Skip to main content
School of Electronic Engineering and Computer Science

Professor Ioannis Patras, BSc MSc ,PhD SMIEEE

Ioannis

Professor of Computer Vision and Human Sensing

Email: i.patras@qmul.ac.uk
Telephone: +44 20 7882 7523
Room Number: Engineering, Eng 211
Website: http://www.eecs.qmul.ac.uk/~ioannisp
Office Hours: Tuesday 14:15-16:15

Teaching

Machine Learning (Postgraduate/Undergraduate)

The aim of the module is to give students an understanding of machine learning methods, including pattern recognition, clustering and neural networks, and to allow them to apply such methods in a range of areas.

Machine Learning for Visual Data Analysis (Postgraduate/Undergraduate)

The module will cover the following topics: The Discrete Fourier Transform and the frequency content of images. The design and use of Gabor filters. Principal Component Analysis for denoising and compression. Unsupervised classification via feature space clustering. Texture segmentation with Gabor filters.

Research

Research Interests:

My research experience lies mainly in the areas of Computer Vision, Image Processing and Pattern Recognition, and their applications in Multimedia Analysis, Visual Communications and Multimodal Man Machine Interaction. My recent research focuses on Human Sensining and Facial And Body Gesture Analysis, Tracking and Recognition.

Keywords: Face and Gesture Recognition, Tracking, Facial (Expression) Analysis, Human Motion Recognition, Behaviour Analysis, Human Sensing, EEG Analysis, Multimedia Indexing.

Publications

  • Kordopatis-Zilos G, Papadopoulos S, Patras I et al. (2019). ViSiL: Fine-grained Spatio-Temporal Video Similarity Learning. International Conference on Computer Vision

    DOI: doi

  • Bishay M, Zoumpourlis G, Patras I (2019). TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition. 30th British Machine Vision Conference

    DOI: doi

  • BISHAY MAT, PATRAS I, PRIEBE S (2019). CAN AUTOMATIC FACIAL EXPRESSION ANALYSIS BE USED FOR TREATMENT OUTCOME ESTIMATION IN SCHIZOPHRENIA?. IEEE International Conference on Acoustics, Speech and Signal Processing


  • Bishay M, PALASEK P, PRIEBE S et al. (2019). SchiNet: Automatic Estimation of Symptoms of Schizophrenia from Facial Behaviour Analysis.. nameOfConference


  • Kordopatis-Zilos G, Papadopoulos S, Patras I et al. (2019). FIVR: Fine-grained Incident Video Retrieval.. nameOfConference


  • Zampoglou M, Markatopoulou F, Mercier G et al. (2019). Detecting Tampered Videos with Multimedia Forensics and Deep Learning. 25th International Conference on MultiMedia Modeling


  • Nixon L, Apostolidis E, Markatopoulou F et al. (2019). Multimodal Video Annotation for Retrieval and Discovery of Newsworthy Video in a News Verification Scenario. 25th International Conference on MultiMedia Modeling


  • Marras I, Palasek P, Patras I (2019). Deep Mixture of MRFs for Human Pose Estimation. nameOfConference


    QMRO: qmroHref
  • Ahmadi A, Marras I, Patras I (2019). LikeNet: A Siamese motion estimation network trained in an unsupervised way. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Andreadis S, Moumtzidou A, Galanopoulos D et al. (2019). Verge in VBS 2019. nameOfConference


    QMRO: qmroHref
  • Miranda Correa JA, Abadi MK, Sebe N et al. (2018). AMIGOS: A Dataset for Affect, Personality and Mood Research on Individuals and Groups. nameOfConference


  • Mou W, Tzelepis C, Mezaris V et al. (2018). A deep generic to specific recognition model for group membership analysis using non-verbal cues. nameOfConference


  • Markatopoulou F, Mezaris V, Patras I (2018). Implicit and Explicit Concept Relations in Deep Neural Networks for Multi-Label Video/Image Annotation. nameOfConference


