Filters








4,141 Hits in 4.6 sec

Face Exemplars Selection from Video Streams for Online Learning

M. Castrillon-Santana, O. Deniz-Suarez, J. Lorenzo-Navarro, M. Hernandez-Tejera
The 2nd Canadian Conference on Computer and Robot Vision (CRV'05)  
Here we describe an approach to select significant detected faces during interactive sessions in order to learn and modify online, with the initial help of an expert, a classifier for a given task.  ...  This paper tackles the problem of online acquisition of exemplars for dynamic updating of classifiers for facial analysis.  ...  The extraction of significative patterns, or exemplars, is tackled in [14] . That system selects the exemplars from a single gallery video of each individual.  ... 
doi:10.1109/crv.2005.41 dblp:conf/crv/SantanaDLH05 fatcat:y6gfdop3vfew5djn3ndwss3vxi

Learning to Recognize Faces by Successive Meetings

M. Castrillón-Santana, O. Déniz-Suárez, J. Lorenzo-Navarro, M. Hernández-Tejera
2006 Journal of Multimedia  
In this paper we focus on the face recognition problem.  ...  For revisitors, the accumulated error rate decreases in both cases, reaching around 50% if no verification is included.  ...  The search of video streams for that purpose is not an easy task.  ... 
doi:10.4304/jmm.1.7.1-8 fatcat:ui4xsq7t5vanhp4ac3a5i22bli

Exemplar-Based Face Recognition from Video [chapter]

Volker Krüger, Shaohua Zhou
2002 Lecture Notes in Computer Science  
The approach has two stages: First, Exemplars, which are selected representatives from the raw video, are automatically extracted from gallery videos.  ...  A new exemplar-based probabilistic approach for face recognition in video sequences is presented.  ...  An online learning algorithm for exemplars used during testing could allow, in a bootstrapping manner, to learn new exemplars from probe videos. In [18] a similar learning approach was presented.  ... 
doi:10.1007/3-540-47979-1_49 fatcat:5xvyk3autfatjgyfd4pwfd5h5u

Becoming Visually Familiar

M. Castrillon-Santana, O. Deniz-Suarez, J. Lorenzo-Navarro, D. Hernandez-Sosa
2007 14th International Conference on Image Analysis and Processing (ICIAP 2007)  
In this paper, instead of restricting our system to a fixed and precomputed classifier, the system learns iteratively based on the experience extracted from each meeting.  ...  The experiments presented introduce the use of an exemplar average based approach.  ...  The paper describes first the mechanism for detecting faces and selecting samples from video. The representation and classification approaches are briefly presented later.  ... 
doi:10.1109/iciap.2007.4362781 dblp:conf/iciap/SantanaDLH07 fatcat:groborw2srhtlcmsuwj4ownpwy

Memory constrained face recognition

A. Kapoor, S. Baker, S. Basu, E. Horvitz
2012 2012 IEEE Conference on Computer Vision and Pattern Recognition  
We focus on computation of the expected value of information with nearest neighbor classifiers for online face recognition.  ...  We explore methods that can guide the allocation of limited storage resources for classifying streaming data so as to maximize discriminatory power.  ...  In computer vision, active learning has been employed for object categorization [17] [21], video annotation [35] , and face tagging [25] .  ... 
doi:10.1109/cvpr.2012.6247971 dblp:conf/cvpr/KapoorBBH12 fatcat:ndqs23dufrgsrgwgscz3aypbhm

Memory Based Online Learning of Deep Representations from Video Streams [article]

Federico Pernici, Federico Bartoli, Matteo Bruni, Alberto Del Bimbo
2017 arXiv   pre-print
We present a novel online unsupervised method for face identity learning from video streams.  ...  It is shown that the proposed learning procedure is asymptotically stable and can be effectively used in relevant applications like multiple face identification and tracking from unconstrained video streams  ...  Government is authorized to reproduce and distribute reprints for Governmental purpose notwithstanding any copyright annotation thereon.  ... 
arXiv:1711.07368v1 fatcat:vovw2my3b5c7fd2veift2p7xqa

Memory Based Online Learning of Deep Representations from Video Streams

Federico Pernici, Federico Bartoli, Matteo Bruni, Alberto Del Bimbo
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
We present a novel online unsupervised method for face identity learning from video streams.  ...  It is shown that the proposed learning procedure is asymptotically stable and can be effectively used in relevant applications like multiple face identification and tracking from unconstrained video streams  ...  In this paper, we present a novel online unsupervised method for face identity learning from unconstrained video streams.  ... 
doi:10.1109/cvpr.2018.00247 dblp:conf/cvpr/PerniciBBB18 fatcat:gjcpxqnyfre27lb52ahitgybxm

Formative Assessment as an Online Instruction Intervention

Zexuan Chen, Jianli Jiao, Kexin Hu
2021 International Journal of Distance Education Technologies  
Data were collected from the first five weeks of a course that was temporarily converted from blended learning to be fully online in time of school closure.  ...  Online education has long been suffering from high dropout rate and low achievement.  ...  course and replacing previous face-to-face sections with regular live streaming meetings (synchronous online).  ... 
doi:10.4018/ijdet.20210101.oa1 fatcat:3yeta2j2hrda7me7oq4lqle2da

