Research

Machine Learning, Computer Vision, Signal Processing, neuro-physiological signals, Sensing

Interests

My research is in the area of ‘’Looking at /Sensing People’’, using Machine Learning, Computer Vision and Signal Processing methodologies to interpret and predict actions, behaviour, emotions and cognitive states of people by analysing their images, video and neuro-physiological signals. This includes detection, tracking and recognition of facial and body gestures in unconstrained environments. I have more than 200 publications in the most selective Journals and conferences in the field of Computer Vision, an h-index of 33, and more than 5000 citations. I am associate editor in the journals of Pattern Recognition, Computer Vision and Image Understanding, and Image and Vision Computing, and area chair or in the programme committee of all the major conferences in the field. My research has been funded by the EPSRC, EU FP7 and direct bilateral collaborations with research institutes and the industry.

Publications

Publications of specific relevance to Applied Data Science

2021

Loko J, Skopal T, Schoeffmann K, Mezaris V, Li X, Vrochidis S and Patras I (2021). Preface.

2020

Apostolidis E, Adamantidou E, Metsai A, Mezaris V and Patras I (2020). AC-SUM-GAN: Connecting Actor-Critic and Generative Adversarial Networks for Unsupervised Video Summarization. Institute of Electrical and Electronics Engineers  Ieee Transactions On Circuits and Systems For Video Technology  10.1109/TCSVT.2020.3037883

Xie T-T, Tzelepis C and Patras I (2020). Temporal Action Localization with Variance-Aware Networks. Corr  vol. abs/2008.11254,

Xie T, Tzelepis C and Patras I (2020). Boundary Uncertainty in a Single-Stage Temporal Action Localization Network. Corr  vol. abs/2008.11170,

2019

Apostolidis E, Apostolidis K, Patras I and Mezaris V (2019). Video Fragmentation and Reverse Search on the Web. Video Verification in The Fake News Era , Editors: Mezaris V, Nixon L, Papadopoulos S and Teyssou D. Springer, Cham  10.1007/978-3-030-26752-0_3

MARKATOPOULOU F, Zampoglou M, Apostolidis E, Papadopoulos S, Mezaris V, Patras I and Kompatsiaris I (2019). Finding Semantically Related Videos in Closed Collections. Video Verification in The Fake News Era , Editors: Mezaris V, Nixon L, Papadopoulos S and Teyssou D. Springer, Cham  10.1007/978-3-030-26752-0_5

Mercier G, MARKATOPOULOU F, Cozien R, Zampoglou M, Apostolidis E, Metsai A, Papadopoulos S, Mezaris V, Patras I and Kompatsiaris I (2019). Detecting Manipulations in Video. Video Verification in The Fake News Era , Editors: Mezaris V, Nixon L, Papadopoulos S and Teyssou D. Springer, Cham  10.1007/978-3-030-26752-0_6

Kordopatis-Zilos G, Papadopoulos S, Patras I and Kompatsiaris I (2019). Finding Near-Duplicate Videos in Large-Scale Collections. Video Verification in The Fake News Era , Editors: Mezaris V, Nixon L, Papadopoulos S and Teyssou D. Springer  10.1007/978-3-030-26752-0_4

Mou W, Gunes H and Patras I (2019). Alone versus in-a-group: A multi-modal framework for automatic affect recognition. Acm Transactions On Multimedia Computing, Communications and Applications  vol. 15, (2) 10.1145/3321509

Jang Y, Gunes H and Patras I (2019). Registration-free Face-SSD: Single shot analysis of smiles, facial attributes, and affect in the wild. Computer Vision and Image Understanding  vol. 182, 17-29. 10.1016/j.cviu.2019.01.006

Bishay M, PALASEK P, PRIEBE S and Patras I (2019). SchiNet: Automatic Estimation of Symptoms of Schizophrenia from Facial Behaviour Analysis. Ieee Transactions On Affective Computing  10.1109/TAFFC.2019.2907628

Kordopatis-Zilos G, Papadopoulos S, Patras I and Kompatsiaris I (2019). FIVR: Fine-grained Incident Video Retrieval. Institute of Electrical and Electronics Engineers  Ieee Transactions On Multimedia  vol. 21, (10) 2638-2652. 10.1109/TMM.2019.2905741

Kordopatis-Zilos G, Papadopoulos S, Patras I and Kompatsiaris I (2019). FIVR: Fine-Grained Incident Video Retrieval. Ieee Trans. Multim.  vol. 21, 2638-2652.

Mou W, Gunes H and Patras I (2019). Alone versus In-a-group: A Multi-modal Framework for Automatic Affect Recognition. Acm Trans. Multim. Comput. Commun. Appl.  vol. 15, 47:1-47:1.

