for the above tasks contain samples that have been captured in controlled recording conditions and/or captured under a very specific milieu. Arguably, in order to make further progress in automatic understanding of facial behaviour, datasets that have been captured in in the-wild and in various milieus have to be developed. In this paper, we survey the progress that has been recently made on understanding facial behaviour in-the-wild, the datasets that have been developed so far and the methodologies that have been developed, paying particular attention to deep learning techniques for the task. Finally, we make a significant step further and propose a new comprehensive benchmark for training methodologies, as well as assessing the performance of facial affect/behaviour analysis/ understanding in-the-wild. To the best of our knowledge, this is the first time that such a benchmark for valence and arousal "in-the-wild" is presented.

Affect

Benchmark (surveying)

10.1109/cvprw.2016.186

Cite

Citations (41)

Output-associative RVM regression for dimensional and continuous emotion prediction

Image and Vision Computing (2012)

Mihalis A. Nicolaou Hatice Güneş Maja Pantić

Relevance vector machine

Associative property

10.1016/j.imavis.2011.12.005

Cite

Citations (102)

Bilinear Models of Parts and Appearances in Generative Adversarial Networks

IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)

James Oldfield Christos Tzelepis Yannis Panagakis Mihalis A. Nicolaou Ioannis Patras

Recent advances in the understanding of Generative Adversarial Networks (GANs) have led to remarkable progress in visual editing and synthesis tasks, capitalizing on the rich semantics that are embedded in the latent spaces of pre-trained GANs.However, existing methods are often tailored to specific GAN architectures and are limited to either discovering global semantic directions that do not facilitate localized control, or require some form of supervision through manually provided regions or segmentation masks.In this light, we present an architecture-agnostic approach that jointly discovers factors representing spatial parts and their appearances in an entirely unsupervised fashion.These factors are obtained by applying a semi-nonnegative tensor factorization on the feature maps, which in turn enables context-aware local image editing with pixel-level control.In addition, we show that the discovered appearance factors correspond to saliency maps that localize concepts of interest, without using any labels.Experiments on a wide range of GAN architectures and datasets show that, in comparison to the state of the art, our method is far more efficient in terms of training time and, most importantly, provides much more accurate localized control.

Feature (linguistics)

10.1109/tpami.2024.3415506

Cite

Citations (1)

Enhancing Facial Data Diversity with Style-based Face Aging

arXiv (Cornell University) (2020)

Markos Georgopoulos J. E. Oldfield Mihalis A. Nicolaou Yannis Panagakis Maja Pantić

A significant limiting factor in training fair classifiers relates to the presence of dataset bias. In particular, face datasets are typically biased in terms of attributes such as gender, age, and race. If not mitigated, bias leads to algorithms that exhibit unfair behaviour towards such groups. In this work, we address the problem of increasing the diversity of face datasets with respect to age. Concretely, we propose a novel, generative style-based architecture for data augmentation that captures fine-grained aging patterns by conditioning on multi-resolution age-discriminative representations. By evaluating on several age-annotated datasets in both single- and cross-database experiments, we show that the proposed method outperforms state-of-the-art algorithms for age transfer, especially in the case of age groups that lie in the tails of the label distribution. We further show significantly increased diversity in the augmented datasets, outperforming all compared methods according to established metrics.

Discriminative model

Transfer of learning

Generative model

Limiting

10.48550/arxiv.2006.03985

Cite

Citations (0)

Shared-Space Autoencoders with Randomized Skip Connections for Building Footprint Detection with Missing Views

Lecture notes in computer science (2021)

Giannis Ashiotis James Oldfield Charalambos Chrysostomou T. Christoudias Mihalis A. Nicolaou

Autoencoder

Leverage (statistics)

Footprint

Fuse (electrical)

10.1007/978-3-030-68787-8_39

Cite

Citations (1)

Multi-Attribute Probabilistic Linear Discriminant Analysis for 3D Facial Shapes

Lecture notes in computer science (2019)

Stylianos Moschoglou Stylianos Ploumpis Mihalis A. Nicolaou Stefanos Zafeiriou

Discriminative model

10.1007/978-3-030-20893-6_31

Cite

Citations (1)

