Suzanne Little
Prof
Suzanne Little is professor in the School of Computing at Dublin City University and an SFI Principal Investigator at the Insight SFI Research Centre for Data Analytics working in the area of media analytics, information access and retrieval across a variety of application domains. She completed her PhD at the University of Queensland, Australia in 2006 examining and developing tools for analysing and managing scientific multimedia data. She has worked on a number of EU projects in the areas of multimedia, technology enhanced education, security, autonomous vehicles and big data. Prof. Little is co-director of the SFI Centre for Research Training in Artificial Intelligence (CRT-AI) and a Funded Investigator in the iForm Advanced Manufacturing Centre. Her expertise is in video analysis, semantic search and data integration and current research includes projects examining bias in deep learning models for computer vision, safety in micromobility and personal transportation, improved medical image analysis, biomedical data and water desalination.
Peer Reviewed Journal
| Year | Publication | |
|---|---|---|
| 2023 | Gutowska, M.; Little, S.; McCarren, A. (2023) 'Constructing a Meta-Learner for Unsupervised Anomaly Detection'. Ieee Access, 11 . [Link] [DOI] | |
| 2022 | Zhang, D.; O'Conner, N.E.; Simpson, A.J.; Cao, C.; Little, S.; Wu, B. (2022) 'Coastal fisheries resource monitoring through A deep learning-based underwater video analysis'. Estuarine, Coastal and Shelf Science, 269 . [Link] [DOI] | |
| 2021 | Horta, V.A.C.; Tiddi, I.; Little, S.; Mileo, A. (2021) 'Extracting knowledge from Deep Neural Networks through graph analysis'. Future Generation Computer Systems, 120 . [Link] [DOI] | |
| 2021 | McGivern, S.; Boutouil, H.; Al-Kharusi, G.; Little, S.; Dunne, N.J.; Levingstone, T.J. (2021) 'Translational application of 3D bioprinting for cartilage tissue engineering'. Bioengineering (Basel, Switzerland), 8 . [Link] [DOI] | |
| 2019 | Zhang, Dian and Heery, Brendan and O’Neil, Maria and Little, Suzanne and O’Connor, Noel E and Regan, Fiona (2019) 'A Low-Cost Smart Sensor Network for Catchment Monitoring'. 19 (10). | |
| 2018 | Chatbri, Houssem and Kameyama, Keisuke and Kwan, Paul and Little, Suzanne and O’Connor, Noel E (2018) 'A novel shape descriptor based on salient keypoints detection for binary image matching and retrieval'. 77 (21):28925-28948. | |
| 2012 | Little, Suzanne and Ferguson, Rebecca and R\"uger, Stefan (2012) '大发体育在线_大发体育-投注|官网ing and reusing learning materials with multimedia similarity search and social networks'. 21 (2):255-271. https://doi.org/10.1080/1475939x.2012.698378 | |
| 2010 | Suzanne Little and Sara Colantonio and Ovidio Salvetti and Petra Perner (2010) 'Evaluation of Feature Subset Selection, Feature Weighting, and Prototype Selection for Biomedical Applications'. 3 (1):39-49. [Link] [DOI] | |
| 2009 | Little, Suzanne and Colantonio, Sara and Salvetti, Ovidio and Perner, Petra (2009) 'Can Prototype-Based Classification be a good Method for Biomedical Applications?'. 2 (1):44-61. | |
| 2005 | Hunter, Jane and Little, Suzanne (2005) 'A framework to enable the semantic inferencing and querying of multimedia content'. 2 (2-3). https://doi.org/10.1504/ijwet.2005.008487 | |
| 2004 | Hunter, Jane and Drennan, John and Little, Suzanne (2004) 'Realizing the Hydrogen Economy through Semantic Web Technologies'. IEEE Intelligent Systems and Their Applications, 19 (1). [DOI] |
Conference Publication
| Year | Publication | |
|---|---|---|
| 2023 | Mandal, A; Leavy, S; Little, S (2023) Advances in Bias and Fairness in Information Retrieval. BIAS 2023 Measuring Bias in Multimodal Models: Multimodal Composite Association Score https://doi.org/10.1007/978-3-031-37249-0_2 | |