Tao Y, Ling Z and Patras I (2019). Universal Foreground Segmentation Based on Deep Feature Fusion Network for Multi-Scene Videos. Ieee Access  vol. 7, 158326-158337. 10.1109/ACCESS.2019.2950639

Xie T, Yang X, Zhang T, Xu C and Patras I (2019). Exploring Feature Representation and Training strategies in Temporal Action Localization. Corr  vol. abs/1905.10608,

Jang Y, Gunes H and Patras I (2019). Registration-free Face-SSD: Single shot analysis of smiles, facial attributes, and affect in the wild. Corr  vol. abs/1902.04042,

2018

Miranda Correa JA, Abadi MK, Sebe N and Patras I (2018). AMIGOS: A Dataset for Affect, Personality and Mood Research on Individuals and Groups. Ieee Transactions On Affective Computing  10.1109/TAFFC.2018.2884461

Mou W, Tzelepis C, Mezaris V, Gunes H and Patras I (2018). A deep generic to specific recognition model for group membership analysis using non-verbal cues. Image and Vision Computing  10.1016/j.imavis.2018.09.005

Markatopoulou F, Mezaris V and Patras I (2018). Implicit and Explicit Concept Relations in Deep Neural Networks for Multi-Label Video/Image Annotation. Ieee Transactions On Circuits and Systems For Video Technology  10.1109/TCSVT.2018.2848458

Palasek P and Patras I (2018). Semi-supervised Fisher vector network. Corr  vol. abs/1801.04438,

Apostolidis K, Markatopoulou F, Tzelepis C, Mezaris V and Patras I (2018). Multimedia processing essentials. Springer Series On Cultural Computing  10.1007/978-3-319-73465-1_3

Tzelepis C, Mezaris V and Patras I (2018). Linear Maximum Margin Classifier for Learning from Uncertain Data. Ieee Trans. Pattern Anal. Mach. Intell.  vol. 40, 2948-2962. 10.1109/TPAMI.2017.2772235

2017

TZELEPIS C, PATRAS and MEZARIS V (2017). Linear Maximum Margin Classifier for Learning from Uncertain Data. Institute of Electrical and Electronics Engineers  Ieee Transactions On Pattern Analysis and Machine Intelligence  10.1109/TPAMI.2017.2772235

Vrochidis S, Patras I and Kompatsiaris I (2017). Gaze movement-driven random forests for query clustering in automatic video annotation. Multimedia Tools and Applications  vol. 76, (2) 2861-2889. 10.1007/s11042-015-3221-1

Palasek P and Patras I (2017). Discriminative convolutional Fisher vector network for action recognition. Corr  vol. abs/1707.06119,

2016

Kotsia I, Zafeiriou S, Goudelis G, Patras I and Karpouzis K (2016). Multimodal Sensing in Affective Gaming. Emotion in Games  10.1007/978-3-319-41316-7_4

Stefic D and Patras I (2016). Action recognition using saliency learned from recorded human gaze. Image and Vision Computing  vol. 52, 195-205. 10.1016/j.imavis.2016.06.006

Wang L, Patras I, Zhang J, Mori G and Davis L (2016). Special Issue on Individual and Group Activities in Video Event Analysis. Computer Vision and Image Understanding  vol. 144, 1-2. 10.1016/j.cviu.2016.01.008

Tzelepis C, Galanopoulos D, Mezaris V and Patras I (2016). Learning to detect video events from zero or very few video examples. Image Vis. Comput.  vol. 53, 35-44.

2015

Tzelepis C, Galanopoulos D, Mezaris V and Patras I (2015). Learning to detect video events from zero or very few video examples. Image and Vision Computing  vol. 53, 35-44. 10.1016/j.imavis.2015.09.005

Yang H, Jia X, Patras I and Chan KP (2015). Random Subspace Supervised Descent Method for Regression Problems in Computer Vision. Ieee Signal Processing Letters  vol. 22, (10) 1816-1820. 10.1109/LSP.2015.2437883

Yang H and Patras I (2015). Privileged Information-Based Conditional Structured Output Regression Forest for Facial Point Detection. Ieee Transactions On Circuits and Systems For Video Technology  vol. 25, (9) 1507-1520. 10.1109/TCSVT.2015.2389492

Yang H, He X, Jia X and Patras I (2015). Robust face alignment under occlusion via regional predictive power estimation. Ieee Transactions On Image Processing  vol. 24, (8) 2393-2403. 10.1109/TIP.2015.2421438

Patras I (2015). Face Pose Analysis. Encyclopedia of Biometrics  10.1007/978-1-4899-7488-4_191

Gu L and Kanade T (2015). Face Alignment. Encyclopedia of Biometrics  10.1007/978-1-4899-7488-4_186

Abadi MK, Subramanian R, Kia SM, Avesani P, Patras I and Sebe N (2015). DECAF: MEG-Based Multimodal Database for Decoding Affective Physiological Responses. Ieee Transactions On Affective Computing  vol. 6, (3) 209-222. 10.1109/TAFFC.2015.2392932

