Filters








795 Hits in 3.3 sec

A multisource fusion framework driven by user-defined knowledge for egocentric activity recognition

Haibin Yu, Wenyan Jia, Zhen Li, Feixiang Gong, Ding Yuan, Hong Zhang, Mingui Sun
2019 Zenodo  
In this paper, we present a knowledge-driven multisource fusion framework for the recognition of egocentric activities in daily living (ADL).  ...  Recently, egocentric activity recognition has attracted considerable attention in the pattern recognition and artificial intelligence communities because of its widespread applicability to human systems  ...  Our methods for ADL recognition are described in Yu Availability of data and materials The multimodal egocentric activity data used in the performance comparison is presented in [25, 26] .  ... 
doi:10.5281/zenodo.2986947 fatcat:6j47wsaxbragzidwotj4mfetka

A multisource fusion framework driven by user-defined knowledge for egocentric activity recognition

Haibin Yu, Wenyan Jia, Zhen Li, Feixiang Gong, Ding Yuan, Hong Zhang, Mingui Sun
2019 EURASIP Journal on Advances in Signal Processing  
In this paper, we present a knowledge-driven multisource fusion framework for the recognition of egocentric activities in daily living (ADL).  ...  Recently, egocentric activity recognition has attracted considerable attention in the pattern recognition and artificial intelligence communities because of its widespread applicability to human systems  ...  Our methods for ADL recognition are described in Yu Availability of data and materials The multimodal egocentric activity data used in the performance comparison is presented in [25, 26] .  ... 
doi:10.1186/s13634-019-0612-x pmid:30881444 pmcid:PMC6394646 fatcat:fk6iinaqq5gxxphu4rylk5l2y4

A multisource fusion framework driven by user-defined knowledge for egocentric activity recognition

Haibin Yu, Wenyan Jia, Zhen Li, Feixiang Gong, Ding Yuan, Hong Zhang, Mingui Sun
2019 Zenodo  
In this paper, we present a knowledge-driven multisource fusion framework for the recognition of egocentric activities in daily living (ADL).  ...  Recently, egocentric activity recognition has attracted considerable attention in the pattern recognition and artificial intelligence communities because of its widespread applicability to human systems  ...  Our methods for ADL recognition are described in Yu Availability of data and materials The multimodal egocentric activity data used in the performance comparison is presented in [25, 26] .  ... 
doi:10.5281/zenodo.2986824 fatcat:4b7fqbfn7rcjpmeqwjizyldyy4

A Survey on Recent Advances of Computer Vision Algorithms for Egocentric Video [article]

Sven Bambach
2015 arXiv   pre-print
Interestingly, the computer vision community has only recently started to explore this new domain of egocentric vision, where research can roughly be categorized into three areas: Object recognition, activity  ...  detection/recognition, video summarization.  ...  Lu and Grauman [26] extended this work by developing a story-driven (rather than object-driven) approach to summarize egocentric life logging video.  ... 
arXiv:1501.02825v1 fatcat:kkni4ccumbeapn2chqkhpr6frm

Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language [article]

Andy Zeng, Maria Attarian, Brian Ichter, Krzysztof Choromanski, Adrian Wong, Stefan Welker, Federico Tombari, Aveek Purohit, Michael Ryoo, Vikas Sindhwani, Johnny Lee, Vincent Vanhoucke (+1 others)
2022 arXiv   pre-print
As a result, these models store different forms of commonsense knowledge across different domains.  ...  ., via multimodal-informed prompting, to exchange information with each other and capture new multimodal capabilities, without requiring finetuning.  ...  We find that generating candidate activities using an LM yields more suitable descriptions of egocentric activities and interactions with first-person video, than using standard activity recognition dataset  ... 
arXiv:2204.00598v2 fatcat:sdzx7e6h2rfcbpegrnojeu37ra

Eyewear Computing – Augmenting the Human with Head-mounted Wearable Assistants (Dagstuhl Seminar 16042)

Andreas Bulling, Ozan Cakmakci, Kai Kunze, James M. Rehg, Marc Herbstritt
2016 Dagstuhl Reports  
The key results of this seminar are 1) the identification of key research challenges and summaries of breakout groups on multimodal eyewear computing, egocentric vision, security and privacy issues, skill  ...  The seminar was composed of workshops and tutorials on head-mounted eye tracking, egocentric vision, optics, and head-mounted displays.  ...  NS MEME and used them for cognitive activity recognition [3] .  ... 
doi:10.4230/dagrep.6.1.160 dblp:journals/dagstuhl-reports/BullingCKR16 fatcat:d3p4lmvat5aczhawlazkd2chpa

Overview of Lifelogging: Current Challenges and Advances

Amel Ksibi, Ala Saleh Alluhaidan, Amina Salhi, Sahar A. El-Rahman
2021 IEEE Access  
[77] proposed a process that creates object-driven summaries for egocentric videos by selecting frames that reflect the key object-driven events.  ...  [50] proposed an enhanced and realtime multimodal sensor-based activity recognition system, it was based on the fusion of vision based sensors and inertial sensors using machine learning for health  ... 
doi:10.1109/access.2021.3073469 fatcat:qm32iyh77jc43dbux6ftauhtpu

Semantic Event Fusion of Different Visual Modality Concepts for Activity Recognition