| 2021 | Salwala, D.; Yadav, P.; Munirathnam, V.G.; Little, S.; O'connor, N.E.; Curry, E. (2021) UrbanMM 2021 - Proceedings of the 1st International Workshop on Multimedia Computing for Urban Data, co-located with ACM MM 2021 UrbanAccess: Query Driven Urban Analytics Platform for Detecting Complex Accessibility Event Patterns using Tactile Surfaces [Link] [DOI] | |
| 2021 | Venkatesh, G.M.; Pereira, B.; Little, S. (2021) UrbanMM 2021 - Proceedings of the 1st International Workshop on Multimedia Computing for Urban Data, co-located with ACM MM 2021 Urban footpath image dataset to assess pedestrian mobility [Link] [DOI] | |
| 2021 | Mandal, A.; Leavy, S.; Little, S. (2021) Trustworthy AI 2021 - Proceedings of the 1st International Workshop on Trustworthy AI for Multimedia Computing, co-located with ACM MM 2021 Dataset Diversity: Measuring and Mitigating Geographical Bias in Image Search and Retrieval [Link] [DOI] | |
| 2021 | Rudinac, S.; Bozzon, A.; Chua, T.S.; Little, S.; Gatica-Perez, D.; Aizawa, K. (2021) MM 2021 - Proceedings of the 29th ACM International Conference on Multimedia UrbanMM'21: 1st International Workshop on Multimedia Computing for Urban Data [Link] [DOI] | |
| 2020 | Zhang, Dian; Srungavarapu, Swathikiran; Choong, Binwoei; O'Connor, Noel; Little, Suzanne (2020) GLOBAL OCEANS 2020: SINGAPORE - U.S. GULF COAST A Large Scale Under-Sea Dataset for Marine Observation [DOI] | |
| 2020 | Hu, F.; Venkatesh, G.M.; O'Connor, N.E.; Smeaton, A.F.; Little, S. (2020) Utilising visual attention cues for vehicle detection and tracking [Link] [DOI] | |
| 2020 | Naresh Y. G. and Venkatesh Gurram Munirathnam and Noel E. O'Connor and Suzanne Little (2020) IMVIP2020 Proceedings Object polygonization in traffic scenes using small Eigenvalue analysis [Link] | |
| 2020 | Jaime B. Fernandez and Suzanne Little and Noel E. O'Connor (2020) 6th International Conference on Vehicle Technology and Intelligent Transport Systems (VEHITS), Proceedings Multiple path prediction for traffic scenes using LSTMs and mixture density models [Link] | |
| 2019 | Corrigan, Owen and Little, Suzanne (2019) International Conference on Multimedia Modeling Fashion Police: Towards Semantic Indexing of Clothing Information in Surveillance Data | |
| 2019 | Linardos, Panagiotis and Little, Suzanne and McGuinness, Kevin (2019) MediaEval Workshop MediaEval 2019: concealed FGSM perturbations for privacy preservation | |
| 2019 | Fernandez, Jaime B.; Venkatesh, G. M.; Zhang, Dian; Little, Suzanne; O'Connor, Noel E. (2019) 2019 INTERNATIONAL CONFERENCE ON CONTENT-BASED MULTIMEDIA INDEXING (CBMI) Semi-Automatic Multi-Object Video Annotation Based on Tracking, Prediction and Semantic Segmentation | |
| 2019 | Venkatesh, G. M.; Hu, Feiyan; O'Connor, Noel E.; Smeaton, Alan F.; Yang, Zhen; Little, Suzanne (2019) 2019 INTERNATIONAL CONFERENCE ON CONTENT-BASED MULTIMEDIA INDEXING (CBMI) Saliency Guided 2D-Object Annotation for Instrumented Vehicles | |
| 2019 | Fernandez, Jaime B and Little, Suzanne and O’Connor, Noel E (2019) 2019 Ninth International Conference on Image Processing Theory, Tools and Applications (IPTA) A Single-Shot Approach Using an LSTM for Moving Object Path Prediction | |
| 2019 | Linardos, Panagiotis and Little, Suzanne and McGuinness, Kevin (2019) Proceedings of MediaEval 2019 MediaEval 2019: Concealed FGSM Perturbations for Privacy Preservation | |
| 2018 | Venkatesh, GM and Naresh, YG and Little, Suzanne and O’Connor, Noel E (2018) OR 2.0 Context-Aware Operating Theaters, Computer Assisted Robotic Endoscopy, Clinical Image-Based Procedures, and Skin Image Analysis A deep residual architecture for skin lesion segmentation | |
| 2018 | Mark Marsden and Kevin McGuinness and Suzanne Little and Ciara Keogh and Noel E O'Connor (2018) IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) People, Penguins and Petri Dishes: Adapting Object Counting Models To New Visual Domains And Object Types Without Forgetting | |