Yang H and Patras I (2015). Fine-tuning regression forests votes for object alignment in the wild. Ieee Transactions On Image Processing  vol. 24, (2) 619-631. 10.1109/TIP.2014.2383325

Yang H, Zou C and Patras I (2015). Cascade of forests for face alignment. Iet Computer Vision  vol. 9, (3) 321-330. 10.1049/iet-cvi.2014.0085

Yang H, Mou W, Zhang Y, Patras I, Gunes H and Robinson P (2015). Face Alignment Assisted by Head Pose Estimation. 10.5244/c.29.130

Markatopoulou F, Mezaris V, Pittaras N and Patras I (2015). Local Features and a Two-Layer Stacking Architecture for Semantic Concept Detection in Video. Ieee Transactions On Emerging Topics in Computing  vol. 3, (2) 193-204. 10.1109/TETC.2015.2418714

Yang H and Patras I (2015). Mirror, mirror on the wall, tell me, is the error small? Corr  vol. abs/1501.05152,

2014

Yang H, Zou C and Patras I (2014). Face sketch landmarks localization in the wild. Ieee Signal Processing Letters  vol. 21, (11) 1321-1325. 10.1109/LSP.2014.2333544

Kaymak S and Patras I (2014). Multimodal random forest based tensor regression. Iet Computer Vision  vol. 8, (6) 650-657. 10.1049/iet-cvi.2013.0320

2013

Nikolopoulos S, Zafeiriou S, Patras I and Kompatsiaris I (2013). High order pLSA for indexing tagged images. Signal Processing  vol. 93, (8) 2212-2228. 10.1016/j.sigpro.2012.08.004

Rudovic O, Pantic M and Patras IY (2013). Coupled Gaussian Processes for Pose-Invariant Facial Expression Recognition. Ieee Transactions On Pattern Analysis and Machine Intelligence  vol. 35, (6) 1357-1369. 10.1109/TPAMI.2012.233

Koelstra S and Patras I (2013). Fusion of facial expressions and EEG for implicit affective tagging. Image and Vision Computing  vol. 31, (2) 164-174. 10.1016/j.imavis.2012.10.002

Yang H and Patras I (2013). Sieving regression forest votes for facial feature detection in the wild. Proceedings of The Ieee International Conference On Computer Vision  1936-1943. 10.1109/ICCV.2013.243

2012

Kotsia I, Guo W and Patras I (2012). Higher rank support tensor machines for visual recognition. Pattern Recognition  vol. 45, (12) 4192-4203. 10.1016/j.patcog.2012.04.033

Oveisi F, Oveisi S, Efranian A and Patras I (2012). Nonlinear Independent Component Analysis for EEG-Based Brain-Computer Interface Systems. Independent Component Analysis For Audio and Biosignal Applications  10.5772/39092

Chatzilari E, Nikolopoulos S, Patras I and Kompatsiaris I (2012). Leveraging social media for scalable object detection. Pattern Recognition  vol. 45, (8) 2962-2979. 10.1016/j.patcog.2012.02.006

Kumar BGV, Kotsia I and Patras I (2012). Max-margin Non-negative Matrix Factorization. Image and Vision Computing  vol. 30, (4-5) 279-291. 10.1016/j.imavis.2012.02.010

Guo W, Kotsia I and Patras I (2012). Tensor learning for regression. Ieee Trans Image Process  vol. 21, (2) 816-827. 10.1109/TIP.2011.2165291

Oveisi F, Oveisi S, Efranian A and Patras I (2012). Tree-Structured Feature Extraction Using Mutual Information. Ieee Transactions On Neural Networks and Learning Systems  vol. 23, (1) 127-137. 10.1109/TNNLS.2011.2178447

Koelstra S, Muhl C, Soleymani M, Lee J-S, Yazdani A, Ebrahimi T, Pun T, Nijholt A and Patras IY (2012). DEAP: A Database for Emotion Analysis Using Physiological Signals. Ieee Transactions On Affective Computing  vol. 3, (1) 18-31. 10.1109/T-AFFC.2011.15

2011

Nikolopoulos S, Papadopoulos GT, Kompatsiaris I and Patras I (2011). Evidence-driven image interpretation by combining implicit and explicit knowledge in a Bayesian network. Ieee Trans Syst Man Cybern B Cybern  vol. 41, (5) 1366-1381. 10.1109/TSMCB.2011.2147781

Vrochidis S, Kompatsiaris I and Patras I (2011). Utilizing implicit user feedback to improve interactive video retrieval. Advances in Multimedia  vol. 2011, 10.1155/2011/310762

