A5105769246- Face recognition and analysis
- Face and Expression Recognition
- Emotion and Mood Recognition
- Human Pose and Action Recognition
- Biometric Identification and Security
- Video Surveillance and Tracking Methods
- Image Retrieval and Classification Techniques
- Visual Attention and Saliency Detection
- Human Mobility and Location-Based Analysis
- Context-Aware Activity Recognition Systems
- Gaze Tracking and Assistive Technology
- Social Robot Interaction and HRI
- Speech and Audio Processing
- Generative Adversarial Networks and Image Synthesis
- Speech Recognition and Synthesis
- Advanced Image and Video Retrieval Techniques
- Music and Audio Processing
- Hand Gesture Recognition Systems
- Aesthetic Perception and Analysis
- Mental Health Research Topics
- Face Recognition and Perception
- Video Analysis and Summarization
- Gait Recognition and Analysis
- Machine Learning and ELM
- Innovative Human-Technology Interaction
Utrecht University
2019-2024
University of Jyväskylä
2024
University of Minnesota
2024
Boğaziçi University
2014-2023
Michigan State University
2023
Universitas Nusa Nipa Maumere
2022
Alliance Data (United States)
2020
Yeditepe University
2019
Bilkent University
2019
Moscow State University
2019
The Audio/Visual Emotion Challenge and Workshop (AVEC 2018) "Bipolar disorder, cross-cultural affect recognition'' is the eighth competition event aimed at comparison of multimedia processing machine learning methods for automatic audiovisual health emotion analysis, with all participants competing strictly under same conditions. goal to provide a common benchmark test set multimodal information bring together recognition communities, as well compare relative merits various approaches from...
Kinship verification from facial appearance is a difficult problem. This paper explores the possibility of employing expression dynamics in this By using features that describe and spatio-temporal over smile expressions, we show it possible to improve state art problem, verify indeed recognize kinship by resemblance expressions. The proposed method tested on different kin relationships. On average, 72.89% accuracy achieved spontaneous smiles.
This paper describes how mobile phone data can guide government and public health authorities in determining the best course of action to control COVID-19 pandemic assessing effectiveness measures such as physical distancing. It identifies key gaps reasons why this kind is only scarcely used, although their value similar epidemics has proven a number use cases. presents ways overcome these recommendations for urgent action, most notably establishment mixed expert groups on national regional...
Estimating the age of a human from captured images his/her face is challenging problem. In general, existing approaches to this problem use appearance features only. paper, we show that in addition information, facial dynamics can be leveraged estimation. We propose method extract and dynamic for estimation, using person's smile. Our approach tested on large, gender-balanced database with 400 subjects, an range between 8 76. addition, introduce new posed disgust expressions 324 subjects same...
Automatic distinction between genuine (spontaneous) and posed expressions is important for visual analysis of social signals. In this paper, we describe an informative set features the face dynamics, propose a completely automatic system to distinguish enjoyment smiles. Our incorporates facial landmarking tracking, through which are extracted dynamics eyelid, cheek, lip corner movements. By fusing over different regions, as well temporal phases smile, obtain very accurate smile classifier....
The intermittent nature of solar irradiance, primarily due to cloud movements, leads rapid short-term fluctuations in the power output photovoltaic (PV) systems. These pose a significant challenge for integrating this renewable energy source into grid. Accurate forecasting irradiance is not only crucial but also multi-beneficial. It enables more precise grid management by allowing operators anticipate and adjust distribution storage strategies accordingly. This proactive approach reduces...
Parallel pattern recognition requires great computational resources; it is NP-complete. From an engineering point of view desirable to achieve good performance with limited resources. For this purpose, we develop a serial model for visual based on the primate selective attention mechanism. The idea in that not all parts image give us information. If can attend only relevant parts, recognize more quickly and using less We simulate primitive, bottom-up attentive level human system saliency...
Automatically verifying the identity of a person by means biometrics is an important application in day-to-day activities such as accessing banking services and security control airports. To increase system reliability, several biometric devices are often used. Such combined known multimodal system. This paper reports benchmarking study carried out within framework BioSecure DS2 (Access Control) evaluation campaign organized University Surrey, involving face, fingerprint, iris for...
This paper presents our work on ACM MM Audio Visual Emotion Corpus 2014 (AVEC 2014) using the baseline features in accordance with challenge protocol. For prediction, we use Canonical Correlation Analysis (CCA) affect sub-challenge (ASC) and Moore-Penrose generalized inverse (MPGI) depression (DSC). The video provides histograms of Local Gabor Binary Patterns from Three Orthogonal Planes (LGBP-TOP) features. Based preliminary experiments AVEC 2013 data, focus inner facial regions that...
We propose a two-level system for apparent age estimation from facial images. Our first classifies samples into overlapping groups. Within each group, the is estimated with local regressors, whose outputs are then fused final estimate. use deformable parts model based face detector, and features pretrained deep convolutional network. Kernel extreme learning machines used classification. evaluate our on ChaLearn Looking at People 2016 - Apparent Age Estimation challenge dataset, report 0.3740...
Explainability and interpretability are two critical aspects of decision support systems. Despite their importance, it is only recently that researchers starting to explore these aspects. This paper provides an introduction explainability in the context apparent personality recognition. To best our knowledge, this first effort direction. We describe a challenge we organized on impressions analysis from video. analyze detail newly introduced data set, evaluation protocol, proposed solutions...
Abstract Advances in animal motion tracking and pose recognition have been a game changer the study of behavior. Recently, an increasing number works go ‘deeper’ than tracking, address automated animals’ internal states such as emotions pain with aim improving welfare, making this timely moment for systematization field. This paper provides comprehensive survey computer vision-based research on emotional animals, addressing both facial bodily behavior analysis. We summarize efforts that...
Automatic localization of 3D facial features is important for face recognition, tracking, modeling and expression analysis. Methods developed 2D images were shown to have problems working across databases acquired with different illumination conditions. Expression variations, pose variations occlusions also hamper accurate detection landmarks. In this paper we assess a fully automatic landmarking algorithm that relies on statistical features. This can be employed model any landmark, provided...
Joint attention, which is the ability of coordination a common point reference with communicating party, emerges as key factor in various interaction scenarios. This paper presents an image-based method for establishing joint attention between experimenter and robot. The precise analysis experimenter's eye region requires stability high-resolution image acquisition, not always available. We investigate regression-based interpolation gaze direction from head pose experimenter, easier to...
This paper presents our contribution to ACM ICMI 2015 Emotion Recognition in the Wild Challenge (EmotiW 2015). We participate both static facial expression (SFEW) and audio-visual emotion recognition challenges. In challenges, we use a set of visual descriptors their early late fusion schemes. For AFEW, also exploit popularly used spatio-temporal modeling alternatives carry out multi-modal fusion. classification, employ two least squares regression based learners that are shown be fast...
In this study we make use of Canonical Correlation Analysis (CCA) based feature selection for continuous depression recognition from speech. Besides its common in multi-modal/multi-view extraction, CCA can be easily employed as a selector. We introduce several novel ways filter (ranking) methods, showing their relations to previous work. test the suitability proposed methods on AVEC 2013 dataset under ACM MM Challenge protocol. Using 17% features, obtained relative improvement 30%...
Computational Paralinguistics has several unresolved issues, one of which is coping with large variability due to speakers, spoken content and corpora. In this paper, we address the compensation issue by proposing a novel method composed i) Fisher vector encoding low level descriptors extracted from signal, ii) speaker z-normalization applied after clustering iii) non-linear normalization features iv) classification based on Kernel Extreme Learning Machines Partial Least Squares regression....