  • Mioranda-Correa JA, Patras I (2018). A multi-task cascaded network for prediction of affect, personality, mood and social context using EEG signals. nameOfConference


    QMRO: qmroHref
  • Vasilyev A, Hansard M, Mareschal I et al. (2018). A Model of Visual Search in the Presence of Age-Related Macular Degeneration. Proceedings of the AVA Christmas meeting

    DOI: doi

    QMRO: qmroHref
  • Palasek P, Patras I (2018). Semi-supervised Fisher vector network.. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Moumtzidou A, Andreadis S, Markatopoulou F et al. (2018). Verge in VBS 2018. nameOfConference


    QMRO: qmroHref
  • MARRAS I, PALASEK P, PATRAS I (2017). Deep globally constrained MRFs for Human Pose Estimation. IEEE International Conference on Computer Vision (ICCV)


  • TZELEPIS C, PATRAS, MEZARIS, V (2017). Linear Maximum Margin Classifier for Learning from Uncertain Data. nameOfConference


  • KORDOPATIS-ZILOS G, Papadopoulos S, PATRAS I et al. (2017). Near-Duplicate Video Retrieval with Deep Metric Learning. Web-scale Vision and Social Media (VSM), ICCV 2017


  • Tao Y, Palasek P, Ling Z et al. (2017). Background modelling based on generative unet. nameOfConference


    QMRO: qmroHref
  • Jang Y, Gunes H, Patras I (2017). SmileNet: Registration-Free Smiling Face Detection in the Wild. nameOfConference


  • Marras I, Palasek P, Patras I (2017). Deep Refinement Convolutional Networks for Human Pose Estimation. nameOfConference


  • Bishay M, Patras I (2017). Fusing Multilabel Deep Networks for Facial Action Unit Detection. Automatic Face & Gesture Recognition (FG 2017)


  • Mou W, Tzelepis C, Mezaris V et al. (2017). Generic to Specific Recognition Models for Membership Analysis in Group Videos. nameOfConference


    QMRO: qmroHref
  • Galanopoulos D, Markatopoulou F, Mezaris V et al. (2017). Concept language models and event-based concept number selection for zero-example event detection. nameOfConference


    QMRO: qmroHref
  • Markatopoulou F, Galanopoulos D, Mezaris V et al. (2017). Query and keyframe representations for ad-hoc video search. nameOfConference


    QMRO: qmroHref
  • Collyda C, Apostolidis E, Pournaras A et al. (2017). VideoAnalysis4ALL: An on-line tool for the automatic fragmentation and concept-based annotation, and the interactive exploration of videos. nameOfConference


  • Pittaras N, Markatopoulou F, Mezaris V et al. (2017). Comparison of fine-tuning and extension strategies for deep convolutional neural networks. nameOfConference


  • Palasek P, Patras I (2017). Discriminative convolutional Fisher vector network for action recognition.. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Vrochidis S, Patras I, Kompatsiaris I (2017). Gaze movement-driven random forests for query clustering in automatic video annotation. nameOfConference


    QMRO: qmroHref
  • KORDOPATIS-ZILOS G, Papadopoulos S, Patras I et al. (2017). Near-Duplicate Video Retrieval by Aggregating Intermediate CNN Layers. International Conference on Multimedia Modeling


  • Moumtzidou A, Mironidis T, Markatopoulou F et al. (2017). VERGE in VBS 2017. nameOfConference


  • Mou W, Gunes H, Patras I (2016). Automatic Recognition of Emotions and Membership in Group Videos. nameOfConference


    QMRO: qmroHref
  • Mou W, Gunes H, Patras I (2016). Alone versus in-a-group: A comparative analysis of facial affect recognition. nameOfConference


    QMRO: qmroHref
  • Markatopoulou F, Mezaris V, Patras I (2016). Deep multi-task learning with label correlation constraint for video concept detection. nameOfConference