| 2018 | Marsden, Mark and McGuinness, Kevin and Little, Suzanne and Keogh, Ciara E and O'Connor, Noel E (2018) Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition People, penguins and petri dishes: Adapting object counting models to new visual domains and object types without forgetting | |
| 2018 | Naresh, Y. G.; Little, Suzanne; O'Connor, Noel E. (2018) 2018 26TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO) A Residual Encoder-Decoder Network for Semantic Segmentation in Autonomous Driving Scenarios | |
| 2018 | Ballas, Camille and Marsden, Mark and Zhang, Dian and O'Connor, Noel E and Little, Suzanne (2018) IEEE 4th World Forum on Internet of Things Performance of video processing at the edge for crowd-monitoring applications | |
| 2017 | Marsden, Mark and McGuiness, Kevin and Little, Suzanne and O'Connor, Noel E (2017) 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP) Fully Convolutional Crowd Counting On Highly Congested Scenes | |
| 2017 | Little, Suzanne and Zhang, Dian and Ballas, Camille and O'Connor, Noel E and Prendergast, David and Nolan, Keith and Quinn, Brian and Moran, Niall and Myers, Mike and Dillon, Clare and Meehan, Tomas (2017) First ACM International Workshop on the Engineering of Reliable, Robust, and Secure Embedded Wireless Sensing Systems (FAILSAFE) Understanding packet loss for sound monitoring in a smart stadium IoT testbed Delft, The Netherlands, | |
| 2017 | Marsden, Mark; McGuinness, Kevin; Little, Suzanne; O'Connor, Noel E. (2017) 2017 14TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE (AVSS) ResnetCrowd: A Residual Deep Learning Architecture for Crowd Counting, Violent Behaviour Detection and Crowd Density Level Classification | |
| 2017 | Chatbri, Houssem and McGuinness, Kevin and Little, Suzanne and Zhou, Jiang and Kameyama, Keisuke and Kwan, Paul and O'Connor, Noel E (2017) Proceedings of the 2017 ACM Workshop on Multimedia-based Educational and Knowledge Technologies for Personalized and Social Online Training Automatic MOOC video classification using transcript features and convolutional neural networks | |
| 2017 | Chatbri, Houssem and McGuinness, Kevin and Little, Suzanne and Zhou, Jiang and Kameyama, Keisuke and Kwan, Paul and O'Connor, Noel E (2017) ACM Multimedia 2017 - MultiEdTech Workshop Automatic MOOC video classification using transcript features and convolutional neural networks | |
| 2017 | Oliveira, Marlon and Chatbri, Houssem and Little, Suzanne and O'Connor, Noel E. and Sutherland, Alistair (2017) Image and Vision Computing New Zealand 2017 (IVCNZ) A comparison between end-to-end approaches and feature extraction based approaches for Sign Language recognition Christchurch, New Zealand, 04/12/2017- 06/12/2017 [Link] | |
| 2017 | Oliveira, Marlon and Chatbri, Houssem and Little, Suzanne and Ferstl, Ylva and O'Connor, Noel E. and Sutherland, Alistair (2017) International Conference on Digital Image Computing: Techniques and Applications (DICTA) Irish sign language recognition using principal component analysis and convolutional neural networks Sydney, Australia, 29/11/2017- 01/12/2017 [Link] | |
| 2017 | Duane, A. and Zhou, J. and Little, S. and Gurrin, C. and Smeaton, A.F. (2017) Proceedings of the International Conference on Multimedia Modelling (MMM2017) An annotation system for egocentric image media | |
| 2017 | Jargalsaikhan, I and Little, S and O'Connor, N E (2017) 14th IEEE International Conference on Advance Video and Signal-based Surveillance (AVSS) Action Localization in Video using a Graph-based Feature Representation | |