Dynamic Probabilistic Linear Discriminant Analysis for video classification

Alessandro Fabris Mihalis A. Nicolaou Irene Kotsia Stefanos Zafeiriou

Component Analysis (CA) comprises of statistical techniques that decompose signals into appropriate latent components, relevant to a task-at-hand (e.g., clustering, segmentation, classification). Recently, an explosion of research in CA has been witnessed, with several novel probabilistic models proposed (e.g., Probabilistic Principal CA, Probabilistic Linear Discriminant Analysis (PLDA), Probabilistic Canonical Correlation Analysis). PLDA is a popular generative probabilistic CA method, that incorporates knowledge regarding class-labels and furthermore introduces class-specific and sample-specific latent spaces. While PLDA has been shown to outperform several state-of-the-art methods, it is nevertheless a static model; any feature-level temporal dependencies that arise in the data are ignored. As has been repeatedly shown, appropriate modelling of temporal dynamics is crucial for the analysis of temporal data (e.g., videos). In this light, we propose the first, to the best of our knowledge, probabilistic LDA formulation that models dynamics, the so-called Dynamic-PLDA (DPLDA). DPLDA is a generative model suitable for video classification and is able to jointly model the label information (e.g., face identity, consistent over videos of the same subject), as well as dynamic variations of each individual video. Experiments on video classification tasks such as face and facial expression recognition show the efficacy of the proposed method.

Optimal discriminant analysis

10.1109/icassp.2017.7952663

Cite

Citations (3)

A Wavelet-based Approach for Multimodal Prediction of Alexithymia from Physiological Signals

INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION (2022)

Valeria Filippou Nikolas Theodosiou Mihalis A. Nicolaou Elena Constantinou Georgia Panayiotou

Alexithymia is a trait reflecting a person's difficulty in identifying and expressing their emotions that has been linked to various forms of psychopathology. The identification of alexithymia might have therapeutic, preventive and diagnostic benefits. However, not much research has been done in proposing predictive models for alexithymia, while literature on multimodal approaches is virtually non-existent. In this light, we present, to the best of our knowledge, the first predictive framework that leverages multimodal physiological signals (heart rate, skin conductance level, facial electromyograms) to detect alexithymia. In particular, we develop a set of features that primarily capture spectral-information that is also localized in the time domain via wavelets. Subsequently, simple classifiers are utilized that can learn correlations between features extracted from all modalities. Via several experiments on a novel dataset collected via an emotion processing imagery experiment, we further show that (i) one can detect alexithymia in patients using only one stage of the experiment (elicitation of joy), and (ii) that our simpler framework outperforms compared methods, including deep networks, on the task of alexithymia detection. Our proposed method achieves an accuracy of up to 92% when using simple classifiers on specific imagery tasks. The simplicity and efficiency of our approach makes it suitable for low-powered embedded devices.

Modalities

Discriminative model

10.1145/3536220.3558076

Cite

Citations (3)

Multimodal Joint Emotion and Game Context Recognition in League of Legends Livestreams

arXiv (Cornell University) (2019)

Charles Ringer James Alfred Walker Mihalis A. Nicolaou

Video game streaming provides the viewer with a rich set of audio-visual data, conveying information both with regards to the game itself, through game footage and audio, as well as the streamer's emotional state and behaviour via webcam footage and audio. Analysing player behaviour and discovering correlations with game context is crucial for modelling and understanding important aspects of livestreams, but comes with a significant set of challenges - such as fusing multimodal data captured by different sensors in uncontrolled ('in-the-wild') conditions. Firstly, we present, to our knowledge, the first data set of League of Legends livestreams, annotated for both streamer affect and game context. Secondly, we propose a method that exploits tensor decompositions for high-order fusion of multimodal representations. The proposed method is evaluated on the problem of jointly predicting game context and player affect, compared with a set of baseline fusion approaches such as late and early fusion.

Video game

Affect

Baseline (sea)

Sensor Fusion

10.48550/arxiv.1905.13694

Cite

Citations (0)