    QMRO: qmroHref
  • AHMADI A, Patras I (2016). UNSUPERVISED CONVOLUTIONAL NEURAL NETWORKS FOR MOTION ESTIMATION. Image Processing (ICIP), 2016 IEEE International Conference on


  • Markatopoulou F, Mezaris V, Patras I (2016). Online multi-task learning for semantic concept detection in video. nameOfConference


    QMRO: qmroHref
  • Ahmadi A, Patras I (2016). Unsupervised convolutional neural networks for motion estimation. nameOfConference


  • Tzelepis C, Mavridaki E, Mezaris V et al. (2016). Video aesthetic quality assessment using kernel Support Vector Machine with isotropic Gaussian sample uncertainty (KSVM-IGSU). nameOfConference


    QMRO: qmroHref
  • Stefic D, Patras I (2016). Action recognition using saliency learned from recorded human gaze. nameOfConference


  • Palasek P, Patras I (2016). Action recognition using convolutional restricted boltzmann machines. nameOfConference


  • Wang L, Patras I, Zhang J et al. (2016). Special Issue on Individual and Group Activities in Video Event Analysis. nameOfConference


    QMRO: qmroHref
  • Tzelepis C, Galanopoulos D, Mezaris V et al. (2016). Learning to detect video events from zero or very few video examples.. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Kuranuki Y, Patras I (2016). Minimal filtered channel features for pedestrian detection. nameOfConference


    QMRO: qmroHref
  • Markatopoulou F, Mezaris V, Patras I (2016). Ordering of visual descriptors in a classifier cascade towards improved video concept detection. nameOfConference


    QMRO: qmroHref
  • Moumtzidou A, Mironidis T, Apostolidis E et al. (2016). Verge: A multimodal interactive search engine for video browsing and retrieval. nameOfConference


  • Tzelepis C, Mezaris V, Patras I (2016). Video event detection using kernel support vector machine with isotropic gaussian sample uncertainty (KSVM-iGSU). nameOfConference


    QMRO: qmroHref
  • Markatopoulou F, Mezaris V, Patras I (2015). Cascade of classifiers based on binary, non-binary and deep convolutional network descriptors for video concept detection. nameOfConference


    QMRO: qmroHref
  • Chen M, Han J, Guo L et al. (2015). Identifying valence and arousal levels via connectivity between EEG channels. nameOfConference


    QMRO: qmroHref
  • Kalpakis G, Tsikrika T, Markatopoulou F et al. (2015). Concept detection in multimedia web resources about home made explosives. nameOfConference


    QMRO: qmroHref
  • Yang H, Patras I (2015). Mirror, mirror on the wall, tell me, is the error small?. nameOfConference


    QMRO: qmroHref
  • Tzelepis C, Galanopoulos D, Mezaris V et al. (2015). Learning to detect video events from zero or very few video examples. nameOfConference


    QMRO: qmroHref
  • Yang H, Jia X, Patras I et al. (2015). Random Subspace Supervised Descent Method for Regression Problems in Computer Vision. nameOfConference


    QMRO: qmroHref
  • Yang H, Patras I (2015). Privileged Information-Based Conditional Structured Output Regression Forest for Facial Point Detection. nameOfConference


  • Yang H, He X, Jia X et al. (2015). Robust face alignment under occlusion via regional predictive power estimation. nameOfConference


  • Palasek P, Yang H, Xu Z et al. (2015). A flexible calibration method of multiple Kinects for 3D human reconstruction. nameOfConference


  • Abadi MK, Correa JAM, Wache J et al. (2015). Inference of personality traits and affect schedule by analysis of spontaneous reactions to affective videos. nameOfConference


    QMRO: qmroHref
  • Abadi MK, Subramanian R, Kia SM et al. (2015). DECAF: MEG-Based Multimodal Database for Decoding Affective Physiological Responses. nameOfConference


    QMRO: qmroHref
  • Yang H, Patras I (2015). Fine-tuning regression forests votes for object alignment in the wild. nameOfConference


