Filters








613 Hits in 8.3 sec

Take an Emotion Walk: Perceiving Emotions from Gaits Using Hierarchical Attention Pooling and Affective Mapping [article]

Uttaran Bhattacharya, Christian Roncal, Trisha Mittal, Rohan Chandra, Kyra Kapsaskis, Kurt Gray, Aniket Bera, Dinesh Manocha
2020 arXiv   pre-print
We present an autoencoder-based semi-supervised approach to classify perceived human emotions from walking styles obtained from videos or motion-captured data and represented as sequences of 3D poses.  ...  We outperform current state-of-art algorithms for both emotion recognition and action recognition from 3D gaits by 7%--23% on the absolute.  ...  Decoder with Hierarchical Attention Un-pooling The decoder takes in the embedding from the encoder, repeats it five times for un-pooling, and passes the repeated features through five linear layers.  ... 
arXiv:1911.08708v2 fatcat:p74fnpengjb5jcyjw6rkji7xwe

TNTC: two-stream network with transformer-based complementarity for gait-based emotion recognition [article]

Chuanfei Hu, Weijie Sheng, Bo Dong, Xinde Li
2021 arXiv   pre-print
The popular pipeline is to first extract affective features from joint skeletons, and then aggregate the skeleton joint and affective features as the feature vector for classifying the emotion.  ...  Recently, gait-based emotion recognition, especially gait skeletons-based characteristic, has attracted much attention, while many available methods have been proposed gradually.  ...  The average attention maps in TCMs of different instances are ordered by four categories from happy, sad, angry to neutral.  ... 
arXiv:2110.13708v1 fatcat:keqs4d7svjf5xn6ni5tbbmgxri

Reliability and feasibility of the six minute walk test in subjects with myotonic dystrophy

Marie Kierkegaard, Anna Tollbäck
2007 Neuromuscular Disorders  
They were also to take at least one brisk 30-minute walk every week, and to document these in an exercise diary.  ...  a cardiologist to take part in an exercise programme.  ...  up, grasping) d445* Hand and arm use d4500* Walking short distances d4501* Walking long distances d4502* Walking on different surfaces d4503* Walking around obstacles d4551* Climbing d4552* Running d4600  ... 
doi:10.1016/j.nmd.2007.08.003 pmid:17869516 fatcat:untpep7j3jbgxebtpzqb5n7sia

Thinking, Walking, Talking: Integratory Motor and Cognitive Brain Function

Gerry Leisman, Ahmed Moustafa, Tal Shafir
2016 Frontiers in Public Health  
Data for face-and leg-related words were subtracted from arm-related words. The circles on the left represent the head from above (nose = up; left = left).  ...  The view from the top is shown on the left and a lateral view on the left hemisphere is presented on the right. Stronger ingoing potentials for face (leg) words are specified in blue (red).  ...  own emotions (138) .  ... 
doi:10.3389/fpubh.2016.00094 pmid:27252937 pmcid:PMC4879139 fatcat:5slkniq4pvalviygipvwmmg27i

Emotion Recognition from Multiple Modalities: Fundamentals and Methodologies [article]

Sicheng Zhao, Guoli Jia, Jufeng Yang, Guiguang Ding, Kurt Keutzer
2021 arXiv   pre-print
In this tutorial, we discuss several key aspects of multi-modal emotion recognition (MER). We begin with a brief introduction on widely used emotion representation models and affective modalities.  ...  Furthermore, we present some representative approaches on representation learning of each affective modality, feature fusion of different affective modalities, classifier optimization for MER, and domain  ...  Similar to action, emotions can be perceived from a person's gait, i.e., their walking style.  ... 
arXiv:2108.10152v1 fatcat:hwnq7hoiqba3pdf6aakcxjq33i

Towards Explainable, Privacy-Preserved Human-Motion Affect Recognition [article]

Matthew Malek-Podjaski, Fani Deligianni
2021 arXiv   pre-print
Since perceptions of emotions are also interleaved with body posture and movements, emotion recognition from human gait can be used to quantitatively monitor mood changes.  ...  By disentangling subject biometrics from the gait data, we show that the subject's privacy is preserved while the affect recognition performance outperforms traditional methods.  ...  Gait Emotion Characteristics Extensive research has been done into manually extracted features from human motion in order to understand how humans perceive emotion from body language.  ... 
arXiv:2105.03958v2 fatcat:er4dcdi3hrfzdb66qwz73yjhbu

Deep Learning Analysis of Mobile Physiological, Environmental and Location Sensor Data for Emotion Detection

Eiman Kanjo, Eman M.G. Younis, Chee Siang Ang
2018 Information Fusion  
The version in the Kent Academic Repository may differ from the final published version. Users are advised to check http://kar.kent.ac.uk for the status of the paper.  ...  EEG data, air quality), and then build an emotion map using our model on mobile devices along with the sensors. Fig. 2 . 2 Fig. 2.  ...  In other words, RNNs take as their input not just the current input data they see, but also what they perceived one step back in time.  ... 
doi:10.1016/j.inffus.2018.09.001 fatcat:di56h2kpcjcdhondjlyghm2gai

