Publications

In this page the complete list of publications about LASIE results is reported.

Scientific publications published in journals:

Spatio-Temporal Crowd Density Model in a Human Detection and Tracking Framework” by Hajer Fradi, Volker Eiselein, Jean-Luc Dugelay, Ivo Keller, Thomas Sikora  at Signal Processing: Image Communication, ELSEVIER, vol. 31, 2015, pp. 100-111

“Violence detection in crowded scenes based on local features and lagrangian measures” by T. Senst, V. Eiselein, A. Kuhn, T. Sikora (HUA and TUB) at IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2016

 “Robust feature matching in long-running poor quality videosby Craig Henderson, Ebroul Izquierdo (QMUL), at IEEE Trans. Circuits and Systems in Video Technology, 2015

“The association between face recognition ability, surveillance ability and change blindness” by Davis, J.P., Treml. F., Forrest, C. & Jansari, A. (UoG) at Cognitive Psychology (publication planned)

“Predictors of face recognition ability” by Davis, J.P. & Maigut, A.C., Forrest, C. & Jansari, A. (UoG) at Cognition (publication planned)

“A test of superior face recognition for police officers” by Davis, J.P., Forrest, C. & Jansari, A. (UoG) at Behavioural Research Methods (publication planned)

“Foreground Detection with Dynamic Tree-Structured Sparse RPCA” by Erfanian Ebadi S., and Izquierdo E.(QMUL) at IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (publication planned)

“Feature Learning with Matrix Factorization Applied to Acoustic Scene Classification” by Victor Bisot, Romain Serizel, Slim Essid, Gaël Richard (IMT) at IEEE transaction on audio speech and language 2016 (publication planned)

Identification from CCTV: Identification from CCTV: Assessing police super-recognisers ability to spot faces in a crowd and susceptibility to change blindness, Davis, J.P., Treml. F., Forrest, C. & Jansari, A (in press).

Crowd Violence Detection Using Global Motion-Compensated Lagrangian Features and Scale-Sensitive Video-Level Representation, Tobias Senst, Volker Eiselein, Alexander Kuhn, Thomas Sikora, IEEE Transactions on Information Forensics and Security, IEEE, vol. PP, no. 99, 11.07.2017, pp. 1–12

Foreground Segmentation with Tree-Structured Sparse RPCA, Erfanian Ebadi S., and Izquierdo E., IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).

A framework for large-scale analysis of video ‘in the Wild’ to assist digital forensic examination, A. Axenopoulos, V. Eiselein, A. Penta, E. Koblents, E. La Mattina, P. Daras, T. Semertzidis, M. Lazaridis, A. Dimou, T. Senst, J. Amores, F. Alvarez, L. Kondrad, G. Vella, A. Randazzo, P. Pomo, IEEE Security & Privacy Magazine, Special Issue on Digital Forensics, 2017

Investigating predictors of superior face recognition in police super-recognisers.”, Davis, J.P., Lander, K., Evans, R., & Jansari, A. (2016 online only). Applied Cognitive Psychology. DOI: 10.1002/acp.3260.

Scientific publications presented at conferences:

Crowd Analysis in non-static Cameras using Feature Tracking and Multi-Person Density” by Tobias Senst, Volker Eiselein, Ivo Keller, Thomas Sikora at 21th IEEE International Conference on Image Processing, Paris, France, 27.10.2014 – 30.10.2014, pp. 6041-6045, ISBN: 978-1-4799-5750-7

Person re-Identification using Region Covariance in a Multi-feature Approach” by Volker Eiselein, Gleb Sternharz, Tobias Senst, Ivo Keller, Thomas Sikora  at International Conference on Image Analysis and Recognition (ICIAR) 2014, 22.10.2014

“Large-scale forensic analysis of security images and videos” by Craig Henderson, Ebroul Izquierdo (QMUL), at BMVC’2014

Motion Modeling for Motion Vector Coding in HEVC” by Michael Tok, Volker Eiselein and Thomas Sikora (TUB)  at 31st IEEE Picture Coding Symposium, Cairns, Australia, 31.05.2015 – 03.06.2015

“An Ontology Framework for Automated Visual Surveillance System” by Faranak Sobhani, Nur Farhan Kahar, Qianni Zhang (talk planned) (QMUL) at Int. Conf. on Content-Based Multimedia Indexing (CBMI), Prague, 10-12 June, 2015