  • Markatopoulou F, Pittaras N, Papadopoulou O et al. (2015). A study on the use of a binary local descriptor and color extensions of local descriptors for video concept detection. nameOfConference


  • Yang H, Zou C, Patras I (2015). Cascade of forests for face alignment. nameOfConference


    QMRO: qmroHref
  • Yang H, Mou W, Zhang Y et al. (2015). Face Alignment Assisted by Head Pose Estimation.. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Patras I (2015). Face Pose Analysis.. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Abadi MK, Correa JAM, Wache J et al. (2015). Inference of Personality Traits and Affect Schedule by Analysis of Spontaneous Reactions to Affective Videos. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Markatopoulou F, Mezaris V, Pittaras N et al. (2015). Local Features and a Two-Layer Stacking Architecture for Semantic Concept Detection in Video. nameOfConference


  • Yang H, Patras I (2015). Mirror, mirror on the wall, tell me, is the error small?. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Patras MV, B¿nacu CS, Popescu AM et al. (2015). The effect of limiting the right of appeal on the quality of the public procurement management system: Case study of Romania. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Moumtzidou A, Avgerinakis K, Apostolidis E et al. (2015). VERGE: A multimodal interactive video search engine. nameOfConference

    DOI: doi

  • Stefic D, Patras I (2014). Learning visual saliency using topographic independent component analysis. nameOfConference


    QMRO: qmroHref
  • Yang H, Zou C, Patras I (2014). Face sketch landmarks localization in the wild. nameOfConference


    QMRO: qmroHref
  • Stefic D, Patras I (2014). Learning visual saliency using topographic independent component analysis. nameOfConference


  • Kaymak S, Patras I (2014). Multimodal random forest based tensor regression. nameOfConference


    QMRO: qmroHref
  • Burelli P, Triantafyllidis G, Patras I (2014). Non-invasive player experience estimation from body motion and game context. nameOfConference


    QMRO: qmroHref
  • Jia X, Yang H, Chan K-P et al. (2014). Structured Semi-supervised Forest for Facial Landmarks Localization with Face Mask Reasoning.. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Guo W, Hu W, Boulgouris NV et al. (2013). Semi-supervised visual recognition with constrained graph regularized non negative matrix factorization. nameOfConference


    QMRO: qmroHref
  • Vijay Kumar BG, Patras I (2013). Supervised dictionary learning for action localization. nameOfConference


    QMRO: qmroHref
  • Nikolopoulos S, Zafeiriou S, Patras I et al. (2013). High order pLSA for indexing tagged images. nameOfConference


    QMRO: qmroHref
  • Rudovic O, Pantic M, Patras IY (2013). Coupled Gaussian Processes for Pose-Invariant Facial Expression Recognition. nameOfConference


    QMRO: qmroHref
  • Kaymak S, Patras I (2013). Exploiting depth and intensity information for head pose estimation with random forests and tensor models. nameOfConference


    QMRO: qmroHref
  • Kotsia I, Patras I (2013). Exploring the similarities of neighboring spatiotemporal points for action pair matching. nameOfConference


    QMRO: qmroHref
  • Koelstra S, Patras I (2013). Fusion of facial expressions and EEG for implicit affective tagging. nameOfConference


    QMRO: qmroHref
  • Yang H, Patras I (2013). Privileged information-based Conditional Regression Forests for Facial Feature Detection. nameOfConference


    QMRO: qmroHref
  • Yang H, Patras I (2013). Sieving regression forest votes for facial feature detection in the wild. nameOfConference


    QMRO: qmroHref
  • Kotsia I, Guo W, Patras I (2012). Higher rank support tensor machines for visual recognition. nameOfConference


    QMRO: qmroHref
  • Kotsia I, Guo W, Patras I (2012). Higher rank support tensor machines. nameOfConference


    QMRO: qmroHref
  • Vrochidis S, Patras I, Kompatsiaris I (2012). Exploiting gaze movements for automatic video annotation. nameOfConference