Using a Product Manifold distance for unsupervised action recognition

Stephen O'Hara, Yui Man Lui, Bruce A. Draper
2012 Image and Vision Computing  
In the second part of this paper, we present an unsupervised mechanism for learning micro-actions in continuous video streams using the PM representation.  ...  This paper presents a method for unsupervised learning and recognition of human actions in video.  ...  Acknowledgments We would like to thank Piotr Dollár for the Bag-of-Features code he has made available.  ... 
doi:10.1016/j.imavis.2011.11.001 fatcat:62bakb2y2vfwzexlw5g4ah4zvq

Label-Efficient Online Continual Object Detection in Streaming Video [article]

Jay Zhangjie Wu, David Junhao Zhang, Wynne Hsu, Mengmi Zhang, Mike Zheng Shou
2022 arXiv   pre-print
Here, we examine a more realistic and challenging problemx2014Label-Efficient Online Continual Object Detection (LEOCOD) in video streams.  ...  Like humans, Efficient-CLS learns to detect new object classes incrementally from a continuous temporal stream of non-repeating video with minimal forgetting.  ...  ., OAK [27] and EgoObjects [9] for online continual object detection on video streams.  ... 
arXiv:2206.00309v1 fatcat:kflcn2gptvhnvaky65qwts5eke

Experiential Education Conference at Stellenbosch University, South Africa, 10–11 November 2020

Ruth Andrews
2020 Journal of Student Affairs in Africa  
The SUEEC offered two online modalities: video-streaming of pre-recorded content, and live-streaming of live-recorded engagement.  ...  Reflecting the understanding that experiential learning is a philosophy rather than a methodology, the SUEEC emphasis was on exploring experiential learning as lived reality in various contexts from across  ...  Authors were granted the opportunity to amend their virtual submissions based on feedback before final submission of a video-streamed paper presentation.  ... 
doi:10.24085/jsaa.v8i2.4453 fatcat:mgpgbzq4dfeh7iyfcb6cl4dg4a

Visual Robotic Perception System with Incremental Learning for Child–Robot Interaction Scenarios

Niki Efthymiou, Panagiotis Paraskevas Filntisis, Gerasimos Potamianos, Petros Maragos
2021 Technologies  
This paper proposes a novel lightweight visual perception system with Incremental Learning (IL), tailored to child–robot interaction scenarios.  ...  Finally, we demonstrate the robustness and effectiveness of the IL system for action recognition by conducting a thorough experimental analysis for various conditions and parameters.  ...  Simple random sampling is used to select the exemplars that are held out from each class.  ... 
doi:10.3390/technologies9040086 fatcat:npztklczwfghrcgdrsqg2pakha

Developing a Solution for Hybrid Classroom: A Pilot Study From a Malaysian Private University

Enna Ayub, Lim Chee Leong, Donny Chuan Hoe Yeo, Siti Ramadhaniatun Ismail
2022 Frontiers in Education  
The COVID-19 pandemic brought about an opportunity for higher education institutions (HEI) to explore modes of education delivery other than face-to-face (F2F) and remote learning via fully online mode  ...  The "pandemic pedagogy" based on real-life needs can be an opportunity to scale up learning for borderless learning in the future.  ...  ACKNOWLEDGMENTS We are grateful for the support from the higher management of the Centre for Future Learning (eLA) and Faculty of Social Sciences and Leisure Management and the chef instructors for the  ... 
doi:10.3389/feduc.2022.841363 fatcat:qgmlo323f5ggbo5wa7zzybasd4

Learning feed-forward one-shot learners [article]

Luca Bertinetto, João F. Henriques, Jack Valmadre, Philip H. S. Torr, Andrea Vedaldi
2016 arXiv   pre-print
We demonstrate encouraging results by learning characters from single exemplars in Omniglot, and by tracking visual objects from a single initial exemplar in the Visual Object Tracking benchmark.  ...  Discriminative methods based on deep learning, which are very effective in other learning scenarios, are ill-suited for one-shot learning as they need large amounts of training data.  ...  The best architecture reduced the error from 37.3% for a siamese network with shared parameters to 28.6% for a single-stream learnet.  ... 
arXiv:1606.05233v1 fatcat:yokwlepezjcsnmafmra72dl76y

Visual search performance in 'CCTV' and mobile phone-like video footage

Viktoria R. Mileva, Peter J. B. Hancock, Stephen R. H. Langton
2021 Cognitive Research  
In Experiment 1, videos were taken from above and at a distance to simulate CCTV, and images of the target showed their face and torso.  ...  In Experiment 2, videos were taken from approximately shoulder height, such as one would expect from body-camera or mobile phone recordings, and target images included only the face.  ...  Acknowledgements We would like to thank Megan Taylor and Emily Maclean (Experiment 1); and Kathryn Bland, Emma Clark, and Havana Russell (Experiment 2) for their help in collecting data and recruiting  ... 
doi:10.1186/s41235-021-00326-w pmid:34559334 fatcat:3o56tekoevhitjvt6xscoyplvu
« Previous Showing results 1 — 15 out of 4,141 results