| 2017 | Chatbri, Houssem and Oliveira, Marlon and McGuinness, Kevin and Little, Suzanne and Kameyama, Keisuke and Kwan, Paul and Sutherland, Alistair and O’Connor, Noel E (2017) 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA) Educational video classification by using a transcript to image transform and supervised learning | |
| 2017 | Marsden, Mark and McGuinness, Kevin and Little, Suzanne and O'Connor, Noel E (2017) 14th IEEE International Conference on Advance Video and Signal-based Surveillance (AVSS) ResnetCrowd: A Residual Deep Learning Architecture for Crowd Counting, Violent Behaviour Detection and Crowd Density Level Classification | |
| 2017 | Oliveira, Marlon and Chatbri, Houssem and Ferstl, Ylva and Farouk, Mohamed and Little, Suzanne and O'Connor, Noel E. and Sutherland, Alistair (2017) Irish Machine Vision and Image Processing Conference (IMVIP) . In: McDonald, John and Markham, Charles and Winstanley, Adam C eds. A Dataset for Irish sign language recognition Maynooth, 30/08/2017- 01/09/2017 [Link] | |
| 2017 | Chatbri, Houssem and Oliveira, Marlon and McGuinness, Kevin and Little, Suzanne and Kameyama, Keisuke and Kwan, Paul and Sutherland, Alistair and O'Connor, Noel E (2017) International Conference on Image Processing Theory, Tools and Applications (IPTA) Educational video classification by using a transcript to image transform and supervised learning Montreal, Canada, 28/11/2017- 01/12/2017 | |
| 2016 | Panchanathan, Sethuraman and Chakraborty, Shayok and McDaniel, Troy and Bunch, Matt and O'Connor, Noel and Little, Suzanne and McGuinness, Kevin and Marsden, Mark (2016) IEEE International Symposium on Multimedia (ISM) Smart Stadium for Smarter Living: Enriching the Fan Experience | |
| 2016 | Marsden, M.; McGuinness, K.; Little, S.; O'Connor, N.E. (2016) Proceedings - International Conference on Image Processing, ICIP Holistic features for real-time crowd behaviour anomaly detection [Link] [DOI] | |
| 2016 | Marsden, Mark; McGuinness, Kevin; Little, Suzanne; O'Connor, Noel E. (2016) 2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) HOLISTIC FEATURES FOR REAL-TIME CROWD BEHAVIOUR ANOMALY DETECTION | |
| 2016 | Marsden, Mark and McGuinness, Kevin and Little, Suzanne and O'Connor, Noel E (2016) International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP) Fully convolutional crowd counting on highly congested scenes | |
| 2016 | Panchanathan, Sethuraman and Chakraborty, Shayok and McDaniel, Troy and Bunch, Matt and O’Connor, Noel and Little, Suzanne and McGuinness, Kevin and Marsden, Mark (2016) 2016 IEEE international symposium on multimedia (ISM) Smart stadium for smarter living: Enriching the fan experience | |
| 2015 | Jargalsaikhan, I. and Little, S. and Trichet, R. and O'Connor, N.E. (2015) 12th IEEE International Conference on Advanced Video and Signal Based Surveillance Action recognition in video using a spatial-temporal graph-based feature representation | |
| 2014 | Albatal, R. and Little, S. (2014) Proceedings of the 21st International Conference on Multimedia Modelling (MMM2014) Empirical exploration of extreme SVM-RBF parameter values for visual object classification | |
| 2014 | Jargalsaikhan, I. and Direkoglu, C. and Little, S. and O'Connor, N.E. (2014) Proceedings of the 21st International Conference on Multimedia Modelling (MMM2014) An evaluation of local action descriptors for human action classification in the presence of occlusion | |
| 2013 | Little, S. and Jargalsaikhan, I. and Clawson, K. and Li, H. and Nieto, M. and Direkoglu, C. and O'Connor, N.E. and Smeaton, A.F. and Liu, J. and Scotney, B. and Wang, H. and Gaines, S. and Rodriguez, A. and Sanchez, P. and Mart\'inez Llorens (2013) Proceedings of the 3rd ACM International Conference on Multimedia Retrieval (demo) Interactive surveillance event detection at TRECVid2012 | |