    QMRO: qmroHref
  • Kumar BGV, Patras I (2012). Learning codebook weights for action detection. nameOfConference


    QMRO: qmroHref
  • Chatzilari E, Nikolopoulos S, Patras I et al. (2012). Leveraging social media for scalable object detection. nameOfConference


    QMRO: qmroHref
  • Kotsia I, Patras I, Fotopoulos S (2012). Affective gaming: Beyond using sensors. nameOfConference


    QMRO: qmroHref
  • Nikolopoulos S, Papadopoulos GT, Kompatsiaris I et al. (2012). Image interpretation by combining ontologies and Bayesian networks. nameOfConference


    QMRO: qmroHref
  • Kumar BGV, Kotsia I, Patras I (2012). Max-margin Non-negative Matrix Factorization. nameOfConference


    QMRO: qmroHref
  • Guo W, Kotsia I, Patras I (2012). Tensor learning for regression.. nameOfConference


    QMRO: qmroHref
  • Yang H, Liu X, Patras I (2012). A Simple and Effective Extrinsic Calibration Method of a Camera and a Single Line Scanning Lidar. ICPR 2012

    DOI: doi

    QMRO: qmroHref
  • Yang H, Zhang Y, Liu X et al. (2012). Coupled 3D Tracking and Pose Optimization of Rigid Objects Using Particle Filter. ICPR 2012

    DOI: doi

    QMRO: qmroHref
  • Koelstra S, Muhl C, Soleymani M et al. (2012). DEAP: A Database for Emotion Analysis Using Physiological Signals. nameOfConference


    QMRO: qmroHref
  • Yang H, Patras I (2012). Face Parts Localization Using Structured-output Regression Forests. ACCV 2012


    QMRO: qmroHref
  • Kotsia I, Patras I, IEEE (2012). SUPPORT TENSOR ACTION SPOTTING. nameOfConference


    QMRO: qmroHref
  • Oveisi F, Oveisi S, Efranian A et al. (2012). Tree-Structured Feature Extraction Using Mutual Information. nameOfConference


    QMRO: qmroHref
  • Nikolopoulos S, Papadopoulos GT, Kompatsiaris I et al. (2011). Evidence-driven image interpretation by combining implicit and explicit knowledge in a Bayesian network.. nameOfConference


    QMRO: qmroHref
  • Vrochidis S, Patras I, Kompatsiaris I (2011). An eye-tracking-based approach to facilitate interactive video search. nameOfConference


    QMRO: qmroHref
  • Vrochidis S, Kompatsiaris I, Patras I (2011). Utilizing implicit user feedback to improve interactive video retrieval. nameOfConference


    QMRO: qmroHref
  • Soleymani M, Koelstra S, Patras I et al. (2011). Continuous emotion detection in response to music videos. nameOfConference


    QMRO: qmroHref
  • Oikonomopoulos A, Patras I, Pantic M (2011). Spatiotemporal localization and categorization of human actions in unsegmented image sequences.. nameOfConference


    QMRO: qmroHref
  • Chatzilari E, Nikolopoulos S, Patras I et al. (2011). Enhancing computer vision using the collective intelligence of social media. nameOfConference


    QMRO: qmroHref
  • Nikolopoulos S, Giannakidou E, Kompatsiaris I et al. (2011). Combining Multi-modal Features for Social Media Analysis.. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Guo W, Kotsia I, Patras I (2011). Higher order Support tensor regression for head pose estimation. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Moumtzidou A, Sidiropoulos P, Vrochidis S et al. (2011). ITI-CERTH participation to TRECVID 2011. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Vijay Kumar BG, Kotsia I, Patras I (2011). Max-margin semi-NMF. nameOfConference


    QMRO: qmroHref
  • Kotsia I, Patras I (2011). Support Tucker Machines. nameOfConference


    QMRO: qmroHref
  • Oikonomopoulos A, Patras I, Pantic M (2010). Discriminative space-time voting for joint recognition and localization of actions. nameOfConference


