Ardhendu is a Reader (Associate Professor) in Computer Vision & AI and programme leader for Computer Sciences in the Department of Computer Science.Before that he was a Senior Lecturer. Dr Behera was a post-doc at the Computer Vision Group in the University of Leeds (2007-14). He was also EHU’s Impact Fellow (2017-18, REF panel B) to develop and support strategies in generating high quality impact studies (interdisciplinary aspects) across several UoA for the REF 2021. He has been PI of several projects on developing Computer Vision and AI algorithms to analyse images/videos, multimodal data, and recognise human behaviour and activities. He is a member of AAAI, British Computer Society & IEEE, and a Fellow of HEA of the UK. Dr Behera has published high quality journals/conference papers and many of them are of interdisciplinary nature. He has delivered keynotes and involved in various outreach activities. His dementia monitoring research (social robotics and multimodal AI) was covered by national/international media (e.g. BBC News, BBC Radio, The Times, The Sun, ITV & many more). He delivered keynote speech in NCVPRIPG 2019 and ICIoT 2019, and was invited speaker at: 1) Home Care Research Forum at King’s College London, 2) Alzheimer’s Research UK – Public meeting at Leeds, and 3) Palliative Care, Architecture and Designs Symposium at the University of Liverpool.

Invited talks:

Computer Vision and Deep Learning – A Marriage of Neuroscience and Machine Learning. Keynote speaker at the Seventh National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG), December 2019. Internet of Things (IoT) and Artificial Intelligence (AI) – A Marriage Made in Data. Keynote speaker at the International Conference on Internet of Things (ICIoT 2019), Chennai, India, March 2019. Computer Vision and Deep Learning – A Marriage of Neuroscience and Machine Learning. Invited speaker at the Department of Data Science, Department of Electrical Engineering, Indian Institute of Science (IISc), Bangalore, India, December 2019. The Role of Human-Robot Social Interactions in Healthcare, Social Care and Home Care of the Future. Invited speaker at the Home Care Research Forum at King’s College London, November 2018 Computer Vision in Automation and Robotics – An Opportunity or a Threat. Keynote speaker at International Conference on Emerging Trends in Engineering, Science and Technology (ICRISET 2018), Gujarat, India, December 2018 Social robotics in healthcare and overview of the CAVE at Edge Hill University. Invited speaker in Palliative Care, Architecture and Designs Symposium, University of Liverpool, November 2018 Human-Robot Social Interactions: The Future of Health and Social Care. Invited speaker in Alzheimers Research UK (ARUK) – Public meeting, University of Leeds, June 2018 Human Sensing – Enabling machines/robots to understand and characterize human activity and behavior. Invited speaker at The National University of Malaysia (Faulty of Science and Technology), August 2018 Human Activity Recognition and Monitoring. Invited speaker at Trakomatic Kuala Lumpur, Malaysia, August 2018

Research/Industrial Grants:

CRUK-PCUK-EPSRC (2021- 2022, PI) PANC-CYS-GAN: A Multimodal Longitudinal Generative Adversarial Network (GAN) to Discriminate High-risk Cysts for the Early Detection of Pancreatic Cancer (£100K) PhenomUK (2021- 2022, Co-I): DeepEarNet: Accurate Segmentation and Measurement of Cereal Grain Spikes Directly in Point Clouds Using Latest Deep Learning and Domain Knowledge (£25K). UKIERI-DST (2019- 2022, PI): CHARM: Context-aware Human Activity Recognition and Monitoring for intelligent vehicles (£195K). Royal DSM (2021- 2022, Co-I): AI approaches for process performance and product quality (£17K). Royal Society (2020 – 2021, Co-I): High resolution aerosol monitoring from Fengyun-3D MERSI-II satellite image classification to enhance air quality assessment (~£12K). Engage Liverpool (2018 – 2019, Co-I): How can architecture and technology be used to design living environments to improve quality of life for people with palliative care needs (2.5K). RITA (2016 – 2018, PI): Adaptive User Interface: Design and Development of an Eye-based Human-Computer Interaction (HCI) for People with varying Severity of Disabilities (£25K). RIF (2016 – 2018, PI): Autonomous Intelligent Feature for Reducing Driver’s Interaction by Understanding their Behaviour Pattern (£15K). RIF (2016 – 2017, Co-I): GENEActiv and Actigraph accelerometers in older adults (£7.5K).

Reviewer in :

Many top-tier conferences/journals such as CVPR, ICML, ICLR, ICCV, ECCV, NeurIPS, AAAI, BMVC, WACV, ACCV, Pattern Recognition, IEEE ITS, Neurocomputing, CVIU and many more.