| 2013 | Little, S. and Jargalsaikhan, I. and Direkoglu, C. and O'Connor, N.E. and Smeaton, A.F. and Clawson, K. and Li, H. and Liu, J. and Scotney, B. and Wang, H. and Nieto, M. (2013) Proceedings of the 3rd ACM International Conference on Multimedia Retrieval An information retrieval approach to identifying infrequent events in surveillance video | |
| 2013 | Kafetzakis, E. and Xilouris, C. and Kourtis, M.A. and Nieto, M. and Jargalsaikhan, I. and Little, S. (2013) Proceedings of IEEE International Symposium on Multimedia The impact of video transcoding parameters on event detection for surveillance systems | |
| 2013 | Jargalsaikhan, I.; Little, S.; Direkoglu, C.; O'Connor, N.E. (2013) 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings Action recognition based on sparse motion trajectories [Link] [DOI] | |
| 2013 | Little, Suzanne and Clawson, Kathy and Mereu, Anna and Rodriguez, Aitor (2013) 5th International Conference on Imaging for Crime Prevention and Detection ICDP-13 Identifying and addressing challenges for search and analysis of disparate surveillance video archives London, UK, | |
| 2012 | Okada, A and Mikroyannidis, A and Meister, I and Little, S (2012) Cambridge 2012: Innovation and Impact - Openly Collaborating to Enhance Education Colearning - Collaborative networks for creating, sharing and reusing OER through social media | |
| 2011 | Little, Suzanne and Mikroyannidis, Alexander and Okada, Alexandra and Scott, Peter (2011) Signal-Image Technology and Internet-Based Systems (SITIS), 2011 Seventh International Conference on Formal metadata and shared experiences for discovering tools to adapt open educational resources | |
| 2011 | Little, Suzanne and Ferguson, Rebecca and R\"uger, Stefan (2011) Proc. World Conference on Educational Multimedia, Hypermedia and Telecommunications (EDMEDIA) Navigating and discovering educational materials through visual similarity search | |
| 2010 | Diriye, A and Zagorac, S and Little, S and Rueger, S (2010) Demo at 11th ACM SIGMM International Conference on Multimedia Information Retrieval NewsRoom: An Information-Seeking Support System for News Videos | |
| 2010 | Gurrin, C. and He, Y. and Kazai, G. and Kruschwitz, U. and Little, S. and Roelleke, T. and R\"uger, S. and Van Rijsbergen (2010) Proceedings of the 32nd European Conference on Information Retrieval (Lecture Notes in Computer Science) Recent developments in information retrieval | |
| 2010 | Gurrin, Cathal and He, Yulan and Kruschwitz, Udo and Little, Suzanne and R\"uger, Stefan (2010) ACM SIGIR Forum ECIR 2010: 32nd european conference on information retrieval research | |
| 2009 | Zagorac, S and Llorente, A and Little, S and Liu, H and Rueger, S (2009) TREC Video Retrieval Evaluation Notebook Papers, NIST Automated Content Based Video Retrieval | |
| 2009 | Llorente, A and Little, S and Rueger, S (2009) Working notes for the CLEF 2009 Workshop MMIS at ImageCLEF 2009: Non-parametric Density Estimation Algorithms Corfu, Greece, | |
| 2009 | Little, Suzanne and Rueger, Stefan (2009) 2009 IEEE International Workshop on Multimedia Signal Processing Conservation of effort in feature selection for image annotation [Link] | |
| 2008 | Asirelli, P. and Colantonio, S. and Little, S. and Martinelli, M. and Salvetti, O. (2008) Proceedings of the 1st International Workshop on Image Mining Theory and Applications, IMTA 2008 - In Conjunction with VIISIGRAPP 2008 Media analysis and the algorithm ontology | |
| 2008 | Llorente, A and Zagorac, S and Little, S and Hu, R and Kumar, A and Shaik, S and Ma, X and Rueger, S (2008) TREC Video Retrieval Evaluation Notebook Papers, NIST Semantic Video Annotation using Background Knowledge and Similarity-based Video Retrieval Gaithersburg, Maryland, | |
| 2008 | Little, Suzanne and Salvetti, Ovidio and Perner, Petra (2008) Proceedings of the 9th European Conference on Case-Based Reasoning Evaluation of Feature Subset Selection, Feature Weighting, and Prototype Selection for Biomedical Application Trier, Germany, | |