    QMRO: qmroHref
  • Kotsia I, Patras I (2010). Multiplicative update rules for multilinear support tensor machines. nameOfConference


    QMRO: qmroHref
  • Rudovic O, Patras I, Pantic M (2010). Regression-based multi-view facial expression recognition. nameOfConference


    QMRO: qmroHref
  • Koelstra S, Pantic M, Patras I (2010). A Dynamic Texture-Based Approach to Recognition of Facial Actions and Their Temporal Models. nameOfConference


    QMRO: qmroHref
  • Rudovic O, Patras I, Pantic M (2010). Facial expression invariant head pose normalization using Gaussian Process Regression. nameOfConference


    QMRO: qmroHref
  • Passino G, Patras I, Izquierdo E (2010). Aspect coherence for graph-based semantic image labelling. nameOfConference


    QMRO: qmroHref
  • Patras I, Hancock ER (2010). Coupled Prediction Classification for Robust Visual Tracking. nameOfConference


    QMRO: qmroHref
  • Vrochidis S, Kompatsiaris I, Patras I (2010). Optimizing visual search with implicit user feedback in interactive video retrieval. nameOfConference


    QMRO: qmroHref
  • Kotsia I, Patras I (2010). Relative Margin Support Tensor Machines for gait and action recognition. nameOfConference


    QMRO: qmroHref
  • Passino G, Patras I, Izquierdo E (2010). Pyramidal Model for Image Semantic Segmentation. ICPR 2010


    QMRO: qmroHref
  • Koelstra S, Pantic M, Patras I (2010). A Dynamic Texture-Based Approach to Recognition of Facial Actions and Their Temporal Models. nameOfConference


    QMRO: qmroHref
  • Kumar.B.G V, Patras I (2010). A discriminative voting scheme for object detection using hough forests. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Rudovic O, Patras I, Pantic M (2010). Coupled Gaussian Process Regression for Pose-Invariant Facial Expression Recognition. nameOfConference


    QMRO: qmroHref
  • Rudovic O, Patras I, Pantic M (2010). Coupled Gaussian process regression for pose-invariant facial expression recognition. nameOfConference


    QMRO: qmroHref
  • Vrochidis S, Kompatsiaris I, Patras I (2010). Exploiting implicit user feedback in interactive video retrieval.. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Guo W, Patras I (2010). Learning output-kernel-dependent regression for human pose estimation. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Koelstra S, Yazdani A, Soleymani M et al. (2010). Single Trial Classification of EEG and Peripheral Physiological Signals for Recognition of Emotions Induced by Music Videos. nameOfConference


    QMRO: qmroHref
  • Guo W, Patras I (2009). Discriminative 3D human pose estimation from monocular images via topological preserving hierarchical affinity clustering. nameOfConference


    QMRO: qmroHref
  • Koelstra S, Mühl C, Patras I (2009). EEG analysis for implicit tagging of video data. nameOfConference


    QMRO: qmroHref
  • Oikonomopoulos A, Patras I, Pantic M (2009). An implicit spatiotemporal shape model for human activity localization and recognition. nameOfConference


    QMRO: qmroHref
  • Oikonomopoulos A, Pantic M, Patras I (2009). Sparse B-spline polynomial descriptors for human activity recognition. nameOfConference


    QMRO: qmroHref
  • Passino G, Patras I, Izquierdo E (2009). Latent Semantics Local Distribution for CRF-based Image Semantic Segmentation. BMVC 2009


    QMRO: qmroHref
  • Passino G, Piatrik T, Patras I et al. (2009). A Multimedia Content Semantics Extraction Framework for Enhanced Social Interaction. EuroITV 2009

    DOI: doi

    QMRO: qmroHref
  • Oikonomopoulos A, Patras I, Pantic M (2009). An implicit spatiotemporal shape model for human activity localization and recognition. 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)