“Action Recognition in Surveillance Videos using Semantic Web Rules” by Pantoja (QMUL), A. Ciapetti (INNEN), C. Massari (INNEN), M. Tarentelli (INNEN), at ICDP’2015

“Recommendation techniques in forensic data analysis: a new approach” by Quintana, F. Sánchez, S. Uribe. F.Alvarez (UPM), at ICDP’2015

“Introducing Target Profiling for Context-Aware Tracking” by Anastasios Dimou, Apostolos Axenopoulos, Petros Daras (CERTH), at ICDP’2015

“A user-centric approach for event-driven summarisation of surveillance videos” by Anastasios Dimou, Dimitra Matsiki, Apostolos Axenopoulos, Petros Daras (CERTH) at  ICDP’2015

“A Local Feature based on Lagrangian Measures for Violent Video Classification” by Tobias Senst, Volker Eiselein, Thomas Sikora (TUB) at ICDP’2015

“On the impurity of street-scene video footage” by Craig Henderson, Saverio G. Blasi, Faranak Sobhani and Ebroul Izquierdo (QMUL) at ICDP’2015

“Improving event detection for audio surveillance” by Jurgen Geiger and Karim Helwani (HUA) at EUSIPCO’2015

“Spectrogram image features for acoustic scene classification” by Victor Bisot, Slim Essid, Gaël Richard (IMT) at EUSIPCO’2015

Robust Feature Matching in the Wild”by Craig Henderson, Ebroul Izquierdo (QMUL) at SAI’2015

“Human-in-the-loop based object-track retrieval” by J. Amores, A. Penta and S. Yous (UTRC) at Image Processing, 2015 IEEE International Conference on., September 2015 (ICIP)

“Approximated RPCA for Fast and Efficient Recovery of Corrupted and Linearly Correlated Images and Video Frames” by VErfanian Ebadi S. and Izquierdo E. in Systems Signals and Image Processing, IEEE International Conference on., September 2015 (IWSSIP)

“Efficient Background Subtraction with Low-rank and Sparse Matrix Decomposition” by Erfanian Ebadi S., Guerra Ones V., and Izquierdo E. in Image Processing, 2015 IEEE International Conference on., September 2015 (ICIP)

“A Random Hough Forests for video database indexing and pattern search in the wild” by C. Henderson and E. Izquierdo (QMUL) Image Processing, 2015 IEEE International Conference on., September 2015 (ICIP)

“Minimal Hough Forest training for pattern detection in Query by Example video search” by Craig Henderson, Ebroul Izquierdo (QMUL) in Systems Signals and Image Processing, IEEE International Conference on., September 2015 (IWSSIP)

“Deep wavelet activation features for visual recognition” by E. Machairidou, G. Th. Papadopoulos and P. Daras (CERTH) in Image Processing, 2015 IEEE International Conference on., September 2015 (ICIP)

“Soft Biometrics in Low Resolution and Low Quality CCTV Videos” by T. Semertzidis, A. Axenopoulos and P. Daras (CERTH) in Image Processing, 2015 IEEE International Conference on., September 2015 (ICIP)

“Acoustic Scene Classification with Matrix Factorization for Unsupervised Feature Learning” by Victor Bisot, Romain Serizel, Slim Essid, Gaël Richard at ICASSP’2016

“Localization of sound sources with known statistics in the presence of interferers” by Chen, K., Geiger, J. T., Helwani, K., and Taghizadeh, M. J., ICASSP’2016

“Individual differences in upright and inverted face recognition, simultaneous face matching and object recognition ability throughout the adult lifespan” by Davis, J.P., Forrest, C., Maigut, A., Kamińska, K., & Jansari, A. at British Psychological Society: Annual Conference, East Midlands Conference Centre, Nottingham, 27 April 2016.

“Rethinking Random Hough Forests for video indexing and pattern search” by C. Henderson and E. Izquierdo (QMUL) at in 4th International conference on Computational Visual Media, April 2016.