| 2008 | Little, Suzanne and Salvetti, Ovidio and Perner, Petra (2008) Proceedings of the Twenty-First IEEE International Symposium on Computer-Based Medical Systems (CBMS) Evaluating a Case-Based Classifier for Biomedical Applications Jyv\a\skyl\a\, | |
| 2007 | Little, Suzanne and Salvetti, Ovidio and Perner, Petra (2007) LWA 2007 Lernen--Wissen--Adaption Using Neural Nets for Semi-Automatic Semantic Annotation of Images | |
| 2007 | Little, S. and Salvetti, O. and Perner, P. (2007) Proceedings - IEEE International Conference on Data Mining, ICDM Semi-automatic semantic annotation of images | |
| 2007 | Little, Suzanne and Salvetti, Ovidio and Perner, Petra (2007) International Conference on Mass Data Analysis of Images and Signals in Medicine, Biotechnology, and Chemistry Semi-automatic semantic tagging of 3D images from pancreas cells | |
| 2007 | Troncy, Raphael and Celma, Oscar and Little, Suzanne and Garcia, Roberto and Tsinaraki, Chrisa (2007) Proceedings of Workshop on Multimedia Annotation and Retrieval Enabled by Shared Ontologies (SAMT) MPEG-7 based Multimedia Ontologies: Interoperability Support or Interoperability Issue? Genova, Italy, | |
| 2006 | Asirelli, Patrizia and Little, Suzanne and Martinelli, Massimo and Salvetti, Ovidio (2006) Workshop on Semantic Web Applications and Perspecitives (SWAP06) MultiMedia Metadata Management: a proposal for an infrastructure | |
| 2005 | Hollink, L and Little, S and Hunter, J (2005) Proceedings of the 3rd international conference on Knowledge capture Evaluating the application of semantic inferencing rules to image annotation [Link] | |
| 2005 | Hunter, Jane and Cheung, Kwok and Little, Suzanne and Drennan, John (2005) International Conference on Solid State Ionics. Applications: Fuel Cells. Baden--Baden. July. p FUSION-A Knowledge Management System for Fuel Cell Optimization | |
| 2004 | Hunter, Jane and Ragan, Mark A and Little, Suzanne (2004) W3C's Semantic Web Life Sciences Workshop Position Paper for Semantic Web Life Sciences Workshop | |
| 2004 | Little, Suzanne and Hardman, Lynda (2004) Proceedings of the 10th International Multimedia Modeling Conference (MMM 2004) Cuypers Meets Users: Implementing a User Model Architecture for Multimedia Presentation Generation Brisbane, Australia, [Link] | |
| 2002 | Little, Suzanne and Geurts, Joost and Hunter, Jane (2002) Proceedings of 6th European Conference on Research and Advanced Technology for Digital Libraries (ECDL) Dynamic Generation of Intelligent Multimedia Presentations through Semantic Inferencing Rome, Italy, [Link] | |
| 2002 | Little, Suzanne and Hunter, Jane (2002) EdMedia A Tool for Creating, Editing and Tracking Virtual SMIL Presentations Denver, Colorado, USA, | |
| 2001 | Hunter, Jane and Little, Suzanne (2001) Proceedings of 5th European Conference on Research and Advanced Technology for Digital Libraries (ECDL) Building and Indexing a Distributed Multimedia Presentation Archive Using SMIL Darmstadt, Germany, [Link] |
Book Chapter
Published Report
Certain data included herein are derived from the ? Web of Science (2024) of Clarivate. All rights reserved.
Research Interests
Content-based analysis and indexing of digital multimedia - principally images and video - using computer vision, machine learning and related techniques. This can be for object or event detection, segmentation, classification and/or tracking. Example applications include surveillance, document reuse (eg, lectures), traffic or instrumented vehicles, smart cities, cultural heritage, sport or entertainment. Also fundamental research in optimising complex neural network based architectures and in the consequences of biased visual datasets and models.