    QMRO: qmroHref
  • Nikolopoulos S, Papadopoulos GT, Kompatsiaris I et al. (2009). An Evidence-Driven Probabilistic Inference Framework for Semantic Image Understanding. nameOfConference


    QMRO: qmroHref
  • Oikonomopoulos A, Patras I, Pantic M (2009). An Implicit Spatiotemporal Shape Model for Human Activity Localization and Recognition. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Passino G, Patras I, Izquierdo E (2009). CONTEXT AWARENESS IN GRAPH-BASED IMAGE SEMANTIC SEGMENTATION VIA VISUAL WORD DISTRIBUTIONS. nameOfConference


    QMRO: qmroHref
  • Patras I (2009). Face Pose Analysis.. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Koelstra S, Patras I (2009). THE FAST-3D SPATIO-TEMPORAL INTEREST REGION DETECTOR. nameOfConference


    QMRO: qmroHref
  • Oikonomopoulos A, Pantic M, Patras I (2008). Human Gesture Recognition using Sparse B-spline Polynomial Representations. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Andreopoulos Y, Patras I (2008). Incremental refinement of image salient-point detection.. nameOfConference


    QMRO: qmroHref
  • Passino G, Patras I, Izquierdo E (2008). Aspect Coherence for Graph-Based Image Labelling. VIE 2008


    QMRO: qmroHref
  • Oikonomopoulos A, Pantic M, Patras I (2008). B-spline Polynomial Descriptors for Human Activity Recognition. nameOfConference


    QMRO: qmroHref
  • Oikonomopoulos A, Pantic M, Patras I (2008). B-spline polynomial descriptors for human activity recognition.. nameOfConference


    QMRO: qmroHref
  • Patras I, Andreopoulos Y (2008). Incremental salient point detection. nameOfConference


    QMRO: qmroHref
  • Passino G, Patras I, Izquierdo E (2008). ON THE ROLE OF STRUCTURE IN PART-BASED OBJECT DETECTION. nameOfConference


    QMRO: qmroHref
  • PATRAS I, Lagendijk RL, Hendriks EA (2007). Bayesian Confidence Measures for Block-based Motion Estimation. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Patras I, Hendriks EA, Lagendijk RL (2007). Probabilistic confidence measures for block matching motion estimation. nameOfConference


    QMRO: qmroHref
  • PATRAS I, Hancock ER (2007). Regression-ased Template Tracking in Presence of Occlusions. International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS), Santorini, Greece


    QMRO: qmroHref
  • Pogalin E, Redert A, Patras I et al. (2007). Gaze tracking by using factorized likelihoods particle filtering and stereo vision. nameOfConference


    QMRO: qmroHref
  • PATRAS I, Paragios N, Oikonomopoulos A et al. (2007). Particle Filtering Tracking Scheme for Trajectory-based Recognition of Human Actions. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Patras I, Hancock ER (2007). Regression tracking with data relevance determination. nameOfConference


    QMRO: qmroHref
  • Patras I, Hancock E (2007). Template tracking with observation relevance determination. nameOfConference


    QMRO: qmroHref
  • Oikonomopoulos A, Patras I, Pantic M et al. (2007). Trajectory-based representation of human actions. nameOfConference


    QMRO: qmroHref
  • PATRAS I, Pantic M, Oikonomopoulos A (2006). Kernel-based Recognition of Human Actions Using Spatiotemporal Salient Points. Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, Workshop on Vision for HCI, New York, USA - June 2006


    QMRO: qmroHref
  • Oikonomopoulos A, Patras I, Pantic M (2006). Spatiotemporal salient points for visual recognition of human actions.. nameOfConference


    QMRO: qmroHref
  • Pantic M, Patras I (2006). Dynamics of facial expression: recognition of facial actions and their temporal segments from face profile image sequences.. nameOfConference


    QMRO: qmroHref
  • Diplaros A, Gevers T, Patras I (2006). Combining color and shape information for illumination-viewpoint invariant object recognition.. nameOfConference