“Machine listening techniques for CCTV with audio” by R. Serizel, V. Bisot, S. Essid and G. Richard (IMT) at ICIP’2015

“Group Nonnegative Matrix Factorisation with Speaker and Session Variability Compensation for Speaker Identification” by R. Serizel, S. Essid and G. Richard (IMT) at ICASSP’2016

“Analysis and Development of Forensic Ontology using Description Logic” by Faranak Sobhani, K. Chandramouli and Q. Zhang at CBMI 2016

“A Novel Architecture of Semantic Web Reasoner based on Transferable Belief Model” by C. Pantoja and E. Izquierdo at 14th Workshop on Content-based Multimedia Indexing, CBMI 2016

“Reflection invariance” by C. Henderson and E. Izquierdo,SAI Computing Conference, London, 2016

“Training a Convolutional Neural Network for Multi-Class Object Detection Using Solely Virtual World Data” by E. Bochinski, V. Eiselein, T. Sikora IEEE AVSS 2016

“Mini-batch stochastic approaches for accelerated multiplicative updates in nonnegative matrix factorisation with beta-divergence” by R. Serizel, S. Essid, and G. Richard, Accepted for publication In Proc. of MLSP, p. 2016

“Robust Subspace Separation by Low-Rank and Sparse Representation” by Erfanian Ebadi S., and Izquierdo E., British Machine Vision Conference, York, United Kingdom, (BMVC).

“Formal Representation of events in a surveillance domain ontology” by F. Sobhani, K. Chandramouli, Q. Zhang, E. Izquierdo, IEEE ICIP 2016

“Robust Subspace Separation by Low-Rank and Sparse Representation” by Erfanian Ebadi S., and Izquierdo E., British Machine Vision Conference, York, United Kingdom, (BMVC).

“Multi-target detection in CCTV footage for tracking applications using deep learning techniques” by A. Dimou, P. Medentzidou, F. Alvarez, Petros Daras, ICIP’2016

“Machine listening techniques for CCTV with audio” by R. Serizel, V. Bisot, S. Essid and G. Richard, ICIP’2016

“Dynamic Tree Structured Sparse RPCA via Column Subset Selection for Background Modeling and Foreground Detection” by Erfanian Ebadi S., Guerra Ones V., and Izquierdo E., ICIP’2016

“Deep wavelet activation features for visual recognition” by E. Machairidou, G. Th. Papadopoulos and P. Daras , ICIP’2016

Scalable pattern retrieval from videos using a Random Forest index, C. Henderson and E. Izquierdo, in International Conference on Internet of Things, Data and Cloud Computing (ICC 2017), 2017.

Masters of disguise: Super-recognisers’ superior memory for concealed unfamiliar faces. Davis, J.P., & Tamonytė, D. (2017). Proceedings of the 2017 Seventh International Conference on Emerging Security Technologies (EST), 6-8 September 2017, Canterbury, UK.

Deep cross-layer activation features for visual recognition, G. T. Papadopoulos, E. Machairidou, P. Daras, IEEE International Conference on Image Processing, ICIP 2016, Sept 25-28, Phoenix, Arizona, USA, not listed in previous reporting period.

Robust Audio Localization With Phase Unwrapping, Kainan Chen, Jürgen T. Geiger, Walter Kellermann (HUA), 42nd IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP2017, March 5-9, 2017, New Orleans, USA.

Reverberation-based Feature Extraction For Acoustic Scene Classification, Miloš Marković, Jürgen Geiger (HUA), 42nd IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP2017, March 5-9, 2017, New Orleans, USA.

Overlapping sound event detection with supervised nonnegative matrix factorization, V. Bisot, R. Serizel, S. Essid and G. Richard, in Proc. International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017.

Supervised group nonnegative matrix factorisation with similarity constraints and applications to speaker identification, R. Serizel, V. Bisot, S. Essid and G. Richard, in Proc. International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017.

Assessing Post-Detection Filters for a Generic Pedestrian Detector in a Tracking-By-Detection Scheme, Volker Eiselein, Erik Bochinski, Thomas Sikora, IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS) (Analysis of video and audio “in the Wild” workshop), 29.08.2017, Lecce, Italy.

Sequential Sensor Fusion Combining Probability Hypothesis Density and Kernelized Correlation Filters for Multi-Object Tracking in Video Data, Tino Kutschbach, Erik Bochinski, Volker Eiselein, Thomas Sikora, International Workshop on Traffic and Street Surveillance for Safety and Security at IEEE AVSS 2017, Lecce, Italy, 29.08.2017 – 01.09.2017.