Oikonomopoulos A, Patras I and Pantic M (2011). Spatiotemporal localization and categorization of human actions in unsegmented image sequences. Ieee Transactions On Image Processing  vol. 20, (4) 1126-1140. 10.1109/TIP.2010.2076821

Chatzilari E, Nikolopoulos S, Patras I and Kompatsiaris I (2011). Enhancing computer vision using the collective intelligence of social media. 10.1007/978-3-642-17551-0_9

Nikolopoulos S, Giannakidou E, Kompatsiaris I, Patras I and Vakali A (2011). Combining Multi-modal Features for Social Media Analysis. Social Media Modeling and Computing  10.1007/978-0-85729-436-4_4

2010

Koelstra S, Pantic M and Patras I (2010). A Dynamic Texture-Based Approach to Recognition of Facial Actions and Their Temporal Models. Ieee Transactions On Pattern Analysis and Machine Intelligence  vol. 32, (11) 1940-1954. 10.1109/TPAMI.2010.50

Passino G, Patras I and Izquierdo E (2010). Aspect coherence for graph-based semantic image labelling. Ieee  Computer Vision, Iet  vol. 4, 183-194. 10.1049/iet-cvi.2008.0093

Patras I and Hancock ER (2010). Coupled Prediction Classification for Robust Visual Tracking. Ieee Transactions On Pattern Analysis and Machine Intelligence  vol. 32, (9) 1553-1567. 10.1109/TPAMI.2009.175

Koelstra S, Pantic M and Patras I (2010). A Dynamic Texture-Based Approach to Recognition of Facial Actions and Their Temporal Models. Ieee Computer Society  Ieee Transactions On Pattern Analysis and Machine Intelligence  vol. 32, 1940-1954-1940-1954. 10.1109/TPAMI.2010.50

2009

Oikonomopoulos A, Pantic M and Patras I (2009). Sparse B-spline polynomial descriptors for human activity recognition. Image Vision Comput  vol. 27, (12) 1814-1825. 10.1016/j.imavis.2009.05.010

Patras I (2009). Face Pose Analysis. Encyclopedia of Biometrics  10.1007/978-0-387-73003-5_191

(2009). Face Acquisition. Encyclopedia of Biometrics  10.1007/978-0-387-73003-5_2145

2008

Andreopoulos Y and Patras I (2008). Incremental refinement of image salient-point detection. Ieee Transactions On Image Processing  vol. 17, (9) 1685-1699. 10.1109/TIP.2008.2001051

2007

PATRAS I, Lagendijk RL and Hendriks EA (2007). Bayesian Confidence Measures for Block-based Motion Estimation. Ieee Trans. Circuits and Systems For Video Technology  vol. 17 Issue 8, 988-995.

Patras I, Hendriks EA and Lagendijk RL (2007). Probabilistic confidence measures for block matching motion estimation. Ieee T Circ Syst Vid  vol. 17, (8) 988-995. 10.1109/TCSVT.2007.903121

PATRAS I, Paragios N, Oikonomopoulos A and Pantic M (2007). Particle Filtering Tracking Scheme for Trajectory-based Recognition of Human Actions. Artificial Intelligence For Human Computing , Editors: Huang TS, Nijholt A, Pantic M and Pentland A. Springer 

2006

Oikonomopoulos A, Patras I and Pantic M (2006). Spatiotemporal salient points for visual recognition of human actions. Ieee Trans Syst Man Cybern B Cybern  vol. 36, (3) 710-719. 10.1109/tsmcb.2005.861864

Pantic M and Patras I (2006). Dynamics of facial expression: recognition of facial actions and their temporal segments from face profile image sequences. Ieee Trans Syst Man Cybern B Cybern  vol. 36, (2) 433-449. 10.1109/tsmcb.2005.859075

Diplaros A, Gevers T and Patras I (2006). Combining color and shape information for illumination-viewpoint invariant object recognition. Ieee Trans Image Process  vol. 15, (1) 1-11. 10.1109/tip.2005.860320

2004

Patras I, Worring M and van den Boomgaard R (2004). Dense motion estimation using regularization constraints on local parametric models. Ieee Trans Image Process  vol. 13, (11) 1432-1443. 10.1109/tip.2004.836179

2003

Patras I, Hendriks EA and Lagendijk RL (2003). Semi-automatic object-based video segmentation with labeling of color segments. Signal Process-Image  vol. 18, (1) 51-65. 10.1016/S0923-5965(02)00092-9

2001

Patras I, Hendriks EA and Lagendijk RL (2001). Video segmentation by MAP labeling of watershed segments. Ieee T Pattern Anal  vol. 23, (3) 326-332. 10.1109/34.910886

PATRAS I, Hendriks EA, Broekhoven M and Hupkens T (2001). Robust Region Merging for Motion Based Sementation Using the Kolmogorov-Smirnov Test. Image Processing and Communications  vol. 6, (3-4) 27-34.