    QMRO: qmroHref
  • PATRAS I, Valstar MF, Pantic M (2005). Learning Spatiotemporal Models of Facial Expressions. International Conference on Measuring Behaviour, Wageningen - September 2005

    DOI: doi

    QMRO: qmroHref
  • PATRAS I, Pantic M, Valstar MF (2005). Facial Action Unit Detection Using Probabilistically Actively Learned Support Vector Machines on Tracked Facial Point Data. Proceedings of IEEE International Confernece on Computer Visision and Pattern Recognition, workshop on Vision for HCI, San Diego, USA - June 2005


    QMRO: qmroHref
  • Pantic M, Patras I (2005). Detecting facial actions and their temporal segments in nearly frontal-view face image sequences. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Oikonomopoulos A, Patras I, Pantic M (2005). Spatiotemporal saliency for human action recognition. nameOfConference


    QMRO: qmroHref
  • Patras I, Pantic M (2005). Tracking deformable motion. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Patras I, Worring M, van den Boomgaard R (2004). Dense motion estimation using regularization constraints on local parametric models.. nameOfConference


    QMRO: qmroHref
  • PATRAS I, Pantic M, Valstar M (2004). Multilevel Motion History for Facial Action Detection from Face Video. IEEE International Conference on Systems, Management and Cybernetics, Den Haag, The Netherlands - October 2005

    DOI: doi

    QMRO: qmroHref
  • Diplaros A, Gevers T, Patras I (2004). Combining color and shape information for content-based image retrieval on the Internet. nameOfConference


    QMRO: qmroHref
  • Valstar M, Patras I, Pantic M (2004). Facial action unit recognition using temporal templates. nameOfConference


    QMRO: qmroHref
  • Winkelman F, Patras I (2004). Online globally consistent mosaicing using an efficient representation. nameOfConference


    QMRO: qmroHref
  • Patras I, Pantic M (2004). Particle filtering with factorized likelihoods for tracking facial features. nameOfConference


    QMRO: qmroHref
  • Pantic M, Patras I (2004). Temporal modeling of facial actions from face profile image sequences. nameOfConference


    QMRO: qmroHref
  • PATRAS I, Gevers T, Diplaros A (2003). Color-Shape Context for Object Recognition. IEEE Workshop on Color and Photometric Methods in Computer Vision (in conjunction with ICCV 2003), Nice, France

    DOI: doi

    QMRO: qmroHref
  • Patras I, Hendriks EA, Lagendijk RL (2003). Semi-automatic object-based video segmentation with labeling of color segments. nameOfConference


    QMRO: qmroHref
  • PATRAS I, Raaijmakers S, Snoek C et al. (2002). TREC Feature Extraction by Active Learning. 11th Text Retrieval Confernece (TREC), Gaithersburg, MD - November 2002

    DOI: doi

    QMRO: qmroHref
  • Patras I, Hendriks EA, Lagendijk RL (2002). Confidence measures for block matching motion estimation. nameOfConference

    DOI: doi

    QMRO: qmroHref
  • Pantic M, Patras I, Rothkrantz L (2002). Facial action recognition in face profile image sequences. nameOfConference


    QMRO: qmroHref
  • Patras I, Worring M (2002). Regularized patch motion estimation. nameOfConference


    QMRO: qmroHref
  • Patras I, Hendriks EA, Lagendijk RL (2001). Video segmentation by MAP labeling of watershed segments. nameOfConference


    QMRO: qmroHref
  • PATRAS I, List J, Geusebroek J-M et al. (2001). Lazy Users and Automatic Video Retrieval Tools in (the) Lowlands. Proceedings of the 10th Text Retrieval Conference (TREC), NIST 2001

    DOI: doi

    QMRO: qmroHref
  • PATRAS I, Hendriks EA, Broekhoven M et al. (2001). Robust Region Merging for Motion Based Sementation Using the Kolmogorov-Smirnov Test. nameOfConference

    DOI: doi

    QMRO: qmroHref