Event Organization:

International Workshop (2021) on Hazard Perception in Intelligent Vehicles (HPIV) in conjunction with IEEE WACV 2022 Edge Hill University Festival of Ideas Event (2018), Human-robot Social Interactions: The future of robotics and automation in social care and support British Machine Vision Association (BMVA) Symposium on Human Activity Recognition and Monitoring , British Computer Society (BCS) London, 8th November 2017 International Workshop on Cognitive Assistive Systems: Closing the Action-Perception Loop (CAS 2012). In Conjunction with IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2012), Algarve, Portugal 2012

Member of Professional Bodies:

Association for the Advancement of Artificial Intelligence (AAAI) Institute of Electrical and Electronics Engineers (IEEE) Fellow of Higher Education Academy (FHEA) British Machine Vision Association (BMVA) Applied Vision Association (AVA) British Computer Society (MBCS) Affiliated member of International Association of Pattern Recognition (IAPR) Affiliated member of the European Coordinating Committee for Artificial Intelligence (ECAI)

Member of Research Networks:

Visual Image Interpretation in Humans and Machines ViiHM ), EPSRC Network for Biological and Computer Vision Vision and Language Integrating Vision and Language, European Network European Research Network for Cognitive Computer Vision System (ECVision), European Network

Up to date publications can be found in Google Scholar.

Press Release:

C. J. Howard, T. Troscianko, I. D. Gilchrist, A. Behera and D. C. Hogg, Waiting strategy helps street camera operators to judge suspicious events, Journal Frontiers , 22nd August 2013. Journal Frontiers

Selected Research Publications:

Z. Wharton, E. Thomas, B. Debnath and A. Behera, A Vision-based Transfer Learning Approach for Recognizing Behavioral Symptoms in People with Dementia. 15th IEEE International Conference on Advanced Video and Signal-based Surveillance (AVSS), Auckland, New Zealand, 2018 A. Behera, A. Keidel and B. Debnath, Context-driven Multi-stream LSTM (M-LSTM) for Recognizing Fine-Grained Activity of Drivers. The German Conference on Pattern Recognition (GCPR), Stuttgart, Germany, 10-12 October 2018 (Oral acceptance rate ~20%) B. Debnath, M. O’Brien, M. Yamaguchi and A. Behera, Adapting MobileNets for mobile based upper body pose estimation. 15th IEEE International Conference on Advanced Video and Signal-based Surveillance (AVSS), Auckland, New Zealand, 2018 A. Behera and A. Keidel, Latent Body-Pose guided DenseNet for Recognizing Driver’s Fine-grained Secondary Activities. 15th IEEE International Conference on Advanced Video and Signal-based Surveillance (AVSS), Auckland, New Zealand, 2018 G. Bleser, A. Behera, D. Damen, G. Hendeby, A. Gee, M. Miezal, K. Mura, N. Petersen, N. Schmitz,L. Almeida, A. Calway, W. Mayol-Cuevas, A. G. Cohn, D. C. Hogg and D. Stricker, Cognitive Learning, Monitoring and Assistance of Industrial Workflows using Egocentric Sensor Networks. PLoS ONE 10(6), doi:10.1371/journal.pone.0127769, 2015. Behera, A. G. Cohn and D. C. Hogg, Real-time Activity Recognition by Discerning Qualitative Relationships Between Randomly Chosen Visual Features. The 25th British Machine Vision Conference (BMVC) 2014, Nottingham, UK, 1-5 September 2014 (acceptance rate 30.2%). [Datasets and source codes] Behera, M. Chapman, D. C. Hogg and A. G. Cohn, Egocentric Activity Recognition using Histograms of Oriented Pairwise Relations. The 9th International Conference on Computer Vision Theory and Applications (VISAPP), Lisbon, Portugal, 5-8 January 2014 (Oral acceptance rate 17%) J. Howard, T. Troscianko, I. D. Gilchrist, A. Behera and D. C. Hogg, Suspiciousness perception in dynamic scenes: a comparison of CCTV operators and novices. Frontiers in Human Neuroscience 2013, 7:441. Ferryman, D. C. Hogg, J. Sochman, A. Behera, J. Rodriguez, S Worgan, L. Li, V. Leung, M. Evans, P. Cornic, S. Herbin, S. Schlenger, M. Dose, Robust abandoned object detection integrating wide area visual surveillance and social context. Pattern Recognition Letters 34(7), pp. 789-798, 2103. Behera, D. C. Hogg and A. G. Cohn, Egocentric Activity Monitoring and Recovery. The 11th Asian Conference on Computer Vision (ACCV), Daejeon, Korea, 5-9 November 2012 (acceptance rate 26.8%). [ Leeds Egocentric Dataset] Behera, D. C. Hogg, C. J. Howard, I. D. Gilchrist and T. Troscianko. Visual Attention-based Approach for Prediction of Abnormalities in CCTV Video Surveillance. AVA/BMVA Annual Meeting Abstract, PERCEPTION, 41(3), pp. 367-367, 2012. Behera, A. G. Cohn and D. C. Hogg, Workflow Activity Monitoring using the Dynamics of Pair-wise Qualitative Spatial Relations. International Conference on MultiMedia Modeling (MMM), Klagenfurt, Austria, 4-6 January 2012 (acceptance rate 15%). J. Howard, I. D. Gilchrist, T. Troscianko, A. Behera and D. C. Hogg, Task relevance predicts gaze in videos of real moving scenes. Experimental Brain Research, 214(1), pp 131-137, 2011. F. Worgan, A. Behera, A. G. Cohn and D. C. Hogg, Exploiting petri-net structure for activity classification and user instruction within an industrial setting. International Conference on Multimodal Interaction (ICMI), Alicante, Spain, 14-18 November 2011 (acceptance rate 39%). Behera, D. Lalanne and R. Ingold, DocMIR: An automatic document-based indexing system for meeting retrieval, International Journal of Multimedia Tools and Applications (MTAP), 37(2), pp 135-167, 2008. Behera, D. Lalanne and R. Ingold, Combining Color and Layout Features for the Identification of Low-resolution Documents, International Journal of Signal Processing (IJSP), ISSN:1304-4478, 2(1), pp. 7-14, 2005. J. Howard, I. D. Gilchrist, T. Troscianko, A. Behera and D. C. Hogg, Continuous manual responses and continuous gaze tracking during closed circuit television (CCTV) monitoring. European Conference on Eye Movements, Southampton, August 2009. J. Howard, T. Troscianko, I. D. Gilchrist, A. Behera and D. C. Hogg, Searching for threat: factors determining performance during CCTV monitoring. In D. de Waard, J. Godthelp, F.L. Kooi, and K.A. Brookhuis (Eds.). Human Factors, Security and Safety, pp. 333 – 339, 2009. Maastricht, the Netherlands: Shaker Publishing. J. Howard, I. D. Gilchrist, T. Troscianko, A. Behera and D. C. Hogg, Monitoring CCTV and watching football: expert-novice differences in the magnitude of a visuo-motor buffer, Vision Science Society Abstracts. Journal of Vision, 9(8), pp.416 – 416, 2009. J. Howard, I. D. Gilchrist, T. Troscianko, A. Behera and D. C. Hogg, Monitoring CCTV and watching football: expert-novice differences in the magnitude of a visuo-motor buffer. Vision Sciences Society Annual Meeting May 2009. Behera, D. Lalanne and R. Ingold, Influence of Fusion Strategies on Feature-based Identification of Low-resolution Documents, The ACM Symposium on Document Engineering (DocEng) 2005, 2 – 4 November, Bristol, UK, pp. 20-22 (acceptance rate 39%). Behera, D. Lalanne and R. Ingold, Enhancement of Layout-based Identification of Low-resolution Documents using Geometrical Color Distribution, International Conference on Document Analysis and Recognition (ICDAR) 2005, IEEE Computer Society, August 29-1st September, Seoul, Korea, pp. 468-472 (acceptance rate 40%). Behera, D. Lalanne and R. Ingold, Color and Layout-based Identification of Documents Captured from Low-resolution Handheld Devices, International Conference on Pattern Recognition and Computer Vision 2005, 25-27 February, Istanbul, Turkey, 2nd World Enformatika Congress, WEC’05, ISBN 975-98458-3-0, Vol 1, pp. 51-54. Behera, D. Lalanne and R. Ingold, Visual Signature based Identification of Low-resolution Document Images. The ACM Symposium on Document Engineering (DocEng) 2004, Milwaukee, Wisconsin, USA, October 28-30, 2004, pp. 178-187 (acceptance rate 36%). Behera, D. Lalanne and R. Ingold, Looking at projected documents: Event detection and Document Identification, IEEE International Conference on Multimedia and Expo (ICME) 2004, Taipei, Taiwan, June 2004, pp. 2127-2130 (acceptance rate 30%). Lalanne, R. Ingold, D. von Rotz, A. Behera, D. Mekhaldi and A. Popescu-Belis, Using static documents as structured and thematic interfaces to multimedia meeting archives. 1st International Workshop on Machine Learning for Multimodal Interaction (MLMI) 2004, Martigny, Switzerland, LNCS, Vol. 3361, pp. 87-100. Lalanne, S. Sire, R. Ingold, A. Behera, D. Mekhaldi and D. von Rotz, A research agenda for assessing the utility of document annotations in multimedia databases of meeting recordings, 3rd International Workshop on Multimedia Data and Document Engineering (MDDE), in conjunction with VLDB-2003, Berlin, Germany, pp. 47-55.