High-Speed Tracking-by-Detection Without Using Image Information, Erik Bochinski, Volker Eiselein and Thomas Sikora, International Workshop on Traffic and Street Surveillance for Safety and Security at IEEE AVSS 2017, Lecce, Italy, 29.08.2017, CHALLENGE WINNER IWOT4S.

Leveraging deep neural networks with nonnegative representations for improved environmental sound classification, V.Bisot and R. Serizel and S. Essid and G. Richard, In Proc. of Workshop on Machine Learning for Signal Processing (MLSP), 2017.

A Consistent Two-Level Metric for Evaluation of Automated Abandoned Object Detection Methods, Patrick Krusch, Erik Bochinski, Volker Eiselein, Thomas Sikora, IEEE International Conference on Image Processing (ICIP), Beijing, China, 17.09.2017 – 20.09.2017.

Hyper-Parameter Optimization for Convolutional Neural Network Committees Based on Evolutionary Algorithms, Erik Bochinski, Tobias Senst, Thomas Sikora, IEEE International Conference on Image Processing (ICIP), Beijing, China, 17.09.2017 – 20.09.2017.

TooManyEyes: Super-recogniser directed identification of target individuals on CCTV, M.D. Durova, A. Dimou, G. Litos, P. Daras, & J.P. Davis, ICDP 2017: 8th IET International Conference of Imaging for Crime Detection and Prevention.

Nonnegative Feature Learning Methods for Acoustic Scene Classification, V. Bisot, R. Serizel, S. Essid and G. Richard, in IEEE workshop on Detection and Classification of Acoustic Scenes and Events (DCASE) 2017.

Evidence recommendation in forensics based on cyclic meta-paths in heterogeneous information networks, E. Koblents and F. Alvarez, submitted to ICDP’ 2017.

Books and Chapters

Valentine, T., & Davis, J.P. “Forensic Facial Identification: Theory and Practice of Identification from Eyewitnesses, Composites and CCTV“. Chichester: Wiley-Blackwell (2015).

Davis, J.P., & ¬Valentine, T. (2015). “Human verification of identity from photographic images”. In T. Valentine and J.P. Davis (Eds.). Forensic Facial Identification: Theory and Practice of Identification from Eyewitnesses, Composites and CCTV” (pp. 211-238). Chichester: Wiley-Blackwell.

C. Henderson and E. Izquierdo, “Feature correspondence in low quality CCTV videos, in Studies in Computational Intelligence”, Springer, 2016

Theodoros Semertzidis, Christos Athanasiadis, Michael Gerassimos Strintzis, and Petros Daras, “Social Media: Trends, Events, and Influential Users“, Encyclopedia of Computer Science and Technology, Second Edition. Dec 2016 , 732 -744.

Romain Serizel, Victor Bisot, Slim Essid, Gaël Richard, Chapter 4: Acoustic Features for Environmental Sound Analysis, Computational Analysis of Sound Scenes and Events, pg 71-101.

Slim Essid, Sanjeel Parekh, Ngoc Q. K. Duong, Romain Serizel, Alexey Ozerov, Fabio Antonacci, Augusto Sarti, Chapter 9: Multiview Approaches to Event Detection and Scene Analysis, Computational Analysis of Sound Scenes and Events, pg 243-276.

Articles

Bryce, M. (2014). Psychologist recruits crowd watchers to assist CCTV algorithms a UoG interview, 17th November 2014, published on “Focus on crime”. Wired, December 2014, 53.

Neuroscience, BBC (2015). The superpower police now use to tackle crime. 11 June 2015. www.bbc.com/future/story/20150611-the-superpower-police-now-use-to-tackle-crime

Zolfagharifard, Z.. “Are YOU a ‘super recogniser’? Take the test to see if you are one of an elite group of people who never forget”. The Daily Mail, 15 June 2015.www.dailymail.co.uk/sciencetech/article-3125173/Are-super-recogniser-test-one-elite-group-people-rarely-forgets-face.html

McCrum, K. (2015). “Are you a super recogniser? Take the test Met police use to help find criminals” 16 June 2015www.mirror.co.uk/news/weird-news/you-super-recogniser-take-test-5892509