Neurorobots as a Means Toward Neuroethology and Explainable AI

Kexin Chen, Tiffany Hwu, Hirak J. Kashyap, Jeffrey L. Krichmar, Kenneth Stewart, Jinwei Xing, Xinyun Zou
2020 Frontiers in Neurorobotics  
how the robot's behavior arises from artificial brain activity.  ...  We suggest that using neurorobots as a form of computational neuroethology can be a powerful methodology for understanding neuroscience, as well as for artificial intelligence and machine learning.  ...  AUTHOR CONTRIBUTIONS All authors listed have made a substantial, direct and intellectual contribution to the work, and approved it for publication.  ... 
doi:10.3389/fnbot.2020.570308 pmid:33192435 pmcid:PMC7604467 fatcat:37v42xxymbfuznceh4gofmuawy

Deep Learning for Monitoring of Human Gait: A Review

Abdullah S Alharthi, Syed U Yunas, Krikor B Ozanyan
2019 IEEE Sensors Journal  
In the light of the discussed character of gait data, this is attributed to the possibility to extract the gait features automatically in deep learning as opposed to the shallow learning from the handcrafted  ...  data and the motivation for multi-sensor, multi-modality fusion.  ...  Gait Parameters Gait can be perceived as a transformation of a brain activity to muscle contraction patterns resulting in a walking sequence.  ... 
doi:10.1109/jsen.2019.2928777 fatcat:seb7vcs77bae7ixbpkajo3ysee

Survey on Emotional Body Gesture Recognition

Fatemeh Noroozi, Dorota Kaminska, Ciprian Corneanu, Tomasz Sapinski, Sergio Escalera, Gholamreza Anbarjafari
2019 IEEE Transactions on Affective Computing  
We then comment the recent literature related to representation learning and emotion recognition from images of emotionally expressive gestures.  ...  While works based on facial expressions or speech abound, recognising affect from body gestures remains a less explored topic.  ...  [122] proposed a method for emotion recognition from human gait using Microsoft Kinect cameras.  ... 
doi:10.1109/taffc.2018.2874986 fatcat:zjnr2w4orje7vj2bhmia4f5qki

Human Non-linguistic Vocal Repertoire: Call Types and Their Meaning

Andrey Anikin, Rasmus Bååth, Tomas Persson
2017 Journal of nonverbal behavior  
The repertoire of human nonverbal vocalizations as acoustic types, and the mapping between acoustic and emotional categories, thus remain underexplored.  ...  The association between call type and perceived emotion was systematic but non-redundant: listeners associated every call type with a limited, but in some cases relatively wide, range of emotions.  ...  Acknowledgements We would like to thank Can Kabadayi, Judith Hall, and two anonymous reviewers for their useful comments on the manuscript.  ... 
doi:10.1007/s10919-017-0267-y pmid:29497221 pmcid:PMC5816134 fatcat:uzza3jm4lfh2xol6w6xzdqmhue

North American Society for the Psychology of Sport and Physical Activity Virtual Conference June 11–12, 2020

2020 Journal of Sport & Exercise Psychology (JSEP)  
processing) on performance and attentional reserve (i.e., pool of available attentional resources).  ...  Thus, side-by-side walking may be an effective intervention to improve gait.  ...  Emotional regulation may be a viable self-control training strategy to avoid declines in self-control over an academic semester and sport season for optimal performance in both contexts.  ... 
doi:10.1123/jsep.2020-0172 fatcat:7ap7mzw3rfcf5f5jfqwzhruj4y

State of the Art of Audio- and Video-Based Solutions for AAL

Slavisa ALeksic, Michael Atanasov, Jean Calleja Agius, Kenneth Camilleri, Anto Čartolovni, Pau Climent-Pérez, Sara Colantonio, Stefania Cristina, Vladimir Despotovic, Hazım Kemal Ekenel, Ekrem Erakin, Francisco Florez-Revuelta (+27 others)
2022 Zenodo  
They are designed to provide support in daily life in an invisible, unobtrusive and user-friendly manner.  ...  The recent COVID-19 pandemic has stressed this situation even further, thus highlighting the need for taking action.  ...  The work in [IV.188] presents a method to recognise emotions from facial movements and gestures, which uses a complex deep neural network able to process spatio-temporal hierarchical features.  ... 
doi:10.5281/zenodo.6390708 fatcat:6qfwqd2v2rhe5iuu5zgz77ay4i

Proceedings of the 4th IPLeiria's International Health Congress

2018 BMC Health Services Research  
In other words, practice-based research has been used to gain new knowledge partly by means of practice and the outcomes of that practice [2].  ...  This type of research is an integral part of teaching and curricular assignments in the healthcare settings in the Netherlands and Germany, and particularly at universities of applied sciences.  ...  It is also part of the MIND&GAIT project Promoting independent living in frail older adults by improving cognition and gait ability and using assistive products, which is a Portuguese project with the  ... 
doi:10.1186/s12913-018-3444-8 fatcat:x4fr2u5utbebfadmobuvpniqxy

The Embodied Brain of SOVEREIGN2: From Space-Variant Conscious Percepts During Visual Search and Navigation to Learning Invariant Object Categories and Cognitive-Emotional Plans for Acquiring Valued Goals

Stephen Grossberg
2019 Frontiers in Computational Neuroscience  
Social cognitive joint attention enables imitation learning of skills by learners who observe teachers from different spatial vantage points.  ...  Cumulative movement estimates are derived from visual and vestibular cues.  ...  To help guide the development of a legged robot, neural network models have shown how leg movements can be performed with different gaits, such as walk or run in bipeds, and walk, trot, pace, and gallop  ... 
doi:10.3389/fncom.2019.00036 pmid:31333437 pmcid:PMC6620614 fatcat:6igudrojjrarjeldiw6on4pwxy
« Previous Showing results 1 — 15 out of 613 results