25,932 Hits in 5.5 sec

Automated Modelling of Masonry Walls: a ML and AR Approach [chapter]

Pierpaolo D'Agostino, Federico Minelli
2021 Representation Challenges. Augmented Reality and Artificial Intelligence in Cultural Heritage and Innovative Design Domain  
The implementation of the process is tested on a video sequence to simulate an augmented reality application for masonry detection.  ...  Python environment is chosen for the coding activity in order to provide automation to the process.  ...  An effective delineation of horizontal rows is obtained with robust outcomes on several frames of the video stream.  ... 
doi:10.3280/oa-686.29 fatcat:6bw24tkye5dlxkqv7grorynaeu

Special Issue on Automated Perception of Human Affect from Longitudinal Behavioral Data

Pablo Barros, Stefan Wermter, Ognjen Rudovic, Hatice Gunes
2021 IEEE Transactions on Affective Computing  
Chen and Epps propose an event-based behavior modelling, based on wearable devices, to recognize task load level on a temporally longitudinal task.  ...  Principi, Palmero, Jacques Junior and Escalera present an interesting study where they identify different subjective bias on an apparent personality analysis task.  ...  He worked on machine-learning and computer vision models for automated analysis of human facial behavior with Imperial College London.  ... 
doi:10.1109/taffc.2021.3079535 fatcat:c6ktm46rkbgptffenogw3pagwe

Detecting Drowsy Learners at the Wheel of e-Learning Platforms with Multimodal Learning Analytics

Ryosuke Kawamura, Shizuka Shirai, Noriko Takemura, Mehrasa Alizadeh, Mutlu Cukurova, Haruo Takemura, Hajime Nagahara
2021 IEEE Access  
First, we clustered features based on learners' wakefulness labels as generated by human raters and ran a statistical analysis.  ...  We achieved an average macro-F1 score of 0.82 in automated user-dependent models with CatBoost.  ...  analysis in a video-based online learning context [19] .  ... 
doi:10.1109/access.2021.3104805 fatcat:nkmz62lle5de5ph3mlnnn7dmne

Towards Automated Video Analysis of Sensorimotor Assessment Data

Ana B. Graciano Fouquier, Séverine Dubuisson, Isabelle Bloch, Anja Klöckner
2014 Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods  
Each session is recorded so that the psychomotrician can use the video as a support for reviewing in-session impressions and drawing final conclusions.  ...  It relies on playful activities which are proposed by a psychomotrician expert to the child, with the intent of observing how the latter responds to various physical and cognitive stimuli.  ...  ACKNOWLEDGEMENTS The videos used in this study were acquired with the informed consent of the parents, who agreed to the use of the data for educational and research purposes. Ana B. G.  ... 
doi:10.5220/0004912307350740 dblp:conf/icpram/FouquierDBK14 fatcat:twl5yof3r5e6djvsecamzkt5ge

When Human Coders (and Machines) Disagree on the Meaning of Facial Affect in Spontaneous Videos [chapter]

Mohammed E. Hoque, Rana el Kaliouby, Rosalind W. Picard
2009 Lecture Notes in Computer Science  
We then present an alternative labeling approach, which closely models how the majority of automated facial analysis systems are designed.  ...  This paper describes the challenges of getting ground truth affective labels for spontaneous video, and presents implications for systems such as virtual agents that have automated facial analysis capabilities  ...  Building an automated system that recognizes spontaneous facial expressions remains a challenging endeavor: human facial muscle activations can occur in over twenty thousand combinations and there is no  ... 
doi:10.1007/978-3-642-04380-2_37 fatcat:2p6y72g3cjglfcxjcn54b4iwgi

Student behavior analysis to measure engagement levels in online learning environments

Khawlah Altuwairqi, Salma Kammoun Jarraya, Arwa Allinjawi, Mohamed Hammami
2021 Signal, Image and Video Processing  
The challenge that researchers face is how to measure student engagement based on their emotions.  ...  In fact, we build new and realistic student engagement datasets to validate our contributions.  ...  Based on the multimodal approach, the engagement level detection provided more accurate results than dual and single modalities.  ... 
doi:10.1007/s11760-021-01869-7 pmid:34007342 pmcid:PMC8119613 fatcat:3mwqszh3tjdfhp2aycdgiymfby

A Study on Automatic Attention Span Detection of Students

Aditya Parashar
2021 International Journal for Research in Applied Science and Engineering Technology  
The ensemble comprises three cluster-based conventional models and one attention-based neural network model(bi-directional LSTM), boosted with heuristic posture-based rules(like hand fidgeting and body  ...  The proposed agent in this paper [6] uses an ensemble of four models to track student engagement.  ...  Therefore, it is vital to design and develop automated engagement tracking methods based on rapidly evolving computer vision (CV) and machine learning (ML) technologies. B.  ... 
doi:10.22214/ijraset.2021.34707 fatcat:e6f4eun6ujbtzaglmie3b7ho4u

It's Written on Your Face: Detecting Affective States from Facial Expressions while Learning Computer Programming [chapter]