Sims, A. “Super-recognisers used by the police to identify criminals and spot offender in crowds”. The Independent, 19 June 2015.www.independent.co.uk/news/uk/crime/super-recognisers-used-by-the-police-to-identify-criminals-and-spot-offenders-in-crowds-10324186.html

Lewis, T. “A select group of people have an uncanny ability to remember faces for years”. Business Insider Australia, 29 October 2015.www.businessinsider.com.au/people-who-are-good-at-remembering-faces-2015-10

Leigh Sinrod, M. “I might have a superpower”. Scitechnow, 30 October 2015.scitechnow.org/psychology/might-superpower/#

Noack, R. “Software can’t compete with these cops in identifying suspects”. Washington Post, 13 March 2016.www.washingtonpost.com/news/worldviews/wp/2016/03/13/software-cant-compete-with-these-cops-in-identifying-suspects/

Cummings, J. “A day with the super-recognisers – the police unit who put thousands of faces to names”. The Tab. 31 Mar 2016.http://thetab.com/2016/03/31/a-day-with-the-super-recognisers-82812

TV programs and Interviews, online videos

Crimewatch Roadshow, BBC1 (2014). Live interview on police super-recognisers. 30 June 2014.www.facebook.com/metpoliceuk/posts/739174566139518

De Kennis van Nu, The Netherlands (2015). Recorded documentary on super-recognizers. 8 April 2015. www.npowetenschap.nl/programmas/de-kennis-van-nu-tv/uitzendingen/2015/april/gezichtsherkenning.html

Potts, L. (2015). “The police ‘super-recognisers’ putting names to faces”. BBC London News, 19 October 2015. www.bbc.co.uk/news/uk-england-34544199

Craig Henderson, interview to the winner of best paper award at SAI Conference 2015, July 2015. www.youtube.com/watch?v=RPw7C4ZnIvY

Channel 4 (2016). Your face says it all. Channel 4, 18 October 2016. http://www.channel4.com/programmes/your-face-says-it-all

SWR Fernsehen TV, Germany (2016). Geschichte der Super Recogniser. SWR Fernsehen, 1 December 2016, http://www.swr.de/odysso/super-recogniser-begabte-ermittler/-/id=1046894/did=18343408/nid=1046894/cx58wo/index.html

BBC (2017). Dr Weston’s Casebook. BBC2, 8 March 2017, https://vimeo.com/210776496 (password: Waterloo)

BBC1 (2017). Fugitives. BBC1, 17 March 2017.

BBC Kent (2016). Steve N Allen (live phone interview). BBC Kent, 1 March 2017

BBC (2017). Dr Weston’s Casebook. BBC2, 8 March 2017, https://vimeo.com/210776496 (password: Waterloo)

BBC1 (2017). Fugitives. BBC1, 17 March 2017

Radio Sputnik (2017). Live interview on face recognition technology. Radio Sputnik World Service, Moscow, Russia, 14 September 2017. https://sputniknews.com/

RADIO

Bamford, A. (2015). “Interview about super-recognisers”. PM: Eddie Mair Show, BBC Radio 4, 14 October 2015. www.bbc.co.uk/programmes/p0356fvj

BBC1 London News (2015). “Interview about super-recognisers with Andy Jones”. BBC1, 19 October, 2015. Inside Out (2015).

BBC Radio World Service (2015). “Live interview about super-recognisers with Julian Marshall”. BBC World Service, 19 October 2015.

New Zealand Radio (2015). “Live interview about super-recognisers. From nine to noon”. New Zealand Radio, 12 November 2015.

Bamford, A. (2015). “Follow-up interview about super-recognisers, after EEG testing at the University of Greenwich”. PM: Eddie Mair Show, BBC Radio 4, 20 December 2015. www.bbc.co.uk/programmes/p0356fvj

McGovern, N. (2016). “How ‘super recognisers’ are helping Cologne police (live interview)”. Outside Source, BBC World Service, 26 Jan 2016. www.bbc.co.uk/programmes/p03gn90h

New Zealand Radio (2016). Saturday Morning. New Zealand Radio, New Zealand, 20 August 2016, http://www.radionz.co.nz/national/programmes/saturday

Talk Radio (2016). Johnny Gould featuring Ash. Talk Radio, 26 September 2016, http://talkradio.co.uk/jonny-gould-feat-ash

BBC Kent (2016). Julia North Show (live studio interview). BBC Kent, 24 November 2016.