Carlos F. Crispim-Junior, Vincent Buso, Konstantinos Avgerinakis, Georgios Meditskos, Alexia Briassouli, Jenny Benois-Pineau, Ioannis Yiannis Kompatsiaris, Francois Bremond
2016 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Combining multimodal concept streams from heterogeneous sensors is a problem superficially explored for activity recognition.  ...  This paper proposes a hybrid framework between knowledge-driven and probabilistic-driven methods for event representation and recognition.  ...  [10] have proposed a hybrid approach between knowledge-driven (ontology-based) and data-driven methods for activity modeling and recognition.  ... 
doi:10.1109/tpami.2016.2537323 pmid:26955015 fatcat:b3v4qtxjtvg23lljhqy4lma6om

Embodied learning of a generative neural model for biological motion perception and inference

Fabian Schrodt, Georg Layher, Heiko Neumann, Martin V. Butz
2015 Frontiers in Computational Neuroscience  
It first learns to correlate and segment multimodal sensory streams of own bodily motion.  ...  When biological motion of another person is observed, this self-knowledge is utilized to recognize similar motion patterns and predict their progress.  ...  The model's neural activity is driven bottom-up by sets of visual and proprioceptive features.  ... 
doi:10.3389/fncom.2015.00079 pmid:26217215 pmcid:PMC4491628 fatcat:pko3lo5w7vd7tpzhb2ypdjb2oq

Toward Storytelling From Visual Lifelogging: An Overview

Marc Bolanos, Mariella Dimiccoli, Petia Radeva
2017 IEEE Transactions on Human-Machine Systems  
However, automatically building a story from a huge collection of unstructured egocentric data presents major challenges.  ...  The pictures taken offer considerable potential for knowledge mining concerning how people live their lives, hence, they open up new opportunities for many potential applications in fields including healthcare  ...  To the best of our knowledge, there is no published work on recognition of egocentric activities recorded by freely worn cameras.  ... 
doi:10.1109/thms.2016.2616296 fatcat:zbxjzfagjnhq3f2dej7poikf3m

Multimodal Deep Learning for Group Activity Recognition in Smart Office Environments

George Albert Florea, Radu-Casian Mihailescu
2020 Future Internet  
In this paper we investigate the problem of group activity recognition in office environments using a multimodal deep learning approach, by fusing audio and visual data from video.  ...  Group activity recognition is a complex classification task, given that it extends beyond identifying the activities of individuals, by focusing on the combinations of activities and the interactions between  ...  A similar example of egocentric activity recognition is introduced in [15] .  ... 
doi:10.3390/fi12080133 fatcat:hckhaqzlzjbkfhskvgvhbgodr4

Hapto-Acoustic Interaction Metaphors in 3D Virtual Environments for Non-Visual Settings [chapter]

Fabio De, Floriana Renna, Giovanni Attolico, Arcangelo Distante
2011 Virtual Reality  
At our knowledge, no works have addressed the multimodal enhancement of these metaphors in non-visual settings.  ...  HOMER yes Selection yes possible Egocentric Object in Hand yes no yes possible Egocentric Image Plane yes Selection no no Egocentric World in Miniature yes Selection/ Navigation  ...  The reviews in this book describe the latest virtual reality-related knowledge in these two fields such as: advanced human-computer interaction and virtual reality technologies, evaluation tools for cognition  ... 
doi:10.5772/13116 fatcat:2zugmvgzwvawbcerjpete7icru

Actor and Observer: Joint Modeling of First and Third-Person Videos

Gunnar A. Sigurdsson, Abhinav Gupta, Cordelia Schmid, Ali Farhadi, Karteek Alahari
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Despite this, learning such models for human action recognition has not been achievable due to the lack of data.  ...  knowledge between third-person (observer) and first-person (actor).  ...  Egocentric understanding of activities.  ... 
doi:10.1109/cvpr.2018.00772 dblp:conf/cvpr/SigurdssonGSFA18 fatcat:k2boyq34vrcp7ocgsi3fkf7ree

Sonic Interactions in Virtual Environments: the Egocentric Audio Perspective of the Digital Twin [article]

Michele Geronazzo, Stefania Serafin
2022 arXiv   pre-print
The idea of entanglement theory is here mainly declined in an egocentric-spatial perspective related to emerging knowledge of the listener's perceptual capabilities.  ...  This is an actively transformative relation with the digital twin potentials to create movement, transparency, and provocative activities in VEs.  ...  Hence, the knowledge of the perceptual-cognitive listener capabilities emerges as active transformations in multimodal digital VR experiences.  ... 
arXiv:2204.09919v1 fatcat:gzjb7fke3jca5oubltjdh4ayte

A Bayesian framework for active artificial perception

J. F. Ferreira, J. Lobo, P. Bessiere, M. Castelo-Branco, J. Dias
2013 IEEE Transactions on Cybernetics  
In this text, we present a Bayesian framework for active multimodal perception of 3D structure and motion.  ...  The computational models described in this text will support the construction of a simultaneously flexible and powerful robotic implementation of multimodal active perception to be used in real-world applications  ...  ACTIVE EXPLORATION USING BAYESIAN MODELS FOR MULTIMODAL PERCEPTION A.  ... 
doi:10.1109/tsmcb.2012.2214477 pmid:23014760 fatcat:2och4qlnavbd3f6pyy4obyne3a
« Previous Showing results 1 — 15 out of 795 results