Nigel Bosch, Yuxuan Chen, Sidney D'Mello
2014 Lecture Notes in Computer Science  
We built detectors capable of automatically recognizing affective states of novice computer programmers from student-annotated videos of their faces recorded during an introductory programming tutoring  ...  We used the Computer Expression Recognition Toolbox (CERT) to track facial features based on the Facial Action Coding System, and machine learning techniques to build classification models.  ...  [5] used multimodal data channels including facial features from video to predict Frustration in an automated learning companion.  ... 
doi:10.1007/978-3-319-07221-0_5 fatcat:tbjs3nkr4ncl3goqif6ktpoq3e

AI technologies: A key to unlock the door of Omni-channel capabilities

Vidushi and Dr. R Kashyap
2020 International journal of modern trends in science and technology  
This paper also explores the different AI technologies which can be used by retailer to manage the supply chain, data and their engagement with customers.  ...  Detection: Locates and detects human faces inimages and videos. Capture: Conversion of analog information (aface) into digital information (data) based on theperson's facial features takes place.  ...  III Positive and Negative of Speech Recognition TechnologyImage Recognition: This technology identifies and detects an object in a digital image or video.  ... 
doi:10.46501/ijmtst0609s17 fatcat:ribfcosjtbfqjigkj2v476epni

Student destraction detection Project Thesis.pdf

Zeeshan Keerio
The objective of this Project was to build an automatic system that allowed the faculties to capture and make a summary of student behaviors and detect student weather attentive or distracted in the VLE  ...  We combine information about the movements of the eyes and head, and facial emotions to produce a concentration index with three classes of engagement: "very engaged", "nominally engaged" and "not engaged  ...  Recently, plenty of methods have been proposed to build video-level representations based on CNN features.  ... 
doi:10.6084/m9.figshare.14130023.v1 fatcat:ednzq3ijrvbqfanofphdh4vyyq

Future Vision of Interactive and Intelligent TV Systems using Edge AI

Álan Guedes, Antonio Busson, João Paulo Navarro, Sérgio Colcher
This paper presents TeleMídia Lab's future vision on interactive and intelligent TV Systems, with particular focus on edge AI.  ...  One of the new features to be addressed by this future application layer is the use of Artificial Intelligence technologies.  ...  Media Analysis Methods based on Deep Learning (DL) became the stateof-the-art in various segments related to automatic media analysis.  ... 
doi:10.18580/setijbe.2020.4 fatcat:crbczniv3zaypmnfc7r7jntpsu

Building Automation and the Contextualization of Information Technology: The Journey of a Midwestern Community College in the U.S

Neal Grandgenett, Pam Perry, Thomas Pensabene, Karen Wegner, Robert Nirenberg, Phil Pilcher, Candi Otterpohl
2018 Journal of Education and Training Studies  
around the context of building automation systems (BAS).  ...  The research-based approach, activities, and outcomes of this project are all described here, as well as the lessons learned by one community college seeking to make their IT program increasingly relevant  ...  Acknowledgements The authors would like to acknowledge the three years of funding and support from the National Science Foundation's Advanced Technical Education program, which funded the Automate Project  ... 
doi:10.11114/jets.v6i2.2959 fatcat:zt2qmh47rbcftjz5xblwf3pw6y

Robust Modeling of Epistemic Mental States [article]

AKMMahbubur Rahman, ASM Iftekhar Anam, Mohammed Yeasin
2020 arXiv   pre-print
This work identifies and advances some research challenges in the analysis of facial features and their temporal dynamics with epistemic mental states in dyadic conversations.  ...  Then, we propose a novel prediction framework that takes facial features and their nonlinear relation scores as input and predict different epistemic states in videos.  ...  Then, we reported our observations and key findings followed by a proposition of a new framework based on our observations. At the end, the paper reports the performance of the proposed framework.  ... 
arXiv:2005.13982v1 fatcat:wg6h4tetpbbchebzwp5g6u4q3y

A Low Cost Outdoor Service Robot

Norma Elva Chavez, Saiph Savage, Rodrigo Savage
2017 Advances in Robotics & Automation  
Based on our design and study, we reflect on the future of low cost service robots for outdoor and indoor activities. Figure 1: Photo of Nokovic the service robot engaging outdoors.  ...  To provide service robots to everyone, everywhere, we present Nokovic, a low cost service robot built with recycled parts based on FPGA and radio frequency control that recognizes outdoor and indoor human  ...  After we have a more clean video image, we perform connected component analysis on the corresponding binarized filtered image and are able to obtain the blobs (i.e., the parts of the video where humans  ... 
doi:10.4172/2168-9695.1000168 fatcat:eyjd2tmlrfcafiwfchcdz6p3hi

Application of Audio and Video Processing Methods for Language Research and Documentation: The AVATecH Project [chapter]

Przemyslaw Lenkiewicz, Sebastian Drude, Anna Lenkiewicz, Binyam Gebrekidan Gebre, Stefano Masneri, Oliver Schreer, Jochen Schwenninger, Rolf Bardeli
2014 Lecture Notes in Computer Science  
Since creating those annotations is a very laborious task, reaching times 100 longer than the length of the annotated media, innovative video processing algorithms are needed, in order to improve the efficiency  ...  addressed by employing an HMM-based speech recognizer.  ...  It is mainly based on an optimization scheme for a selected range of U and V values in the YUV domain that belongs to human skin colour.  ... 
doi:10.1007/978-3-319-14120-6_24 fatcat:fdnkdvvvpbfu7oh2xrsebt5clu
« Previous Showing results 1 — 15 out of 25,932 results